Prompting¶
The following endpoints outline how to manage prompts.
GET /api/v2/genai/chatPrompts/¶
List chat prompts.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| playgroundId | query | any | false | Only retrieve the chat prompts associated with this playground ID. |
| llmBlueprintId | query | any | false | Only retrieve the chat prompts associated with this LLM blueprint ID. If specified, will retrieve the chat prompts for the oldest chat in this LLM blueprint. |
| chatId | query | any | false | Only retrieve the chat prompts associated with this chat ID. |
| offset | query | integer | false | Skip the specified number of values. |
| limit | query | integer | false | Retrieve only the specified number of values. |
Example responses¶
200 Response
{
"description": "Paginated list of chat prompts.",
"properties": {
"count": {
"description": "The number of records on this page.",
"title": "count",
"type": "integer"
},
"data": {
"description": "The list of records.",
"items": {
"description": "API response object for a single chat prompt.",
"properties": {
"chatContextId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the chat context for this prompt.",
"title": "chatContextId"
},
"chatId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the chat this chat prompt belongs to.",
"title": "chatId"
},
"chatPromptIdsIncludedInHistory": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of IDs of the chat prompts included in this prompt's history.",
"title": "chatPromptIdsIncludedInHistory"
},
"citations": {
"description": "The list of relevant vector database citations (in case of using a vector database).",
"items": {
"description": "API response object for a single vector database citation.",
"properties": {
"chunkId": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The ID of the chunk in the vector database index.",
"title": "chunkId"
},
"metadata": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "LangChain Document metadata information holder.",
"title": "metadata"
},
"page": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The source page number where the citation was found.",
"title": "page"
},
"similarityScore": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The similarity score between the citation and the user prompt.",
"title": "similarityScore"
},
"source": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The source of the citation (e.g., a filename in the original dataset).",
"title": "source"
},
"startIndex": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The chunk's start character index in the source document.",
"title": "startIndex"
},
"text": {
"description": "The text of the citation.",
"title": "text",
"type": "string"
}
},
"required": [
"text",
"source"
],
"title": "Citation",
"type": "object"
},
"title": "citations",
"type": "array"
},
"confidenceScores": {
"anyOf": [
{
"description": "API response object for confidence scores.",
"properties": {
"bleu": {
"description": "BLEU score.",
"title": "bleu",
"type": "number"
},
"meteor": {
"description": "METEOR score.",
"title": "meteor",
"type": "number"
},
"rouge": {
"description": "ROUGE score.",
"title": "rouge",
"type": "number"
}
},
"required": [
"rouge",
"meteor",
"bleu"
],
"title": "ConfidenceScores",
"type": "object"
},
{
"type": "null"
}
],
"description": "The confidence scores that measure the similarity between the prompt context and the prompt completion."
},
"creationDate": {
"description": "The creation date of the chat prompt (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created the chat prompt.",
"title": "creationUserId",
"type": "string"
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"id": {
"description": "The ID of the chat prompt.",
"title": "id",
"type": "string"
},
"llmBlueprintId": {
"description": "The ID of the LLM blueprint the chat prompt belongs to.",
"title": "llmBlueprintId",
"type": "string"
},
"llmId": {
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
"llmSettings": {
"anyOf": [
{
"additionalProperties": false,
"description": "The settings that are available for all non-custom LLMs.",
"properties": {
"maxCompletionLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Maximum number of tokens allowed in the completion. The combined count of this value and prompt tokens must be below the model's maximum context size, where prompt token count is comprised of system prompt, user prompt, recent chat history, and vector database citations.",
"title": "maxCompletionLength"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Temperature controls the randomness of model output, where higher values return more diverse output and lower values return more deterministic results.",
"title": "temperature"
},
"topP": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Top P sets a threshold that controls the selection of words included in the response, based on a cumulative probability cutoff for token selection. For example, 0.2 considers only the top 20% probability mass. Higher numbers return more diverse options for outputs.",
"title": "topP"
}
},
"title": "CommonLLMSettings",
"type": "object"
},
{
"additionalProperties": false,
"description": "The settings that are available for custom model LLMs.",
"properties": {
"externalLlmContextSize": {
"anyOf": [
{
"maximum": 128000,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The external LLM's context size, in tokens. This value is only used for pruning documents supplied to the LLM when a vector database is associated with the LLM blueprint. It does not affect the external LLM's actual context size in any way and is not supplied to the LLM.",
"title": "externalLlmContextSize"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model LLM.",
"title": "validationId"
}
},
"title": "CustomModelLLMSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of LLM settings.",
"title": "llmSettings"
},
"metadataFilter": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "The metadata dictionary defining the filters that documents must match in order to be retrieved.",
"title": "metadataFilter"
},
"resultMetadata": {
"anyOf": [
{
"description": "The additional information about prompt execution results.",
"properties": {
"blockedResultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The message to replace the result text if it is non empty, which represents a blocked response.",
"title": "blockedResultText"
},
"cost": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The estimated cost of executing the prompt.",
"title": "cost"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message for the prompt (in case of an errored prompt).",
"title": "errorMessage"
},
"estimatedDocsTokenCount": {
"default": 0,
"description": "The estimated number of tokens in the documents retrieved from the vector database.",
"title": "estimatedDocsTokenCount",
"type": "integer"
},
"feedbackResult": {
"description": "Prompt feedback included in the result metadata.",
"properties": {
"negativeUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is negative.",
"items": {
"type": "string"
},
"title": "negativeUserIds",
"type": "array"
},
"positiveUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is positive.",
"items": {
"type": "string"
},
"title": "positiveUserIds",
"type": "array"
}
},
"title": "FeedbackResult",
"type": "object"
},
"finalPrompt": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
]
},
"type": "object"
},
"type": "array"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
"type": "array"
},
{
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
{
"type": "null"
}
],
"description": "The final representation of the prompt that was submitted to the LLM.",
"title": "finalPrompt"
},
"inputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM input. This number includes the tokens in the system prompt, the user prompt, the chat history (for history-aware chats) and the documents retrieved from the vector database (in case of using a vector database).",
"title": "inputTokenCount",
"type": "integer"
},
"latencyMilliseconds": {
"description": "The latency of the LLM response (in milliseconds).",
"title": "latencyMilliseconds",
"type": "integer"
},
"metrics": {
"default": [],
"description": "The evaluation metrics for the prompt.",
"items": {
"description": "Prompt metric metadata.",
"properties": {
"costConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the cost configuration.",
"title": "costConfigurationId"
},
"customModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model used for the metric.",
"title": "customModelId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the metric computation.",
"title": "errorMessage"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset configuration.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database."
},
"formattedName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted name of the metric.",
"title": "formattedName"
},
"formattedValue": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted value of the metric.",
"title": "formattedValue"
},
"llmIsDeprecated": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "llmIsDeprecated"
},
"name": {
"description": "The name of the metric.",
"title": "name",
"type": "string"
},
"nemoMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the NeMo Pipeline configuration.",
"title": "nemoMetricId"
},
"ootbMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the OOTB metric configuration.",
"title": "ootbMetricId"
},
"sidecarModelMetricValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the sidecar model validation(in case of using a sidecar model deployment for the metric).",
"title": "sidecarModelMetricValidationId"
},
"stage": {
"anyOf": [
{
"description": "Enum that describes at which stage the metric may be calculated.",
"enum": [
"prompt_pipeline",
"response_pipeline"
],
"title": "PipelineStage",
"type": "string"
},
{
"type": "null"
}
],
"description": "The stage (prompt or response) that the metric applies to."
},
"value": {
"description": "The value of the metric.",
"title": "value"
}
},
"required": [
"name",
"value"
],
"title": "MetricMetadata",
"type": "object"
},
"title": "metrics",
"type": "array"
},
"outputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM output.",
"title": "outputTokenCount",
"type": "integer"
},
"providerLLMGuards": {
"anyOf": [
{
"items": {
"description": "Info on the provider guard metrics.",
"properties": {
"name": {
"description": "The name of the provider guard metric.",
"title": "name",
"type": "string"
},
"satisfyCriteria": {
"description": "Whether the configured provider guard metric satisfied its hidden internal guard criteria.",
"title": "satisfyCriteria",
"type": "boolean"
},
"stage": {
"description": "The data stage where the provider guard metric is acting upon.",
"enum": [
"prompt",
"response"
],
"title": "ProviderGuardStage",
"type": "string"
},
"value": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The value of the provider guard metric.",
"title": "value"
}
},
"required": [
"satisfyCriteria",
"name",
"value",
"stage"
],
"title": "ProviderGuardsMetadata",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The provider llm guards metadata.",
"title": "providerLLMGuards"
},
"totalTokenCount": {
"default": 0,
"description": "The combined number of tokens in the LLM input and output.",
"title": "totalTokenCount",
"type": "integer"
}
},
"required": [
"latencyMilliseconds"
],
"title": "ResultMetadata",
"type": "object"
},
{
"type": "null"
}
],
"description": "The additional information about the chat prompt results."
},
"resultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The text of the prompt completion.",
"title": "resultText"
},
"text": {
"description": "The text of the user prompt.",
"title": "text",
"type": "string"
},
"userName": {
"description": "The name of the user that created the chat prompt.",
"title": "userName",
"type": "string"
},
"vectorDatabaseFamilyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database family this chat prompt belongs to.",
"title": "vectorDatabaseFamilyId"
},
"vectorDatabaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database linked to this LLM blueprint.",
"title": "vectorDatabaseId"
},
"vectorDatabaseSettings": {
"anyOf": [
{
"description": "Vector database retrieval settings.",
"properties": {
"addNeighborChunks": {
"default": false,
"description": "Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1.",
"title": "addNeighborChunks",
"type": "boolean"
},
"maxDocumentsRetrievedPerPrompt": {
"anyOf": [
{
"maximum": 10,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of chunks to retrieve from the vector database.",
"title": "maxDocumentsRetrievedPerPrompt"
},
"maxTokens": {
"anyOf": [
{
"maximum": 51200,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of tokens to retrieve from the vector database.",
"title": "maxTokens"
},
"retriever": {
"description": "The method used to retrieve relevant chunks from the vector database.",
"enum": [
"SINGLE_LOOKUP_RETRIEVER",
"CONVERSATIONAL_RETRIEVER",
"MULTI_STEP_RETRIEVER"
],
"title": "VectorDatabaseRetrievers",
"type": "string"
}
},
"title": "VectorDatabaseSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of vector database settings."
}
},
"required": [
"llmId",
"id",
"text",
"llmBlueprintId",
"creationDate",
"creationUserId",
"userName",
"resultMetadata",
"resultText",
"confidenceScores",
"citations",
"executionStatus"
],
"title": "ChatPromptResponse",
"type": "object"
},
"title": "data",
"type": "array"
},
"next": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the next page, or `null` if there is no such page.",
"title": "next"
},
"previous": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the previous page, or `null` if there is no such page.",
"title": "previous"
},
"totalCount": {
"description": "The total number of records.",
"title": "totalCount",
"type": "integer"
}
},
"required": [
"totalCount",
"count",
"next",
"previous",
"data"
],
"title": "ListChatPromptsResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Successful Response | ListChatPromptsResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
POST /api/v2/genai/chatPrompts/¶
Request the execution of a new prompt within a chat or an LLM blueprint.
Body parameter¶
{
"description": "The body of the \"Create chat prompt\" request.",
"properties": {
"chatId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the chat this prompt belongs to. If LLM and vector database settings are not specified in the request, then the prompt will use the current settings of the chat.",
"title": "chatId"
},
"llmBlueprintId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the LLM blueprint this prompt belongs to. If LLM and vector database settings are not specified in the request, then the prompt will use the current settings of the LLM blueprint.",
"title": "llmBlueprintId"
},
"llmId": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "If specified, uses this LLM ID for the prompt and updates the settings of the corresponding chat or LLM blueprint to use this LLM ID."
},
"llmSettings": {
"anyOf": [
{
"additionalProperties": false,
"description": "The settings that are available for all non-custom LLMs.",
"properties": {
"maxCompletionLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Maximum number of tokens allowed in the completion. The combined count of this value and prompt tokens must be below the model's maximum context size, where prompt token count is comprised of system prompt, user prompt, recent chat history, and vector database citations.",
"title": "maxCompletionLength"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Temperature controls the randomness of model output, where higher values return more diverse output and lower values return more deterministic results.",
"title": "temperature"
},
"topP": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Top P sets a threshold that controls the selection of words included in the response, based on a cumulative probability cutoff for token selection. For example, 0.2 considers only the top 20% probability mass. Higher numbers return more diverse options for outputs.",
"title": "topP"
}
},
"title": "CommonLLMSettings",
"type": "object"
},
{
"additionalProperties": false,
"description": "The settings that are available for custom model LLMs.",
"properties": {
"externalLlmContextSize": {
"anyOf": [
{
"maximum": 128000,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The external LLM's context size, in tokens. This value is only used for pruning documents supplied to the LLM when a vector database is associated with the LLM blueprint. It does not affect the external LLM's actual context size in any way and is not supplied to the LLM.",
"title": "externalLlmContextSize"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model LLM.",
"title": "validationId"
}
},
"title": "CustomModelLLMSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "If specified, uses these LLM settings for the prompt and updates the settings of the corresponding chat or LLM blueprint to use these LLM settings.",
"title": "llmSettings"
},
"metadataFilter": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "The metadata fields to add to the chat prompt.",
"title": "metadataFilter"
},
"text": {
"description": "The text of the user prompt.",
"maxLength": 500000,
"title": "text",
"type": "string"
},
"vectorDatabaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "If specified, uses this vector database ID for the prompt and updates the settings of the corresponding chat or LLM blueprint to use this vector database ID.",
"title": "vectorDatabaseId"
},
"vectorDatabaseSettings": {
"anyOf": [
{
"description": "Vector database retrieval settings.",
"properties": {
"addNeighborChunks": {
"default": false,
"description": "Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1.",
"title": "addNeighborChunks",
"type": "boolean"
},
"maxDocumentsRetrievedPerPrompt": {
"anyOf": [
{
"maximum": 10,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of chunks to retrieve from the vector database.",
"title": "maxDocumentsRetrievedPerPrompt"
},
"maxTokens": {
"anyOf": [
{
"maximum": 51200,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of tokens to retrieve from the vector database.",
"title": "maxTokens"
},
"retriever": {
"description": "The method used to retrieve relevant chunks from the vector database.",
"enum": [
"SINGLE_LOOKUP_RETRIEVER",
"CONVERSATIONAL_RETRIEVER",
"MULTI_STEP_RETRIEVER"
],
"title": "VectorDatabaseRetrievers",
"type": "string"
}
},
"title": "VectorDatabaseSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "If specified, uses these vector database settings for the prompt and updates the settings of the corresponding chat or LLM blueprint to use these vector database settings."
}
},
"required": [
"text"
],
"title": "CreateChatPromptRequest",
"type": "object"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| body | body | CreateChatPromptRequest | true | none |
Example responses¶
202 Response
{
"description": "API response object for a single chat prompt.",
"properties": {
"chatContextId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the chat context for this prompt.",
"title": "chatContextId"
},
"chatId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the chat this chat prompt belongs to.",
"title": "chatId"
},
"chatPromptIdsIncludedInHistory": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of IDs of the chat prompts included in this prompt's history.",
"title": "chatPromptIdsIncludedInHistory"
},
"citations": {
"description": "The list of relevant vector database citations (in case of using a vector database).",
"items": {
"description": "API response object for a single vector database citation.",
"properties": {
"chunkId": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The ID of the chunk in the vector database index.",
"title": "chunkId"
},
"metadata": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "LangChain Document metadata information holder.",
"title": "metadata"
},
"page": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The source page number where the citation was found.",
"title": "page"
},
"similarityScore": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The similarity score between the citation and the user prompt.",
"title": "similarityScore"
},
"source": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The source of the citation (e.g., a filename in the original dataset).",
"title": "source"
},
"startIndex": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The chunk's start character index in the source document.",
"title": "startIndex"
},
"text": {
"description": "The text of the citation.",
"title": "text",
"type": "string"
}
},
"required": [
"text",
"source"
],
"title": "Citation",
"type": "object"
},
"title": "citations",
"type": "array"
},
"confidenceScores": {
"anyOf": [
{
"description": "API response object for confidence scores.",
"properties": {
"bleu": {
"description": "BLEU score.",
"title": "bleu",
"type": "number"
},
"meteor": {
"description": "METEOR score.",
"title": "meteor",
"type": "number"
},
"rouge": {
"description": "ROUGE score.",
"title": "rouge",
"type": "number"
}
},
"required": [
"rouge",
"meteor",
"bleu"
],
"title": "ConfidenceScores",
"type": "object"
},
{
"type": "null"
}
],
"description": "The confidence scores that measure the similarity between the prompt context and the prompt completion."
},
"creationDate": {
"description": "The creation date of the chat prompt (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created the chat prompt.",
"title": "creationUserId",
"type": "string"
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"id": {
"description": "The ID of the chat prompt.",
"title": "id",
"type": "string"
},
"llmBlueprintId": {
"description": "The ID of the LLM blueprint the chat prompt belongs to.",
"title": "llmBlueprintId",
"type": "string"
},
"llmId": {
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
"llmSettings": {
"anyOf": [
{
"additionalProperties": false,
"description": "The settings that are available for all non-custom LLMs.",
"properties": {
"maxCompletionLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Maximum number of tokens allowed in the completion. The combined count of this value and prompt tokens must be below the model's maximum context size, where prompt token count is comprised of system prompt, user prompt, recent chat history, and vector database citations.",
"title": "maxCompletionLength"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Temperature controls the randomness of model output, where higher values return more diverse output and lower values return more deterministic results.",
"title": "temperature"
},
"topP": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Top P sets a threshold that controls the selection of words included in the response, based on a cumulative probability cutoff for token selection. For example, 0.2 considers only the top 20% probability mass. Higher numbers return more diverse options for outputs.",
"title": "topP"
}
},
"title": "CommonLLMSettings",
"type": "object"
},
{
"additionalProperties": false,
"description": "The settings that are available for custom model LLMs.",
"properties": {
"externalLlmContextSize": {
"anyOf": [
{
"maximum": 128000,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The external LLM's context size, in tokens. This value is only used for pruning documents supplied to the LLM when a vector database is associated with the LLM blueprint. It does not affect the external LLM's actual context size in any way and is not supplied to the LLM.",
"title": "externalLlmContextSize"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model LLM.",
"title": "validationId"
}
},
"title": "CustomModelLLMSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of LLM settings.",
"title": "llmSettings"
},
"metadataFilter": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "The metadata dictionary defining the filters that documents must match in order to be retrieved.",
"title": "metadataFilter"
},
"resultMetadata": {
"anyOf": [
{
"description": "The additional information about prompt execution results.",
"properties": {
"blockedResultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The message to replace the result text if it is non empty, which represents a blocked response.",
"title": "blockedResultText"
},
"cost": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The estimated cost of executing the prompt.",
"title": "cost"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message for the prompt (in case of an errored prompt).",
"title": "errorMessage"
},
"estimatedDocsTokenCount": {
"default": 0,
"description": "The estimated number of tokens in the documents retrieved from the vector database.",
"title": "estimatedDocsTokenCount",
"type": "integer"
},
"feedbackResult": {
"description": "Prompt feedback included in the result metadata.",
"properties": {
"negativeUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is negative.",
"items": {
"type": "string"
},
"title": "negativeUserIds",
"type": "array"
},
"positiveUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is positive.",
"items": {
"type": "string"
},
"title": "positiveUserIds",
"type": "array"
}
},
"title": "FeedbackResult",
"type": "object"
},
"finalPrompt": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
]
},
"type": "object"
},
"type": "array"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
"type": "array"
},
{
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
{
"type": "null"
}
],
"description": "The final representation of the prompt that was submitted to the LLM.",
"title": "finalPrompt"
},
"inputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM input. This number includes the tokens in the system prompt, the user prompt, the chat history (for history-aware chats) and the documents retrieved from the vector database (in case of using a vector database).",
"title": "inputTokenCount",
"type": "integer"
},
"latencyMilliseconds": {
"description": "The latency of the LLM response (in milliseconds).",
"title": "latencyMilliseconds",
"type": "integer"
},
"metrics": {
"default": [],
"description": "The evaluation metrics for the prompt.",
"items": {
"description": "Prompt metric metadata.",
"properties": {
"costConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the cost configuration.",
"title": "costConfigurationId"
},
"customModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model used for the metric.",
"title": "customModelId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the metric computation.",
"title": "errorMessage"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset configuration.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database."
},
"formattedName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted name of the metric.",
"title": "formattedName"
},
"formattedValue": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted value of the metric.",
"title": "formattedValue"
},
"llmIsDeprecated": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "llmIsDeprecated"
},
"name": {
"description": "The name of the metric.",
"title": "name",
"type": "string"
},
"nemoMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the NeMo Pipeline configuration.",
"title": "nemoMetricId"
},
"ootbMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the OOTB metric configuration.",
"title": "ootbMetricId"
},
"sidecarModelMetricValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the sidecar model validation(in case of using a sidecar model deployment for the metric).",
"title": "sidecarModelMetricValidationId"
},
"stage": {
"anyOf": [
{
"description": "Enum that describes at which stage the metric may be calculated.",
"enum": [
"prompt_pipeline",
"response_pipeline"
],
"title": "PipelineStage",
"type": "string"
},
{
"type": "null"
}
],
"description": "The stage (prompt or response) that the metric applies to."
},
"value": {
"description": "The value of the metric.",
"title": "value"
}
},
"required": [
"name",
"value"
],
"title": "MetricMetadata",
"type": "object"
},
"title": "metrics",
"type": "array"
},
"outputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM output.",
"title": "outputTokenCount",
"type": "integer"
},
"providerLLMGuards": {
"anyOf": [
{
"items": {
"description": "Info on the provider guard metrics.",
"properties": {
"name": {
"description": "The name of the provider guard metric.",
"title": "name",
"type": "string"
},
"satisfyCriteria": {
"description": "Whether the configured provider guard metric satisfied its hidden internal guard criteria.",
"title": "satisfyCriteria",
"type": "boolean"
},
"stage": {
"description": "The data stage where the provider guard metric is acting upon.",
"enum": [
"prompt",
"response"
],
"title": "ProviderGuardStage",
"type": "string"
},
"value": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The value of the provider guard metric.",
"title": "value"
}
},
"required": [
"satisfyCriteria",
"name",
"value",
"stage"
],
"title": "ProviderGuardsMetadata",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The provider llm guards metadata.",
"title": "providerLLMGuards"
},
"totalTokenCount": {
"default": 0,
"description": "The combined number of tokens in the LLM input and output.",
"title": "totalTokenCount",
"type": "integer"
}
},
"required": [
"latencyMilliseconds"
],
"title": "ResultMetadata",
"type": "object"
},
{
"type": "null"
}
],
"description": "The additional information about the chat prompt results."
},
"resultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The text of the prompt completion.",
"title": "resultText"
},
"text": {
"description": "The text of the user prompt.",
"title": "text",
"type": "string"
},
"userName": {
"description": "The name of the user that created the chat prompt.",
"title": "userName",
"type": "string"
},
"vectorDatabaseFamilyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database family this chat prompt belongs to.",
"title": "vectorDatabaseFamilyId"
},
"vectorDatabaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database linked to this LLM blueprint.",
"title": "vectorDatabaseId"
},
"vectorDatabaseSettings": {
"anyOf": [
{
"description": "Vector database retrieval settings.",
"properties": {
"addNeighborChunks": {
"default": false,
"description": "Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1.",
"title": "addNeighborChunks",
"type": "boolean"
},
"maxDocumentsRetrievedPerPrompt": {
"anyOf": [
{
"maximum": 10,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of chunks to retrieve from the vector database.",
"title": "maxDocumentsRetrievedPerPrompt"
},
"maxTokens": {
"anyOf": [
{
"maximum": 51200,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of tokens to retrieve from the vector database.",
"title": "maxTokens"
},
"retriever": {
"description": "The method used to retrieve relevant chunks from the vector database.",
"enum": [
"SINGLE_LOOKUP_RETRIEVER",
"CONVERSATIONAL_RETRIEVER",
"MULTI_STEP_RETRIEVER"
],
"title": "VectorDatabaseRetrievers",
"type": "string"
}
},
"title": "VectorDatabaseSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of vector database settings."
}
},
"required": [
"llmId",
"id",
"text",
"llmBlueprintId",
"creationDate",
"creationUserId",
"userName",
"resultMetadata",
"resultText",
"confidenceScores",
"citations",
"executionStatus"
],
"title": "ChatPromptResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 202 | Accepted | Successful Response | ChatPromptResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
DELETE /api/v2/genai/chatPrompts/{chatPromptId}/¶
Delete an existing chat prompt.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| chatPromptId | path | string | true | The ID of the chat prompt to delete. |
Example responses¶
422 Response
{
"properties": {
"detail": {
"items": {
"properties": {
"loc": {
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
]
},
"title": "loc",
"type": "array"
},
"msg": {
"title": "msg",
"type": "string"
},
"type": {
"title": "type",
"type": "string"
}
},
"required": [
"loc",
"msg",
"type"
],
"title": "ValidationError",
"type": "object"
},
"title": "detail",
"type": "array"
}
},
"title": "HTTPValidationErrorResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 204 | No Content | Successful Response | None |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/genai/chatPrompts/{chatPromptId}/¶
Retrieve an existing chat prompt.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| chatPromptId | path | string | true | The ID of the chat prompt to retrieve. |
Example responses¶
200 Response
{
"description": "API response object for a single chat prompt.",
"properties": {
"chatContextId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the chat context for this prompt.",
"title": "chatContextId"
},
"chatId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the chat this chat prompt belongs to.",
"title": "chatId"
},
"chatPromptIdsIncludedInHistory": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of IDs of the chat prompts included in this prompt's history.",
"title": "chatPromptIdsIncludedInHistory"
},
"citations": {
"description": "The list of relevant vector database citations (in case of using a vector database).",
"items": {
"description": "API response object for a single vector database citation.",
"properties": {
"chunkId": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The ID of the chunk in the vector database index.",
"title": "chunkId"
},
"metadata": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "LangChain Document metadata information holder.",
"title": "metadata"
},
"page": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The source page number where the citation was found.",
"title": "page"
},
"similarityScore": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The similarity score between the citation and the user prompt.",
"title": "similarityScore"
},
"source": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The source of the citation (e.g., a filename in the original dataset).",
"title": "source"
},
"startIndex": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The chunk's start character index in the source document.",
"title": "startIndex"
},
"text": {
"description": "The text of the citation.",
"title": "text",
"type": "string"
}
},
"required": [
"text",
"source"
],
"title": "Citation",
"type": "object"
},
"title": "citations",
"type": "array"
},
"confidenceScores": {
"anyOf": [
{
"description": "API response object for confidence scores.",
"properties": {
"bleu": {
"description": "BLEU score.",
"title": "bleu",
"type": "number"
},
"meteor": {
"description": "METEOR score.",
"title": "meteor",
"type": "number"
},
"rouge": {
"description": "ROUGE score.",
"title": "rouge",
"type": "number"
}
},
"required": [
"rouge",
"meteor",
"bleu"
],
"title": "ConfidenceScores",
"type": "object"
},
{
"type": "null"
}
],
"description": "The confidence scores that measure the similarity between the prompt context and the prompt completion."
},
"creationDate": {
"description": "The creation date of the chat prompt (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created the chat prompt.",
"title": "creationUserId",
"type": "string"
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"id": {
"description": "The ID of the chat prompt.",
"title": "id",
"type": "string"
},
"llmBlueprintId": {
"description": "The ID of the LLM blueprint the chat prompt belongs to.",
"title": "llmBlueprintId",
"type": "string"
},
"llmId": {
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
"llmSettings": {
"anyOf": [
{
"additionalProperties": false,
"description": "The settings that are available for all non-custom LLMs.",
"properties": {
"maxCompletionLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Maximum number of tokens allowed in the completion. The combined count of this value and prompt tokens must be below the model's maximum context size, where prompt token count is comprised of system prompt, user prompt, recent chat history, and vector database citations.",
"title": "maxCompletionLength"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Temperature controls the randomness of model output, where higher values return more diverse output and lower values return more deterministic results.",
"title": "temperature"
},
"topP": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Top P sets a threshold that controls the selection of words included in the response, based on a cumulative probability cutoff for token selection. For example, 0.2 considers only the top 20% probability mass. Higher numbers return more diverse options for outputs.",
"title": "topP"
}
},
"title": "CommonLLMSettings",
"type": "object"
},
{
"additionalProperties": false,
"description": "The settings that are available for custom model LLMs.",
"properties": {
"externalLlmContextSize": {
"anyOf": [
{
"maximum": 128000,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The external LLM's context size, in tokens. This value is only used for pruning documents supplied to the LLM when a vector database is associated with the LLM blueprint. It does not affect the external LLM's actual context size in any way and is not supplied to the LLM.",
"title": "externalLlmContextSize"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model LLM.",
"title": "validationId"
}
},
"title": "CustomModelLLMSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of LLM settings.",
"title": "llmSettings"
},
"metadataFilter": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "The metadata dictionary defining the filters that documents must match in order to be retrieved.",
"title": "metadataFilter"
},
"resultMetadata": {
"anyOf": [
{
"description": "The additional information about prompt execution results.",
"properties": {
"blockedResultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The message to replace the result text if it is non empty, which represents a blocked response.",
"title": "blockedResultText"
},
"cost": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The estimated cost of executing the prompt.",
"title": "cost"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message for the prompt (in case of an errored prompt).",
"title": "errorMessage"
},
"estimatedDocsTokenCount": {
"default": 0,
"description": "The estimated number of tokens in the documents retrieved from the vector database.",
"title": "estimatedDocsTokenCount",
"type": "integer"
},
"feedbackResult": {
"description": "Prompt feedback included in the result metadata.",
"properties": {
"negativeUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is negative.",
"items": {
"type": "string"
},
"title": "negativeUserIds",
"type": "array"
},
"positiveUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is positive.",
"items": {
"type": "string"
},
"title": "positiveUserIds",
"type": "array"
}
},
"title": "FeedbackResult",
"type": "object"
},
"finalPrompt": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
]
},
"type": "object"
},
"type": "array"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
"type": "array"
},
{
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
{
"type": "null"
}
],
"description": "The final representation of the prompt that was submitted to the LLM.",
"title": "finalPrompt"
},
"inputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM input. This number includes the tokens in the system prompt, the user prompt, the chat history (for history-aware chats) and the documents retrieved from the vector database (in case of using a vector database).",
"title": "inputTokenCount",
"type": "integer"
},
"latencyMilliseconds": {
"description": "The latency of the LLM response (in milliseconds).",
"title": "latencyMilliseconds",
"type": "integer"
},
"metrics": {
"default": [],
"description": "The evaluation metrics for the prompt.",
"items": {
"description": "Prompt metric metadata.",
"properties": {
"costConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the cost configuration.",
"title": "costConfigurationId"
},
"customModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model used for the metric.",
"title": "customModelId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the metric computation.",
"title": "errorMessage"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset configuration.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database."
},
"formattedName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted name of the metric.",
"title": "formattedName"
},
"formattedValue": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted value of the metric.",
"title": "formattedValue"
},
"llmIsDeprecated": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "llmIsDeprecated"
},
"name": {
"description": "The name of the metric.",
"title": "name",
"type": "string"
},
"nemoMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the NeMo Pipeline configuration.",
"title": "nemoMetricId"
},
"ootbMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the OOTB metric configuration.",
"title": "ootbMetricId"
},
"sidecarModelMetricValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the sidecar model validation(in case of using a sidecar model deployment for the metric).",
"title": "sidecarModelMetricValidationId"
},
"stage": {
"anyOf": [
{
"description": "Enum that describes at which stage the metric may be calculated.",
"enum": [
"prompt_pipeline",
"response_pipeline"
],
"title": "PipelineStage",
"type": "string"
},
{
"type": "null"
}
],
"description": "The stage (prompt or response) that the metric applies to."
},
"value": {
"description": "The value of the metric.",
"title": "value"
}
},
"required": [
"name",
"value"
],
"title": "MetricMetadata",
"type": "object"
},
"title": "metrics",
"type": "array"
},
"outputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM output.",
"title": "outputTokenCount",
"type": "integer"
},
"providerLLMGuards": {
"anyOf": [
{
"items": {
"description": "Info on the provider guard metrics.",
"properties": {
"name": {
"description": "The name of the provider guard metric.",
"title": "name",
"type": "string"
},
"satisfyCriteria": {
"description": "Whether the configured provider guard metric satisfied its hidden internal guard criteria.",
"title": "satisfyCriteria",
"type": "boolean"
},
"stage": {
"description": "The data stage where the provider guard metric is acting upon.",
"enum": [
"prompt",
"response"
],
"title": "ProviderGuardStage",
"type": "string"
},
"value": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The value of the provider guard metric.",
"title": "value"
}
},
"required": [
"satisfyCriteria",
"name",
"value",
"stage"
],
"title": "ProviderGuardsMetadata",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The provider llm guards metadata.",
"title": "providerLLMGuards"
},
"totalTokenCount": {
"default": 0,
"description": "The combined number of tokens in the LLM input and output.",
"title": "totalTokenCount",
"type": "integer"
}
},
"required": [
"latencyMilliseconds"
],
"title": "ResultMetadata",
"type": "object"
},
{
"type": "null"
}
],
"description": "The additional information about the chat prompt results."
},
"resultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The text of the prompt completion.",
"title": "resultText"
},
"text": {
"description": "The text of the user prompt.",
"title": "text",
"type": "string"
},
"userName": {
"description": "The name of the user that created the chat prompt.",
"title": "userName",
"type": "string"
},
"vectorDatabaseFamilyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database family this chat prompt belongs to.",
"title": "vectorDatabaseFamilyId"
},
"vectorDatabaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database linked to this LLM blueprint.",
"title": "vectorDatabaseId"
},
"vectorDatabaseSettings": {
"anyOf": [
{
"description": "Vector database retrieval settings.",
"properties": {
"addNeighborChunks": {
"default": false,
"description": "Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1.",
"title": "addNeighborChunks",
"type": "boolean"
},
"maxDocumentsRetrievedPerPrompt": {
"anyOf": [
{
"maximum": 10,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of chunks to retrieve from the vector database.",
"title": "maxDocumentsRetrievedPerPrompt"
},
"maxTokens": {
"anyOf": [
{
"maximum": 51200,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of tokens to retrieve from the vector database.",
"title": "maxTokens"
},
"retriever": {
"description": "The method used to retrieve relevant chunks from the vector database.",
"enum": [
"SINGLE_LOOKUP_RETRIEVER",
"CONVERSATIONAL_RETRIEVER",
"MULTI_STEP_RETRIEVER"
],
"title": "VectorDatabaseRetrievers",
"type": "string"
}
},
"title": "VectorDatabaseSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of vector database settings."
}
},
"required": [
"llmId",
"id",
"text",
"llmBlueprintId",
"creationDate",
"creationUserId",
"userName",
"resultMetadata",
"resultText",
"confidenceScores",
"citations",
"executionStatus"
],
"title": "ChatPromptResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Successful Response | ChatPromptResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
PATCH /api/v2/genai/chatPrompts/{chatPromptId}/¶
Edit an existing chat prompt.
Body parameter¶
{
"description": "The body of the \"Update chat prompt\" request.",
"properties": {
"customMetrics": {
"anyOf": [
{
"items": {
"description": "Prompt metric metadata.",
"properties": {
"costConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the cost configuration.",
"title": "costConfigurationId"
},
"customModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model used for the metric.",
"title": "customModelId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the metric computation.",
"title": "errorMessage"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset configuration.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database."
},
"formattedName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted name of the metric.",
"title": "formattedName"
},
"formattedValue": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted value of the metric.",
"title": "formattedValue"
},
"llmIsDeprecated": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "llmIsDeprecated"
},
"name": {
"description": "The name of the metric.",
"title": "name",
"type": "string"
},
"nemoMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the NeMo Pipeline configuration.",
"title": "nemoMetricId"
},
"ootbMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the OOTB metric configuration.",
"title": "ootbMetricId"
},
"sidecarModelMetricValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the sidecar model validation(in case of using a sidecar model deployment for the metric).",
"title": "sidecarModelMetricValidationId"
},
"stage": {
"anyOf": [
{
"description": "Enum that describes at which stage the metric may be calculated.",
"enum": [
"prompt_pipeline",
"response_pipeline"
],
"title": "PipelineStage",
"type": "string"
},
{
"type": "null"
}
],
"description": "The stage (prompt or response) that the metric applies to."
},
"value": {
"description": "The value of the metric.",
"title": "value"
}
},
"required": [
"name",
"value"
],
"title": "MetricMetadata",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of metric results to add to the chat prompt.",
"title": "customMetrics"
},
"feedbackMetadata": {
"anyOf": [
{
"description": "Prompt feedback metadata.",
"properties": {
"feedback": {
"anyOf": [
{
"description": "The sentiment of the feedback.",
"enum": [
"1",
"0"
],
"title": "FeedbackSentiment",
"type": "string"
},
{
"type": "null"
}
],
"description": "The sentiment of the feedback."
}
},
"required": [
"feedback"
],
"title": "FeedbackMetadata",
"type": "object"
},
{
"type": "null"
}
],
"description": "The feedback metadata to add to the chat prompt."
}
},
"title": "EditChatPromptRequest",
"type": "object"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| chatPromptId | path | string | true | The ID of the chat prompt to edit. |
| body | body | EditChatPromptRequest | true | none |
Example responses¶
200 Response
{
"description": "API response object for a single chat prompt.",
"properties": {
"chatContextId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the chat context for this prompt.",
"title": "chatContextId"
},
"chatId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the chat this chat prompt belongs to.",
"title": "chatId"
},
"chatPromptIdsIncludedInHistory": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of IDs of the chat prompts included in this prompt's history.",
"title": "chatPromptIdsIncludedInHistory"
},
"citations": {
"description": "The list of relevant vector database citations (in case of using a vector database).",
"items": {
"description": "API response object for a single vector database citation.",
"properties": {
"chunkId": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The ID of the chunk in the vector database index.",
"title": "chunkId"
},
"metadata": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "LangChain Document metadata information holder.",
"title": "metadata"
},
"page": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The source page number where the citation was found.",
"title": "page"
},
"similarityScore": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The similarity score between the citation and the user prompt.",
"title": "similarityScore"
},
"source": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The source of the citation (e.g., a filename in the original dataset).",
"title": "source"
},
"startIndex": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The chunk's start character index in the source document.",
"title": "startIndex"
},
"text": {
"description": "The text of the citation.",
"title": "text",
"type": "string"
}
},
"required": [
"text",
"source"
],
"title": "Citation",
"type": "object"
},
"title": "citations",
"type": "array"
},
"confidenceScores": {
"anyOf": [
{
"description": "API response object for confidence scores.",
"properties": {
"bleu": {
"description": "BLEU score.",
"title": "bleu",
"type": "number"
},
"meteor": {
"description": "METEOR score.",
"title": "meteor",
"type": "number"
},
"rouge": {
"description": "ROUGE score.",
"title": "rouge",
"type": "number"
}
},
"required": [
"rouge",
"meteor",
"bleu"
],
"title": "ConfidenceScores",
"type": "object"
},
{
"type": "null"
}
],
"description": "The confidence scores that measure the similarity between the prompt context and the prompt completion."
},
"creationDate": {
"description": "The creation date of the chat prompt (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created the chat prompt.",
"title": "creationUserId",
"type": "string"
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"id": {
"description": "The ID of the chat prompt.",
"title": "id",
"type": "string"
},
"llmBlueprintId": {
"description": "The ID of the LLM blueprint the chat prompt belongs to.",
"title": "llmBlueprintId",
"type": "string"
},
"llmId": {
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
"llmSettings": {
"anyOf": [
{
"additionalProperties": false,
"description": "The settings that are available for all non-custom LLMs.",
"properties": {
"maxCompletionLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Maximum number of tokens allowed in the completion. The combined count of this value and prompt tokens must be below the model's maximum context size, where prompt token count is comprised of system prompt, user prompt, recent chat history, and vector database citations.",
"title": "maxCompletionLength"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Temperature controls the randomness of model output, where higher values return more diverse output and lower values return more deterministic results.",
"title": "temperature"
},
"topP": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Top P sets a threshold that controls the selection of words included in the response, based on a cumulative probability cutoff for token selection. For example, 0.2 considers only the top 20% probability mass. Higher numbers return more diverse options for outputs.",
"title": "topP"
}
},
"title": "CommonLLMSettings",
"type": "object"
},
{
"additionalProperties": false,
"description": "The settings that are available for custom model LLMs.",
"properties": {
"externalLlmContextSize": {
"anyOf": [
{
"maximum": 128000,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The external LLM's context size, in tokens. This value is only used for pruning documents supplied to the LLM when a vector database is associated with the LLM blueprint. It does not affect the external LLM's actual context size in any way and is not supplied to the LLM.",
"title": "externalLlmContextSize"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model LLM.",
"title": "validationId"
}
},
"title": "CustomModelLLMSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of LLM settings.",
"title": "llmSettings"
},
"metadataFilter": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "The metadata dictionary defining the filters that documents must match in order to be retrieved.",
"title": "metadataFilter"
},
"resultMetadata": {
"anyOf": [
{
"description": "The additional information about prompt execution results.",
"properties": {
"blockedResultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The message to replace the result text if it is non empty, which represents a blocked response.",
"title": "blockedResultText"
},
"cost": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The estimated cost of executing the prompt.",
"title": "cost"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message for the prompt (in case of an errored prompt).",
"title": "errorMessage"
},
"estimatedDocsTokenCount": {
"default": 0,
"description": "The estimated number of tokens in the documents retrieved from the vector database.",
"title": "estimatedDocsTokenCount",
"type": "integer"
},
"feedbackResult": {
"description": "Prompt feedback included in the result metadata.",
"properties": {
"negativeUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is negative.",
"items": {
"type": "string"
},
"title": "negativeUserIds",
"type": "array"
},
"positiveUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is positive.",
"items": {
"type": "string"
},
"title": "positiveUserIds",
"type": "array"
}
},
"title": "FeedbackResult",
"type": "object"
},
"finalPrompt": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
]
},
"type": "object"
},
"type": "array"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
"type": "array"
},
{
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
{
"type": "null"
}
],
"description": "The final representation of the prompt that was submitted to the LLM.",
"title": "finalPrompt"
},
"inputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM input. This number includes the tokens in the system prompt, the user prompt, the chat history (for history-aware chats) and the documents retrieved from the vector database (in case of using a vector database).",
"title": "inputTokenCount",
"type": "integer"
},
"latencyMilliseconds": {
"description": "The latency of the LLM response (in milliseconds).",
"title": "latencyMilliseconds",
"type": "integer"
},
"metrics": {
"default": [],
"description": "The evaluation metrics for the prompt.",
"items": {
"description": "Prompt metric metadata.",
"properties": {
"costConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the cost configuration.",
"title": "costConfigurationId"
},
"customModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model used for the metric.",
"title": "customModelId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the metric computation.",
"title": "errorMessage"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset configuration.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database."
},
"formattedName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted name of the metric.",
"title": "formattedName"
},
"formattedValue": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted value of the metric.",
"title": "formattedValue"
},
"llmIsDeprecated": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "llmIsDeprecated"
},
"name": {
"description": "The name of the metric.",
"title": "name",
"type": "string"
},
"nemoMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the NeMo Pipeline configuration.",
"title": "nemoMetricId"
},
"ootbMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the OOTB metric configuration.",
"title": "ootbMetricId"
},
"sidecarModelMetricValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the sidecar model validation(in case of using a sidecar model deployment for the metric).",
"title": "sidecarModelMetricValidationId"
},
"stage": {
"anyOf": [
{
"description": "Enum that describes at which stage the metric may be calculated.",
"enum": [
"prompt_pipeline",
"response_pipeline"
],
"title": "PipelineStage",
"type": "string"
},
{
"type": "null"
}
],
"description": "The stage (prompt or response) that the metric applies to."
},
"value": {
"description": "The value of the metric.",
"title": "value"
}
},
"required": [
"name",
"value"
],
"title": "MetricMetadata",
"type": "object"
},
"title": "metrics",
"type": "array"
},
"outputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM output.",
"title": "outputTokenCount",
"type": "integer"
},
"providerLLMGuards": {
"anyOf": [
{
"items": {
"description": "Info on the provider guard metrics.",
"properties": {
"name": {
"description": "The name of the provider guard metric.",
"title": "name",
"type": "string"
},
"satisfyCriteria": {
"description": "Whether the configured provider guard metric satisfied its hidden internal guard criteria.",
"title": "satisfyCriteria",
"type": "boolean"
},
"stage": {
"description": "The data stage where the provider guard metric is acting upon.",
"enum": [
"prompt",
"response"
],
"title": "ProviderGuardStage",
"type": "string"
},
"value": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The value of the provider guard metric.",
"title": "value"
}
},
"required": [
"satisfyCriteria",
"name",
"value",
"stage"
],
"title": "ProviderGuardsMetadata",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The provider llm guards metadata.",
"title": "providerLLMGuards"
},
"totalTokenCount": {
"default": 0,
"description": "The combined number of tokens in the LLM input and output.",
"title": "totalTokenCount",
"type": "integer"
}
},
"required": [
"latencyMilliseconds"
],
"title": "ResultMetadata",
"type": "object"
},
{
"type": "null"
}
],
"description": "The additional information about the chat prompt results."
},
"resultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The text of the prompt completion.",
"title": "resultText"
},
"text": {
"description": "The text of the user prompt.",
"title": "text",
"type": "string"
},
"userName": {
"description": "The name of the user that created the chat prompt.",
"title": "userName",
"type": "string"
},
"vectorDatabaseFamilyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database family this chat prompt belongs to.",
"title": "vectorDatabaseFamilyId"
},
"vectorDatabaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database linked to this LLM blueprint.",
"title": "vectorDatabaseId"
},
"vectorDatabaseSettings": {
"anyOf": [
{
"description": "Vector database retrieval settings.",
"properties": {
"addNeighborChunks": {
"default": false,
"description": "Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1.",
"title": "addNeighborChunks",
"type": "boolean"
},
"maxDocumentsRetrievedPerPrompt": {
"anyOf": [
{
"maximum": 10,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of chunks to retrieve from the vector database.",
"title": "maxDocumentsRetrievedPerPrompt"
},
"maxTokens": {
"anyOf": [
{
"maximum": 51200,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of tokens to retrieve from the vector database.",
"title": "maxTokens"
},
"retriever": {
"description": "The method used to retrieve relevant chunks from the vector database.",
"enum": [
"SINGLE_LOOKUP_RETRIEVER",
"CONVERSATIONAL_RETRIEVER",
"MULTI_STEP_RETRIEVER"
],
"title": "VectorDatabaseRetrievers",
"type": "string"
}
},
"title": "VectorDatabaseSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of vector database settings."
}
},
"required": [
"llmId",
"id",
"text",
"llmBlueprintId",
"creationDate",
"creationUserId",
"userName",
"resultMetadata",
"resultText",
"confidenceScores",
"citations",
"executionStatus"
],
"title": "ChatPromptResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Successful Response | ChatPromptResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/genai/chats/¶
List chats.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| llmBlueprintId | query | any | false | Only retrieve the chats associated with this LLM blueprint ID. |
| offset | query | integer | false | Skip the specified number of values. |
| limit | query | integer | false | Retrieve only the specified number of values. |
| sort | query | any | false | Apply this sort order to the results. Valid options are "name" and "creationDate". Prefix the attribute name with a dash to sort in descending order, e.g., sort=-creationDate. |
Example responses¶
200 Response
{
"description": "Paginated list of chats.",
"properties": {
"count": {
"description": "The number of records on this page.",
"title": "count",
"type": "integer"
},
"data": {
"description": "The list of records.",
"items": {
"description": "Chat object formatted for API output.",
"properties": {
"creationDate": {
"description": "The creation date of the chat (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created the chat.",
"title": "creationUserId",
"type": "string"
},
"id": {
"description": "The ID of the chat.",
"title": "id",
"type": "string"
},
"isFrozen": {
"description": "Whether the chat is frozen (e.g., an evaluation chat). If the chat is frozen, it does not accept new prompts.",
"title": "isFrozen",
"type": "boolean"
},
"llmBlueprintId": {
"description": "The ID of the LLM blueprint associated with the chat.",
"title": "llmBlueprintId",
"type": "string"
},
"name": {
"description": "The name of the chat.",
"title": "name",
"type": "string"
},
"promptsCount": {
"description": "The number of chat prompts in the chat.",
"title": "promptsCount",
"type": "integer"
},
"warning": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Warning about the contents of the chat.",
"title": "warning"
}
},
"required": [
"id",
"name",
"llmBlueprintId",
"isFrozen",
"warning",
"creationDate",
"creationUserId",
"promptsCount"
],
"title": "ChatResponse",
"type": "object"
},
"title": "data",
"type": "array"
},
"next": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the next page, or `null` if there is no such page.",
"title": "next"
},
"previous": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the previous page, or `null` if there is no such page.",
"title": "previous"
},
"totalCount": {
"description": "The total number of records.",
"title": "totalCount",
"type": "integer"
}
},
"required": [
"totalCount",
"count",
"next",
"previous",
"data"
],
"title": "ListChatsResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Successful Response | ListChatsResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
POST /api/v2/genai/chats/¶
Create a new chat.
Body parameter¶
{
"description": "The body of the \"Create chat\" request.",
"properties": {
"llmBlueprintId": {
"description": "The ID of the LLM blueprint to associate with the chat.",
"title": "llmBlueprintId",
"type": "string"
},
"name": {
"description": "The name of the chat.",
"maxLength": 5000,
"minLength": 1,
"title": "name",
"type": "string"
}
},
"required": [
"name",
"llmBlueprintId"
],
"title": "CreateChatRequest",
"type": "object"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| body | body | CreateChatRequest | true | none |
Example responses¶
201 Response
{
"description": "Chat object formatted for API output.",
"properties": {
"creationDate": {
"description": "The creation date of the chat (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created the chat.",
"title": "creationUserId",
"type": "string"
},
"id": {
"description": "The ID of the chat.",
"title": "id",
"type": "string"
},
"isFrozen": {
"description": "Whether the chat is frozen (e.g., an evaluation chat). If the chat is frozen, it does not accept new prompts.",
"title": "isFrozen",
"type": "boolean"
},
"llmBlueprintId": {
"description": "The ID of the LLM blueprint associated with the chat.",
"title": "llmBlueprintId",
"type": "string"
},
"name": {
"description": "The name of the chat.",
"title": "name",
"type": "string"
},
"promptsCount": {
"description": "The number of chat prompts in the chat.",
"title": "promptsCount",
"type": "integer"
},
"warning": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Warning about the contents of the chat.",
"title": "warning"
}
},
"required": [
"id",
"name",
"llmBlueprintId",
"isFrozen",
"warning",
"creationDate",
"creationUserId",
"promptsCount"
],
"title": "ChatResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 201 | Created | Successful Response | ChatResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
DELETE /api/v2/genai/chats/{chatId}/¶
Delete an existing chat.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| chatId | path | string | true | The ID of the chat to delete. |
Example responses¶
422 Response
{
"properties": {
"detail": {
"items": {
"properties": {
"loc": {
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
]
},
"title": "loc",
"type": "array"
},
"msg": {
"title": "msg",
"type": "string"
},
"type": {
"title": "type",
"type": "string"
}
},
"required": [
"loc",
"msg",
"type"
],
"title": "ValidationError",
"type": "object"
},
"title": "detail",
"type": "array"
}
},
"title": "HTTPValidationErrorResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 204 | No Content | Successful Response | None |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/genai/chats/{chatId}/¶
Retrieve an existing chat.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| chatId | path | string | true | The ID of the chat to retrieve. |
Example responses¶
200 Response
{
"description": "Chat object formatted for API output.",
"properties": {
"creationDate": {
"description": "The creation date of the chat (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created the chat.",
"title": "creationUserId",
"type": "string"
},
"id": {
"description": "The ID of the chat.",
"title": "id",
"type": "string"
},
"isFrozen": {
"description": "Whether the chat is frozen (e.g., an evaluation chat). If the chat is frozen, it does not accept new prompts.",
"title": "isFrozen",
"type": "boolean"
},
"llmBlueprintId": {
"description": "The ID of the LLM blueprint associated with the chat.",
"title": "llmBlueprintId",
"type": "string"
},
"name": {
"description": "The name of the chat.",
"title": "name",
"type": "string"
},
"promptsCount": {
"description": "The number of chat prompts in the chat.",
"title": "promptsCount",
"type": "integer"
},
"warning": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Warning about the contents of the chat.",
"title": "warning"
}
},
"required": [
"id",
"name",
"llmBlueprintId",
"isFrozen",
"warning",
"creationDate",
"creationUserId",
"promptsCount"
],
"title": "ChatResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Successful Response | ChatResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
PATCH /api/v2/genai/chats/{chatId}/¶
Edit an existing chat.
Body parameter¶
{
"description": "The body of the \"Edit chat\" request.",
"properties": {
"name": {
"description": "The new name of the chat.",
"maxLength": 5000,
"minLength": 1,
"title": "name",
"type": "string"
}
},
"required": [
"name"
],
"title": "EditChatRequest",
"type": "object"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| chatId | path | string | true | The ID of the chat to edit. |
| body | body | EditChatRequest | true | none |
Example responses¶
200 Response
{
"description": "Chat object formatted for API output.",
"properties": {
"creationDate": {
"description": "The creation date of the chat (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created the chat.",
"title": "creationUserId",
"type": "string"
},
"id": {
"description": "The ID of the chat.",
"title": "id",
"type": "string"
},
"isFrozen": {
"description": "Whether the chat is frozen (e.g., an evaluation chat). If the chat is frozen, it does not accept new prompts.",
"title": "isFrozen",
"type": "boolean"
},
"llmBlueprintId": {
"description": "The ID of the LLM blueprint associated with the chat.",
"title": "llmBlueprintId",
"type": "string"
},
"name": {
"description": "The name of the chat.",
"title": "name",
"type": "string"
},
"promptsCount": {
"description": "The number of chat prompts in the chat.",
"title": "promptsCount",
"type": "integer"
},
"warning": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Warning about the contents of the chat.",
"title": "warning"
}
},
"required": [
"id",
"name",
"llmBlueprintId",
"isFrozen",
"warning",
"creationDate",
"creationUserId",
"promptsCount"
],
"title": "ChatResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Successful Response | ChatResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/genai/comparisonChats/¶
List comparison chats.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| playgroundId | query | any | false | Only retrieve the comparison chats associated with this playground ID. |
| offset | query | integer | false | Skip the specified number of values. |
| limit | query | integer | false | Retrieve only the specified number of values. |
| sort | query | any | false | Apply this sort order to the results. Valid options are "name" and "creationDate". Prefix the attribute name with a dash to sort in descending order, e.g., sort=-creationDate. |
Example responses¶
200 Response
{
"description": "Paginated list of comparison chats.",
"properties": {
"count": {
"description": "The number of records on this page.",
"title": "count",
"type": "integer"
},
"data": {
"description": "The list of records.",
"items": {
"description": "Comparison chat object formatted for API output.",
"properties": {
"creationDate": {
"description": "The creation date of the comparison chat (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created the comparison chat.",
"title": "creationUserId",
"type": "string"
},
"id": {
"description": "The ID of the comparison chat.",
"title": "id",
"type": "string"
},
"name": {
"description": "The name of the comparison chat.",
"title": "name",
"type": "string"
},
"playgroundId": {
"description": "The ID of the playground associated with the comparison chat.",
"title": "playgroundId",
"type": "string"
},
"promptsCount": {
"description": "The number of comparison prompts in the comparison chat.",
"title": "promptsCount",
"type": "integer"
}
},
"required": [
"id",
"name",
"playgroundId",
"creationDate",
"creationUserId",
"promptsCount"
],
"title": "ComparisonChatResponse",
"type": "object"
},
"title": "data",
"type": "array"
},
"next": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the next page, or `null` if there is no such page.",
"title": "next"
},
"previous": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the previous page, or `null` if there is no such page.",
"title": "previous"
},
"totalCount": {
"description": "The total number of records.",
"title": "totalCount",
"type": "integer"
}
},
"required": [
"totalCount",
"count",
"next",
"previous",
"data"
],
"title": "ListComparisonChatsResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Successful Response | ListComparisonChatsResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
POST /api/v2/genai/comparisonChats/¶
Create a new comparison chat.
Body parameter¶
{
"description": "The body of the \"Create comparison chat\" request.",
"properties": {
"name": {
"description": "The name of the comparison chat.",
"maxLength": 5000,
"minLength": 1,
"title": "name",
"type": "string"
},
"playgroundId": {
"description": "The ID of the playground to associate with the comparison chat.",
"title": "playgroundId",
"type": "string"
}
},
"required": [
"name",
"playgroundId"
],
"title": "CreateComparisonChatRequest",
"type": "object"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| body | body | CreateComparisonChatRequest | true | none |
Example responses¶
201 Response
{
"description": "Comparison chat object formatted for API output.",
"properties": {
"creationDate": {
"description": "The creation date of the comparison chat (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created the comparison chat.",
"title": "creationUserId",
"type": "string"
},
"id": {
"description": "The ID of the comparison chat.",
"title": "id",
"type": "string"
},
"name": {
"description": "The name of the comparison chat.",
"title": "name",
"type": "string"
},
"playgroundId": {
"description": "The ID of the playground associated with the comparison chat.",
"title": "playgroundId",
"type": "string"
},
"promptsCount": {
"description": "The number of comparison prompts in the comparison chat.",
"title": "promptsCount",
"type": "integer"
}
},
"required": [
"id",
"name",
"playgroundId",
"creationDate",
"creationUserId",
"promptsCount"
],
"title": "ComparisonChatResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 201 | Created | Successful Response | ComparisonChatResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
DELETE /api/v2/genai/comparisonChats/{comparisonChatId}/¶
Delete an existing comparison chat.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| comparisonChatId | path | string | true | The ID of the comparison chat to delete. |
Example responses¶
422 Response
{
"properties": {
"detail": {
"items": {
"properties": {
"loc": {
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
]
},
"title": "loc",
"type": "array"
},
"msg": {
"title": "msg",
"type": "string"
},
"type": {
"title": "type",
"type": "string"
}
},
"required": [
"loc",
"msg",
"type"
],
"title": "ValidationError",
"type": "object"
},
"title": "detail",
"type": "array"
}
},
"title": "HTTPValidationErrorResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 204 | No Content | Successful Response | None |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/genai/comparisonChats/{comparisonChatId}/¶
Retrieve an existing comparison chat.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| comparisonChatId | path | string | true | The ID of the comparison chat to retrieve. |
Example responses¶
200 Response
{
"description": "Comparison chat object formatted for API output.",
"properties": {
"creationDate": {
"description": "The creation date of the comparison chat (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created the comparison chat.",
"title": "creationUserId",
"type": "string"
},
"id": {
"description": "The ID of the comparison chat.",
"title": "id",
"type": "string"
},
"name": {
"description": "The name of the comparison chat.",
"title": "name",
"type": "string"
},
"playgroundId": {
"description": "The ID of the playground associated with the comparison chat.",
"title": "playgroundId",
"type": "string"
},
"promptsCount": {
"description": "The number of comparison prompts in the comparison chat.",
"title": "promptsCount",
"type": "integer"
}
},
"required": [
"id",
"name",
"playgroundId",
"creationDate",
"creationUserId",
"promptsCount"
],
"title": "ComparisonChatResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Successful Response | ComparisonChatResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
PATCH /api/v2/genai/comparisonChats/{comparisonChatId}/¶
Edit an existing comparison chat.
Body parameter¶
{
"description": "The body of the \"Edit comparison chat\" request.",
"properties": {
"name": {
"description": "The new name of the comparison chat.",
"maxLength": 5000,
"minLength": 1,
"title": "name",
"type": "string"
}
},
"required": [
"name"
],
"title": "EditComparisonChatRequest",
"type": "object"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| comparisonChatId | path | string | true | The ID of the comparison chat to edit. |
| body | body | EditComparisonChatRequest | true | none |
Example responses¶
200 Response
{
"description": "Comparison chat object formatted for API output.",
"properties": {
"creationDate": {
"description": "The creation date of the comparison chat (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created the comparison chat.",
"title": "creationUserId",
"type": "string"
},
"id": {
"description": "The ID of the comparison chat.",
"title": "id",
"type": "string"
},
"name": {
"description": "The name of the comparison chat.",
"title": "name",
"type": "string"
},
"playgroundId": {
"description": "The ID of the playground associated with the comparison chat.",
"title": "playgroundId",
"type": "string"
},
"promptsCount": {
"description": "The number of comparison prompts in the comparison chat.",
"title": "promptsCount",
"type": "integer"
}
},
"required": [
"id",
"name",
"playgroundId",
"creationDate",
"creationUserId",
"promptsCount"
],
"title": "ComparisonChatResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Successful Response | ComparisonChatResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/genai/comparisonPrompts/¶
List the comparison prompts associated with a comparison chat or a set of LLM blueprints.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| llmBlueprintIds | query | any | false | Only retrieve the comparison prompts associated with the specified LLM blueprint IDs. Either this parameter or comparisonChatId must be specified, but not both. |
| comparisonChatId | query | any | false | Only retrieve the comparison prompts associated with the specified comparison chat ID. Either this parameter or llmBlueprintIds must be specified, but not both. |
| offset | query | integer | false | Skip the specified number of values. |
| limit | query | integer | false | Retrieve only the specified number of values. |
Example responses¶
200 Response
{
"description": "Paginated list of comparison prompts.",
"properties": {
"count": {
"description": "The number of records on this page.",
"title": "count",
"type": "integer"
},
"data": {
"description": "The list of records.",
"items": {
"description": "ComparisonPrompt object formatted for API output.",
"properties": {
"comparisonChatId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the comparison chat associated with the comparison prompt.",
"title": "comparisonChatId"
},
"creationDate": {
"description": "The creation date of the comparison prompt (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created the comparison prompt.",
"title": "creationUserId",
"type": "string"
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"id": {
"description": "The ID of the comparison prompt.",
"title": "id",
"type": "string"
},
"metadataFilter": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "The metadata filters applied to the comparison prompt.",
"title": "metadataFilter"
},
"results": {
"description": "The list of comparison prompt results.",
"items": {
"description": "API response object for a single comparison prompt result.",
"properties": {
"chatContextId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the chat context for this prompt.",
"title": "chatContextId"
},
"citations": {
"description": "The list of relevant vector database citations (in case of using a vector database).",
"items": {
"description": "API response object for a single vector database citation.",
"properties": {
"chunkId": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The ID of the chunk in the vector database index.",
"title": "chunkId"
},
"metadata": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "LangChain Document metadata information holder.",
"title": "metadata"
},
"page": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The source page number where the citation was found.",
"title": "page"
},
"similarityScore": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The similarity score between the citation and the user prompt.",
"title": "similarityScore"
},
"source": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The source of the citation (e.g., a filename in the original dataset).",
"title": "source"
},
"startIndex": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The chunk's start character index in the source document.",
"title": "startIndex"
},
"text": {
"description": "The text of the citation.",
"title": "text",
"type": "string"
}
},
"required": [
"text",
"source"
],
"title": "Citation",
"type": "object"
},
"title": "citations",
"type": "array"
},
"comparisonPromptResultIdsIncludedInHistory": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of IDs of the comparison prompt results included in this prompt's history.",
"title": "comparisonPromptResultIdsIncludedInHistory"
},
"confidenceScores": {
"anyOf": [
{
"description": "API response object for confidence scores.",
"properties": {
"bleu": {
"description": "BLEU score.",
"title": "bleu",
"type": "number"
},
"meteor": {
"description": "METEOR score.",
"title": "meteor",
"type": "number"
},
"rouge": {
"description": "ROUGE score.",
"title": "rouge",
"type": "number"
}
},
"required": [
"rouge",
"meteor",
"bleu"
],
"title": "ConfidenceScores",
"type": "object"
},
{
"type": "null"
}
],
"description": "The confidence scores that measure the similarity between the prompt context and the prompt completion."
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"id": {
"description": "The ID of the comparison prompt result.",
"title": "id",
"type": "string"
},
"llmBlueprintId": {
"description": "The ID of the LLM blueprint that produced the result.",
"title": "llmBlueprintId",
"type": "string"
},
"resultMetadata": {
"anyOf": [
{
"description": "The additional information about prompt execution results.",
"properties": {
"blockedResultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The message to replace the result text if it is non empty, which represents a blocked response.",
"title": "blockedResultText"
},
"cost": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The estimated cost of executing the prompt.",
"title": "cost"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message for the prompt (in case of an errored prompt).",
"title": "errorMessage"
},
"estimatedDocsTokenCount": {
"default": 0,
"description": "The estimated number of tokens in the documents retrieved from the vector database.",
"title": "estimatedDocsTokenCount",
"type": "integer"
},
"feedbackResult": {
"description": "Prompt feedback included in the result metadata.",
"properties": {
"negativeUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is negative.",
"items": {
"type": "string"
},
"title": "negativeUserIds",
"type": "array"
},
"positiveUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is positive.",
"items": {
"type": "string"
},
"title": "positiveUserIds",
"type": "array"
}
},
"title": "FeedbackResult",
"type": "object"
},
"finalPrompt": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
]
},
"type": "object"
},
"type": "array"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
"type": "array"
},
{
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
{
"type": "null"
}
],
"description": "The final representation of the prompt that was submitted to the LLM.",
"title": "finalPrompt"
},
"inputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM input. This number includes the tokens in the system prompt, the user prompt, the chat history (for history-aware chats) and the documents retrieved from the vector database (in case of using a vector database).",
"title": "inputTokenCount",
"type": "integer"
},
"latencyMilliseconds": {
"description": "The latency of the LLM response (in milliseconds).",
"title": "latencyMilliseconds",
"type": "integer"
},
"metrics": {
"default": [],
"description": "The evaluation metrics for the prompt.",
"items": {
"description": "Prompt metric metadata.",
"properties": {
"costConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the cost configuration.",
"title": "costConfigurationId"
},
"customModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model used for the metric.",
"title": "customModelId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the metric computation.",
"title": "errorMessage"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset configuration.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database."
},
"formattedName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted name of the metric.",
"title": "formattedName"
},
"formattedValue": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted value of the metric.",
"title": "formattedValue"
},
"llmIsDeprecated": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "llmIsDeprecated"
},
"name": {
"description": "The name of the metric.",
"title": "name",
"type": "string"
},
"nemoMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the NeMo Pipeline configuration.",
"title": "nemoMetricId"
},
"ootbMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the OOTB metric configuration.",
"title": "ootbMetricId"
},
"sidecarModelMetricValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the sidecar model validation(in case of using a sidecar model deployment for the metric).",
"title": "sidecarModelMetricValidationId"
},
"stage": {
"anyOf": [
{
"description": "Enum that describes at which stage the metric may be calculated.",
"enum": [
"prompt_pipeline",
"response_pipeline"
],
"title": "PipelineStage",
"type": "string"
},
{
"type": "null"
}
],
"description": "The stage (prompt or response) that the metric applies to."
},
"value": {
"description": "The value of the metric.",
"title": "value"
}
},
"required": [
"name",
"value"
],
"title": "MetricMetadata",
"type": "object"
},
"title": "metrics",
"type": "array"
},
"outputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM output.",
"title": "outputTokenCount",
"type": "integer"
},
"providerLLMGuards": {
"anyOf": [
{
"items": {
"description": "Info on the provider guard metrics.",
"properties": {
"name": {
"description": "The name of the provider guard metric.",
"title": "name",
"type": "string"
},
"satisfyCriteria": {
"description": "Whether the configured provider guard metric satisfied its hidden internal guard criteria.",
"title": "satisfyCriteria",
"type": "boolean"
},
"stage": {
"description": "The data stage where the provider guard metric is acting upon.",
"enum": [
"prompt",
"response"
],
"title": "ProviderGuardStage",
"type": "string"
},
"value": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The value of the provider guard metric.",
"title": "value"
}
},
"required": [
"satisfyCriteria",
"name",
"value",
"stage"
],
"title": "ProviderGuardsMetadata",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The provider llm guards metadata.",
"title": "providerLLMGuards"
},
"totalTokenCount": {
"default": 0,
"description": "The combined number of tokens in the LLM input and output.",
"title": "totalTokenCount",
"type": "integer"
}
},
"required": [
"latencyMilliseconds"
],
"title": "ResultMetadata",
"type": "object"
},
{
"type": "null"
}
],
"description": "The additional information about the prompt result."
},
"resultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The text of the prompt completion.",
"title": "resultText"
}
},
"required": [
"id",
"llmBlueprintId",
"resultText",
"confidenceScores",
"citations",
"executionStatus"
],
"title": "ComparisonPromptResult",
"type": "object"
},
"title": "results",
"type": "array"
},
"text": {
"description": "The text of the user prompt.",
"title": "text",
"type": "string"
},
"userName": {
"description": "The name of the user that created the comparison prompt.",
"title": "userName",
"type": "string"
}
},
"required": [
"id",
"text",
"results",
"creationDate",
"creationUserId",
"userName",
"executionStatus"
],
"title": "ComparisonPromptResponse",
"type": "object"
},
"title": "data",
"type": "array"
},
"next": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the next page, or `null` if there is no such page.",
"title": "next"
},
"previous": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the previous page, or `null` if there is no such page.",
"title": "previous"
},
"totalCount": {
"description": "The total number of records.",
"title": "totalCount",
"type": "integer"
}
},
"required": [
"totalCount",
"count",
"next",
"previous",
"data"
],
"title": "ListComparisonPromptsResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Successful Response | ListComparisonPromptsResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
POST /api/v2/genai/comparisonPrompts/¶
Request the execution of a new comparison prompt.
Body parameter¶
{
"description": "The body of the \"Create comparison prompt\" request.",
"properties": {
"comparisonChatId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the comparison chat to associate the comparison prompt with.",
"title": "comparisonChatId"
},
"llmBlueprintIds": {
"description": "The list of LLM blueprint IDs that should execute the comparison prompt.",
"items": {
"type": "string"
},
"maxItems": 10,
"title": "llmBlueprintIds",
"type": "array"
},
"metadataFilter": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "The metadata dict that defines filters that the retrieved documents need to match.",
"title": "metadataFilter"
},
"text": {
"description": "The text of the user prompt.",
"maxLength": 500000,
"title": "text",
"type": "string"
}
},
"required": [
"llmBlueprintIds",
"text"
],
"title": "CreateComparisonPromptRequest",
"type": "object"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| body | body | CreateComparisonPromptRequest | true | none |
Example responses¶
202 Response
{
"description": "ComparisonPrompt object formatted for API output.",
"properties": {
"comparisonChatId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the comparison chat associated with the comparison prompt.",
"title": "comparisonChatId"
},
"creationDate": {
"description": "The creation date of the comparison prompt (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created the comparison prompt.",
"title": "creationUserId",
"type": "string"
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"id": {
"description": "The ID of the comparison prompt.",
"title": "id",
"type": "string"
},
"metadataFilter": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "The metadata filters applied to the comparison prompt.",
"title": "metadataFilter"
},
"results": {
"description": "The list of comparison prompt results.",
"items": {
"description": "API response object for a single comparison prompt result.",
"properties": {
"chatContextId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the chat context for this prompt.",
"title": "chatContextId"
},
"citations": {
"description": "The list of relevant vector database citations (in case of using a vector database).",
"items": {
"description": "API response object for a single vector database citation.",
"properties": {
"chunkId": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The ID of the chunk in the vector database index.",
"title": "chunkId"
},
"metadata": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "LangChain Document metadata information holder.",
"title": "metadata"
},
"page": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The source page number where the citation was found.",
"title": "page"
},
"similarityScore": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The similarity score between the citation and the user prompt.",
"title": "similarityScore"
},
"source": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The source of the citation (e.g., a filename in the original dataset).",
"title": "source"
},
"startIndex": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The chunk's start character index in the source document.",
"title": "startIndex"
},
"text": {
"description": "The text of the citation.",
"title": "text",
"type": "string"
}
},
"required": [
"text",
"source"
],
"title": "Citation",
"type": "object"
},
"title": "citations",
"type": "array"
},
"comparisonPromptResultIdsIncludedInHistory": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of IDs of the comparison prompt results included in this prompt's history.",
"title": "comparisonPromptResultIdsIncludedInHistory"
},
"confidenceScores": {
"anyOf": [
{
"description": "API response object for confidence scores.",
"properties": {
"bleu": {
"description": "BLEU score.",
"title": "bleu",
"type": "number"
},
"meteor": {
"description": "METEOR score.",
"title": "meteor",
"type": "number"
},
"rouge": {
"description": "ROUGE score.",
"title": "rouge",
"type": "number"
}
},
"required": [
"rouge",
"meteor",
"bleu"
],
"title": "ConfidenceScores",
"type": "object"
},
{
"type": "null"
}
],
"description": "The confidence scores that measure the similarity between the prompt context and the prompt completion."
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"id": {
"description": "The ID of the comparison prompt result.",
"title": "id",
"type": "string"
},
"llmBlueprintId": {
"description": "The ID of the LLM blueprint that produced the result.",
"title": "llmBlueprintId",
"type": "string"
},
"resultMetadata": {
"anyOf": [
{
"description": "The additional information about prompt execution results.",
"properties": {
"blockedResultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The message to replace the result text if it is non empty, which represents a blocked response.",
"title": "blockedResultText"
},
"cost": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The estimated cost of executing the prompt.",
"title": "cost"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message for the prompt (in case of an errored prompt).",
"title": "errorMessage"
},
"estimatedDocsTokenCount": {
"default": 0,
"description": "The estimated number of tokens in the documents retrieved from the vector database.",
"title": "estimatedDocsTokenCount",
"type": "integer"
},
"feedbackResult": {
"description": "Prompt feedback included in the result metadata.",
"properties": {
"negativeUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is negative.",
"items": {
"type": "string"
},
"title": "negativeUserIds",
"type": "array"
},
"positiveUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is positive.",
"items": {
"type": "string"
},
"title": "positiveUserIds",
"type": "array"
}
},
"title": "FeedbackResult",
"type": "object"
},
"finalPrompt": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
]
},
"type": "object"
},
"type": "array"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
"type": "array"
},
{
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
{
"type": "null"
}
],
"description": "The final representation of the prompt that was submitted to the LLM.",
"title": "finalPrompt"
},
"inputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM input. This number includes the tokens in the system prompt, the user prompt, the chat history (for history-aware chats) and the documents retrieved from the vector database (in case of using a vector database).",
"title": "inputTokenCount",
"type": "integer"
},
"latencyMilliseconds": {
"description": "The latency of the LLM response (in milliseconds).",
"title": "latencyMilliseconds",
"type": "integer"
},
"metrics": {
"default": [],
"description": "The evaluation metrics for the prompt.",
"items": {
"description": "Prompt metric metadata.",
"properties": {
"costConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the cost configuration.",
"title": "costConfigurationId"
},
"customModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model used for the metric.",
"title": "customModelId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the metric computation.",
"title": "errorMessage"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset configuration.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database."
},
"formattedName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted name of the metric.",
"title": "formattedName"
},
"formattedValue": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted value of the metric.",
"title": "formattedValue"
},
"llmIsDeprecated": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "llmIsDeprecated"
},
"name": {
"description": "The name of the metric.",
"title": "name",
"type": "string"
},
"nemoMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the NeMo Pipeline configuration.",
"title": "nemoMetricId"
},
"ootbMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the OOTB metric configuration.",
"title": "ootbMetricId"
},
"sidecarModelMetricValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the sidecar model validation(in case of using a sidecar model deployment for the metric).",
"title": "sidecarModelMetricValidationId"
},
"stage": {
"anyOf": [
{
"description": "Enum that describes at which stage the metric may be calculated.",
"enum": [
"prompt_pipeline",
"response_pipeline"
],
"title": "PipelineStage",
"type": "string"
},
{
"type": "null"
}
],
"description": "The stage (prompt or response) that the metric applies to."
},
"value": {
"description": "The value of the metric.",
"title": "value"
}
},
"required": [
"name",
"value"
],
"title": "MetricMetadata",
"type": "object"
},
"title": "metrics",
"type": "array"
},
"outputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM output.",
"title": "outputTokenCount",
"type": "integer"
},
"providerLLMGuards": {
"anyOf": [
{
"items": {
"description": "Info on the provider guard metrics.",
"properties": {
"name": {
"description": "The name of the provider guard metric.",
"title": "name",
"type": "string"
},
"satisfyCriteria": {
"description": "Whether the configured provider guard metric satisfied its hidden internal guard criteria.",
"title": "satisfyCriteria",
"type": "boolean"
},
"stage": {
"description": "The data stage where the provider guard metric is acting upon.",
"enum": [
"prompt",
"response"
],
"title": "ProviderGuardStage",
"type": "string"
},
"value": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The value of the provider guard metric.",
"title": "value"
}
},
"required": [
"satisfyCriteria",
"name",
"value",
"stage"
],
"title": "ProviderGuardsMetadata",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The provider llm guards metadata.",
"title": "providerLLMGuards"
},
"totalTokenCount": {
"default": 0,
"description": "The combined number of tokens in the LLM input and output.",
"title": "totalTokenCount",
"type": "integer"
}
},
"required": [
"latencyMilliseconds"
],
"title": "ResultMetadata",
"type": "object"
},
{
"type": "null"
}
],
"description": "The additional information about the prompt result."
},
"resultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The text of the prompt completion.",
"title": "resultText"
}
},
"required": [
"id",
"llmBlueprintId",
"resultText",
"confidenceScores",
"citations",
"executionStatus"
],
"title": "ComparisonPromptResult",
"type": "object"
},
"title": "results",
"type": "array"
},
"text": {
"description": "The text of the user prompt.",
"title": "text",
"type": "string"
},
"userName": {
"description": "The name of the user that created the comparison prompt.",
"title": "userName",
"type": "string"
}
},
"required": [
"id",
"text",
"results",
"creationDate",
"creationUserId",
"userName",
"executionStatus"
],
"title": "ComparisonPromptResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 202 | Accepted | Successful Response | ComparisonPromptResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
DELETE /api/v2/genai/comparisonPrompts/{comparisonPromptId}/¶
Delete an existing comparison prompt.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| comparisonPromptId | path | string | true | The ID of the comparison prompt to delete. |
Example responses¶
422 Response
{
"properties": {
"detail": {
"items": {
"properties": {
"loc": {
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
]
},
"title": "loc",
"type": "array"
},
"msg": {
"title": "msg",
"type": "string"
},
"type": {
"title": "type",
"type": "string"
}
},
"required": [
"loc",
"msg",
"type"
],
"title": "ValidationError",
"type": "object"
},
"title": "detail",
"type": "array"
}
},
"title": "HTTPValidationErrorResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 204 | No Content | Successful Response | None |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/genai/comparisonPrompts/{comparisonPromptId}/¶
Retrieve an existing comparison prompt.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| comparisonPromptId | path | string | true | The ID of the comparison prompt to retrieve. |
Example responses¶
200 Response
{
"description": "ComparisonPrompt object formatted for API output.",
"properties": {
"comparisonChatId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the comparison chat associated with the comparison prompt.",
"title": "comparisonChatId"
},
"creationDate": {
"description": "The creation date of the comparison prompt (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created the comparison prompt.",
"title": "creationUserId",
"type": "string"
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"id": {
"description": "The ID of the comparison prompt.",
"title": "id",
"type": "string"
},
"metadataFilter": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "The metadata filters applied to the comparison prompt.",
"title": "metadataFilter"
},
"results": {
"description": "The list of comparison prompt results.",
"items": {
"description": "API response object for a single comparison prompt result.",
"properties": {
"chatContextId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the chat context for this prompt.",
"title": "chatContextId"
},
"citations": {
"description": "The list of relevant vector database citations (in case of using a vector database).",
"items": {
"description": "API response object for a single vector database citation.",
"properties": {
"chunkId": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The ID of the chunk in the vector database index.",
"title": "chunkId"
},
"metadata": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "LangChain Document metadata information holder.",
"title": "metadata"
},
"page": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The source page number where the citation was found.",
"title": "page"
},
"similarityScore": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The similarity score between the citation and the user prompt.",
"title": "similarityScore"
},
"source": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The source of the citation (e.g., a filename in the original dataset).",
"title": "source"
},
"startIndex": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The chunk's start character index in the source document.",
"title": "startIndex"
},
"text": {
"description": "The text of the citation.",
"title": "text",
"type": "string"
}
},
"required": [
"text",
"source"
],
"title": "Citation",
"type": "object"
},
"title": "citations",
"type": "array"
},
"comparisonPromptResultIdsIncludedInHistory": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of IDs of the comparison prompt results included in this prompt's history.",
"title": "comparisonPromptResultIdsIncludedInHistory"
},
"confidenceScores": {
"anyOf": [
{
"description": "API response object for confidence scores.",
"properties": {
"bleu": {
"description": "BLEU score.",
"title": "bleu",
"type": "number"
},
"meteor": {
"description": "METEOR score.",
"title": "meteor",
"type": "number"
},
"rouge": {
"description": "ROUGE score.",
"title": "rouge",
"type": "number"
}
},
"required": [
"rouge",
"meteor",
"bleu"
],
"title": "ConfidenceScores",
"type": "object"
},
{
"type": "null"
}
],
"description": "The confidence scores that measure the similarity between the prompt context and the prompt completion."
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"id": {
"description": "The ID of the comparison prompt result.",
"title": "id",
"type": "string"
},
"llmBlueprintId": {
"description": "The ID of the LLM blueprint that produced the result.",
"title": "llmBlueprintId",
"type": "string"
},
"resultMetadata": {
"anyOf": [
{
"description": "The additional information about prompt execution results.",
"properties": {
"blockedResultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The message to replace the result text if it is non empty, which represents a blocked response.",
"title": "blockedResultText"
},
"cost": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The estimated cost of executing the prompt.",
"title": "cost"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message for the prompt (in case of an errored prompt).",
"title": "errorMessage"
},
"estimatedDocsTokenCount": {
"default": 0,
"description": "The estimated number of tokens in the documents retrieved from the vector database.",
"title": "estimatedDocsTokenCount",
"type": "integer"
},
"feedbackResult": {
"description": "Prompt feedback included in the result metadata.",
"properties": {
"negativeUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is negative.",
"items": {
"type": "string"
},
"title": "negativeUserIds",
"type": "array"
},
"positiveUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is positive.",
"items": {
"type": "string"
},
"title": "positiveUserIds",
"type": "array"
}
},
"title": "FeedbackResult",
"type": "object"
},
"finalPrompt": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
]
},
"type": "object"
},
"type": "array"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
"type": "array"
},
{
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
{
"type": "null"
}
],
"description": "The final representation of the prompt that was submitted to the LLM.",
"title": "finalPrompt"
},
"inputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM input. This number includes the tokens in the system prompt, the user prompt, the chat history (for history-aware chats) and the documents retrieved from the vector database (in case of using a vector database).",
"title": "inputTokenCount",
"type": "integer"
},
"latencyMilliseconds": {
"description": "The latency of the LLM response (in milliseconds).",
"title": "latencyMilliseconds",
"type": "integer"
},
"metrics": {
"default": [],
"description": "The evaluation metrics for the prompt.",
"items": {
"description": "Prompt metric metadata.",
"properties": {
"costConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the cost configuration.",
"title": "costConfigurationId"
},
"customModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model used for the metric.",
"title": "customModelId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the metric computation.",
"title": "errorMessage"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset configuration.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database."
},
"formattedName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted name of the metric.",
"title": "formattedName"
},
"formattedValue": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted value of the metric.",
"title": "formattedValue"
},
"llmIsDeprecated": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "llmIsDeprecated"
},
"name": {
"description": "The name of the metric.",
"title": "name",
"type": "string"
},
"nemoMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the NeMo Pipeline configuration.",
"title": "nemoMetricId"
},
"ootbMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the OOTB metric configuration.",
"title": "ootbMetricId"
},
"sidecarModelMetricValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the sidecar model validation(in case of using a sidecar model deployment for the metric).",
"title": "sidecarModelMetricValidationId"
},
"stage": {
"anyOf": [
{
"description": "Enum that describes at which stage the metric may be calculated.",
"enum": [
"prompt_pipeline",
"response_pipeline"
],
"title": "PipelineStage",
"type": "string"
},
{
"type": "null"
}
],
"description": "The stage (prompt or response) that the metric applies to."
},
"value": {
"description": "The value of the metric.",
"title": "value"
}
},
"required": [
"name",
"value"
],
"title": "MetricMetadata",
"type": "object"
},
"title": "metrics",
"type": "array"
},
"outputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM output.",
"title": "outputTokenCount",
"type": "integer"
},
"providerLLMGuards": {
"anyOf": [
{
"items": {
"description": "Info on the provider guard metrics.",
"properties": {
"name": {
"description": "The name of the provider guard metric.",
"title": "name",
"type": "string"
},
"satisfyCriteria": {
"description": "Whether the configured provider guard metric satisfied its hidden internal guard criteria.",
"title": "satisfyCriteria",
"type": "boolean"
},
"stage": {
"description": "The data stage where the provider guard metric is acting upon.",
"enum": [
"prompt",
"response"
],
"title": "ProviderGuardStage",
"type": "string"
},
"value": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The value of the provider guard metric.",
"title": "value"
}
},
"required": [
"satisfyCriteria",
"name",
"value",
"stage"
],
"title": "ProviderGuardsMetadata",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The provider llm guards metadata.",
"title": "providerLLMGuards"
},
"totalTokenCount": {
"default": 0,
"description": "The combined number of tokens in the LLM input and output.",
"title": "totalTokenCount",
"type": "integer"
}
},
"required": [
"latencyMilliseconds"
],
"title": "ResultMetadata",
"type": "object"
},
{
"type": "null"
}
],
"description": "The additional information about the prompt result."
},
"resultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The text of the prompt completion.",
"title": "resultText"
}
},
"required": [
"id",
"llmBlueprintId",
"resultText",
"confidenceScores",
"citations",
"executionStatus"
],
"title": "ComparisonPromptResult",
"type": "object"
},
"title": "results",
"type": "array"
},
"text": {
"description": "The text of the user prompt.",
"title": "text",
"type": "string"
},
"userName": {
"description": "The name of the user that created the comparison prompt.",
"title": "userName",
"type": "string"
}
},
"required": [
"id",
"text",
"results",
"creationDate",
"creationUserId",
"userName",
"executionStatus"
],
"title": "ComparisonPromptResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Successful Response | ComparisonPromptResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
PATCH /api/v2/genai/comparisonPrompts/{comparisonPromptId}/¶
Edit an existing comparison prompt. Editing may involve adding new prompt result metadata or executing this comparison prompt on new LLM blueprints.
Body parameter¶
{
"description": "The body of the \"Edit comparison prompt\" request.",
"properties": {
"additionalLLMBlueprintIds": {
"default": [],
"description": "The list of additional LLM blueprint IDs that should execute this comparison prompt.",
"items": {
"type": "string"
},
"maxItems": 10,
"title": "additionalLLMBlueprintIds",
"type": "array"
},
"feedbackResult": {
"anyOf": [
{
"description": "Feedback metadata for a comparison prompt result.",
"properties": {
"comparisonPromptResultId": {
"description": "The ID of the comparison prompt result associated with this feedback.",
"title": "comparisonPromptResultId",
"type": "string"
},
"feedbackMetadata": {
"description": "Prompt feedback metadata.",
"properties": {
"feedback": {
"anyOf": [
{
"description": "The sentiment of the feedback.",
"enum": [
"1",
"0"
],
"title": "FeedbackSentiment",
"type": "string"
},
{
"type": "null"
}
],
"description": "The sentiment of the feedback."
}
},
"required": [
"feedback"
],
"title": "FeedbackMetadata",
"type": "object"
}
},
"required": [
"comparisonPromptResultId",
"feedbackMetadata"
],
"title": "ComparisonPromptFeedbackResult",
"type": "object"
},
{
"type": "null"
}
],
"description": "The feedback information to add to the comparison prompt."
}
},
"title": "EditComparisonPromptRequest",
"type": "object"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| comparisonPromptId | path | string | true | The ID of the comparison prompt to edit. |
| body | body | EditComparisonPromptRequest | true | none |
Example responses¶
202 Response
{
"title": "Response Update Comparison Prompt Comparisonprompts Comparisonpromptid Patch",
"type": "string"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 202 | Accepted | Successful Response | string |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
Schemas¶
ChatPromptResponse
{
"description": "API response object for a single chat prompt.",
"properties": {
"chatContextId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the chat context for this prompt.",
"title": "chatContextId"
},
"chatId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the chat this chat prompt belongs to.",
"title": "chatId"
},
"chatPromptIdsIncludedInHistory": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of IDs of the chat prompts included in this prompt's history.",
"title": "chatPromptIdsIncludedInHistory"
},
"citations": {
"description": "The list of relevant vector database citations (in case of using a vector database).",
"items": {
"description": "API response object for a single vector database citation.",
"properties": {
"chunkId": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The ID of the chunk in the vector database index.",
"title": "chunkId"
},
"metadata": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "LangChain Document metadata information holder.",
"title": "metadata"
},
"page": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The source page number where the citation was found.",
"title": "page"
},
"similarityScore": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The similarity score between the citation and the user prompt.",
"title": "similarityScore"
},
"source": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The source of the citation (e.g., a filename in the original dataset).",
"title": "source"
},
"startIndex": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The chunk's start character index in the source document.",
"title": "startIndex"
},
"text": {
"description": "The text of the citation.",
"title": "text",
"type": "string"
}
},
"required": [
"text",
"source"
],
"title": "Citation",
"type": "object"
},
"title": "citations",
"type": "array"
},
"confidenceScores": {
"anyOf": [
{
"description": "API response object for confidence scores.",
"properties": {
"bleu": {
"description": "BLEU score.",
"title": "bleu",
"type": "number"
},
"meteor": {
"description": "METEOR score.",
"title": "meteor",
"type": "number"
},
"rouge": {
"description": "ROUGE score.",
"title": "rouge",
"type": "number"
}
},
"required": [
"rouge",
"meteor",
"bleu"
],
"title": "ConfidenceScores",
"type": "object"
},
{
"type": "null"
}
],
"description": "The confidence scores that measure the similarity between the prompt context and the prompt completion."
},
"creationDate": {
"description": "The creation date of the chat prompt (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created the chat prompt.",
"title": "creationUserId",
"type": "string"
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"id": {
"description": "The ID of the chat prompt.",
"title": "id",
"type": "string"
},
"llmBlueprintId": {
"description": "The ID of the LLM blueprint the chat prompt belongs to.",
"title": "llmBlueprintId",
"type": "string"
},
"llmId": {
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
"llmSettings": {
"anyOf": [
{
"additionalProperties": false,
"description": "The settings that are available for all non-custom LLMs.",
"properties": {
"maxCompletionLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Maximum number of tokens allowed in the completion. The combined count of this value and prompt tokens must be below the model's maximum context size, where prompt token count is comprised of system prompt, user prompt, recent chat history, and vector database citations.",
"title": "maxCompletionLength"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Temperature controls the randomness of model output, where higher values return more diverse output and lower values return more deterministic results.",
"title": "temperature"
},
"topP": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Top P sets a threshold that controls the selection of words included in the response, based on a cumulative probability cutoff for token selection. For example, 0.2 considers only the top 20% probability mass. Higher numbers return more diverse options for outputs.",
"title": "topP"
}
},
"title": "CommonLLMSettings",
"type": "object"
},
{
"additionalProperties": false,
"description": "The settings that are available for custom model LLMs.",
"properties": {
"externalLlmContextSize": {
"anyOf": [
{
"maximum": 128000,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The external LLM's context size, in tokens. This value is only used for pruning documents supplied to the LLM when a vector database is associated with the LLM blueprint. It does not affect the external LLM's actual context size in any way and is not supplied to the LLM.",
"title": "externalLlmContextSize"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model LLM.",
"title": "validationId"
}
},
"title": "CustomModelLLMSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of LLM settings.",
"title": "llmSettings"
},
"metadataFilter": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "The metadata dictionary defining the filters that documents must match in order to be retrieved.",
"title": "metadataFilter"
},
"resultMetadata": {
"anyOf": [
{
"description": "The additional information about prompt execution results.",
"properties": {
"blockedResultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The message to replace the result text if it is non empty, which represents a blocked response.",
"title": "blockedResultText"
},
"cost": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The estimated cost of executing the prompt.",
"title": "cost"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message for the prompt (in case of an errored prompt).",
"title": "errorMessage"
},
"estimatedDocsTokenCount": {
"default": 0,
"description": "The estimated number of tokens in the documents retrieved from the vector database.",
"title": "estimatedDocsTokenCount",
"type": "integer"
},
"feedbackResult": {
"description": "Prompt feedback included in the result metadata.",
"properties": {
"negativeUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is negative.",
"items": {
"type": "string"
},
"title": "negativeUserIds",
"type": "array"
},
"positiveUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is positive.",
"items": {
"type": "string"
},
"title": "positiveUserIds",
"type": "array"
}
},
"title": "FeedbackResult",
"type": "object"
},
"finalPrompt": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
]
},
"type": "object"
},
"type": "array"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
"type": "array"
},
{
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
{
"type": "null"
}
],
"description": "The final representation of the prompt that was submitted to the LLM.",
"title": "finalPrompt"
},
"inputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM input. This number includes the tokens in the system prompt, the user prompt, the chat history (for history-aware chats) and the documents retrieved from the vector database (in case of using a vector database).",
"title": "inputTokenCount",
"type": "integer"
},
"latencyMilliseconds": {
"description": "The latency of the LLM response (in milliseconds).",
"title": "latencyMilliseconds",
"type": "integer"
},
"metrics": {
"default": [],
"description": "The evaluation metrics for the prompt.",
"items": {
"description": "Prompt metric metadata.",
"properties": {
"costConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the cost configuration.",
"title": "costConfigurationId"
},
"customModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model used for the metric.",
"title": "customModelId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the metric computation.",
"title": "errorMessage"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset configuration.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database."
},
"formattedName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted name of the metric.",
"title": "formattedName"
},
"formattedValue": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted value of the metric.",
"title": "formattedValue"
},
"llmIsDeprecated": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "llmIsDeprecated"
},
"name": {
"description": "The name of the metric.",
"title": "name",
"type": "string"
},
"nemoMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the NeMo Pipeline configuration.",
"title": "nemoMetricId"
},
"ootbMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the OOTB metric configuration.",
"title": "ootbMetricId"
},
"sidecarModelMetricValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the sidecar model validation(in case of using a sidecar model deployment for the metric).",
"title": "sidecarModelMetricValidationId"
},
"stage": {
"anyOf": [
{
"description": "Enum that describes at which stage the metric may be calculated.",
"enum": [
"prompt_pipeline",
"response_pipeline"
],
"title": "PipelineStage",
"type": "string"
},
{
"type": "null"
}
],
"description": "The stage (prompt or response) that the metric applies to."
},
"value": {
"description": "The value of the metric.",
"title": "value"
}
},
"required": [
"name",
"value"
],
"title": "MetricMetadata",
"type": "object"
},
"title": "metrics",
"type": "array"
},
"outputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM output.",
"title": "outputTokenCount",
"type": "integer"
},
"providerLLMGuards": {
"anyOf": [
{
"items": {
"description": "Info on the provider guard metrics.",
"properties": {
"name": {
"description": "The name of the provider guard metric.",
"title": "name",
"type": "string"
},
"satisfyCriteria": {
"description": "Whether the configured provider guard metric satisfied its hidden internal guard criteria.",
"title": "satisfyCriteria",
"type": "boolean"
},
"stage": {
"description": "The data stage where the provider guard metric is acting upon.",
"enum": [
"prompt",
"response"
],
"title": "ProviderGuardStage",
"type": "string"
},
"value": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The value of the provider guard metric.",
"title": "value"
}
},
"required": [
"satisfyCriteria",
"name",
"value",
"stage"
],
"title": "ProviderGuardsMetadata",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The provider llm guards metadata.",
"title": "providerLLMGuards"
},
"totalTokenCount": {
"default": 0,
"description": "The combined number of tokens in the LLM input and output.",
"title": "totalTokenCount",
"type": "integer"
}
},
"required": [
"latencyMilliseconds"
],
"title": "ResultMetadata",
"type": "object"
},
{
"type": "null"
}
],
"description": "The additional information about the chat prompt results."
},
"resultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The text of the prompt completion.",
"title": "resultText"
},
"text": {
"description": "The text of the user prompt.",
"title": "text",
"type": "string"
},
"userName": {
"description": "The name of the user that created the chat prompt.",
"title": "userName",
"type": "string"
},
"vectorDatabaseFamilyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database family this chat prompt belongs to.",
"title": "vectorDatabaseFamilyId"
},
"vectorDatabaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database linked to this LLM blueprint.",
"title": "vectorDatabaseId"
},
"vectorDatabaseSettings": {
"anyOf": [
{
"description": "Vector database retrieval settings.",
"properties": {
"addNeighborChunks": {
"default": false,
"description": "Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1.",
"title": "addNeighborChunks",
"type": "boolean"
},
"maxDocumentsRetrievedPerPrompt": {
"anyOf": [
{
"maximum": 10,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of chunks to retrieve from the vector database.",
"title": "maxDocumentsRetrievedPerPrompt"
},
"maxTokens": {
"anyOf": [
{
"maximum": 51200,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of tokens to retrieve from the vector database.",
"title": "maxTokens"
},
"retriever": {
"description": "The method used to retrieve relevant chunks from the vector database.",
"enum": [
"SINGLE_LOOKUP_RETRIEVER",
"CONVERSATIONAL_RETRIEVER",
"MULTI_STEP_RETRIEVER"
],
"title": "VectorDatabaseRetrievers",
"type": "string"
}
},
"title": "VectorDatabaseSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of vector database settings."
}
},
"required": [
"llmId",
"id",
"text",
"llmBlueprintId",
"creationDate",
"creationUserId",
"userName",
"resultMetadata",
"resultText",
"confidenceScores",
"citations",
"executionStatus"
],
"title": "ChatPromptResponse",
"type": "object"
}
ChatPromptResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| chatContextId | any | false | The ID of the chat context for this prompt. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| chatId | any | false | The ID of the chat this chat prompt belongs to. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| chatPromptIdsIncludedInHistory | any | false | The list of IDs of the chat prompts included in this prompt's history. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | [string] | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| citations | [Citation] | true | The list of relevant vector database citations (in case of using a vector database). | |
| confidenceScores | any | true | The confidence scores that measure the similarity between the prompt context and the prompt completion. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | ConfidenceScores | false | API response object for confidence scores. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| creationDate | string(date-time) | true | The creation date of the chat prompt (ISO 8601 formatted). | |
| creationUserId | string | true | The ID of the user that created the chat prompt. | |
| executionStatus | ExecutionStatus | true | The execution status of the chat prompt. | |
| id | string | true | The ID of the chat prompt. | |
| llmBlueprintId | string | true | The ID of the LLM blueprint the chat prompt belongs to. | |
| llmId | LanguageModelTypeId | true | The ID of the LLM used by the chat prompt. | |
| llmSettings | any | false | A key/value dictionary of LLM settings. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | CommonLLMSettings | false | The settings that are available for all non-custom LLMs. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | CustomModelLLMSettings | false | The settings that are available for custom model LLMs. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| metadataFilter | any | false | The metadata dictionary defining the filters that documents must match in order to be retrieved. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | object | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| resultMetadata | any | true | The additional information about the chat prompt results. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | ResultMetadata | false | The additional information about prompt execution results. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| resultText | any | true | The text of the prompt completion. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| text | string | true | The text of the user prompt. | |
| userName | string | true | The name of the user that created the chat prompt. | |
| vectorDatabaseFamilyId | any | false | The ID of the vector database family this chat prompt belongs to. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| vectorDatabaseId | any | false | The ID of the vector database linked to this LLM blueprint. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| vectorDatabaseSettings | any | false | A key/value dictionary of vector database settings. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | VectorDatabaseSettings | false | Vector database retrieval settings. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
ChatResponse
{
"description": "Chat object formatted for API output.",
"properties": {
"creationDate": {
"description": "The creation date of the chat (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created the chat.",
"title": "creationUserId",
"type": "string"
},
"id": {
"description": "The ID of the chat.",
"title": "id",
"type": "string"
},
"isFrozen": {
"description": "Whether the chat is frozen (e.g., an evaluation chat). If the chat is frozen, it does not accept new prompts.",
"title": "isFrozen",
"type": "boolean"
},
"llmBlueprintId": {
"description": "The ID of the LLM blueprint associated with the chat.",
"title": "llmBlueprintId",
"type": "string"
},
"name": {
"description": "The name of the chat.",
"title": "name",
"type": "string"
},
"promptsCount": {
"description": "The number of chat prompts in the chat.",
"title": "promptsCount",
"type": "integer"
},
"warning": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Warning about the contents of the chat.",
"title": "warning"
}
},
"required": [
"id",
"name",
"llmBlueprintId",
"isFrozen",
"warning",
"creationDate",
"creationUserId",
"promptsCount"
],
"title": "ChatResponse",
"type": "object"
}
ChatResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| creationDate | string(date-time) | true | The creation date of the chat (ISO 8601 formatted). | |
| creationUserId | string | true | The ID of the user that created the chat. | |
| id | string | true | The ID of the chat. | |
| isFrozen | boolean | true | Whether the chat is frozen (e.g., an evaluation chat). If the chat is frozen, it does not accept new prompts. | |
| llmBlueprintId | string | true | The ID of the LLM blueprint associated with the chat. | |
| name | string | true | The name of the chat. | |
| promptsCount | integer | true | The number of chat prompts in the chat. | |
| warning | any | true | Warning about the contents of the chat. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
ChatsSortQueryParam
{
"description": "Sort order values for listing chats.",
"enum": [
"name",
"-name",
"creationDate",
"-creationDate"
],
"title": "ChatsSortQueryParam",
"type": "string"
}
ChatsSortQueryParam
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| ChatsSortQueryParam | string | false | Sort order values for listing chats. |
Enumerated Values¶
| Property | Value |
|---|---|
| ChatsSortQueryParam | [name, -name, creationDate, -creationDate] |
Citation
{
"description": "API response object for a single vector database citation.",
"properties": {
"chunkId": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The ID of the chunk in the vector database index.",
"title": "chunkId"
},
"metadata": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "LangChain Document metadata information holder.",
"title": "metadata"
},
"page": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The source page number where the citation was found.",
"title": "page"
},
"similarityScore": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The similarity score between the citation and the user prompt.",
"title": "similarityScore"
},
"source": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The source of the citation (e.g., a filename in the original dataset).",
"title": "source"
},
"startIndex": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The chunk's start character index in the source document.",
"title": "startIndex"
},
"text": {
"description": "The text of the citation.",
"title": "text",
"type": "string"
}
},
"required": [
"text",
"source"
],
"title": "Citation",
"type": "object"
}
Citation
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| chunkId | any | false | The ID of the chunk in the vector database index. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | integer | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| metadata | any | false | LangChain Document metadata information holder. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | object | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| page | any | false | The source page number where the citation was found. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | integer | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| similarityScore | any | false | The similarity score between the citation and the user prompt. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | number | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| source | any | true | The source of the citation (e.g., a filename in the original dataset). |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| startIndex | any | false | The chunk's start character index in the source document. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | integer | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| text | string | true | The text of the citation. |
CommonLLMSettings
{
"additionalProperties": false,
"description": "The settings that are available for all non-custom LLMs.",
"properties": {
"maxCompletionLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Maximum number of tokens allowed in the completion. The combined count of this value and prompt tokens must be below the model's maximum context size, where prompt token count is comprised of system prompt, user prompt, recent chat history, and vector database citations.",
"title": "maxCompletionLength"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Temperature controls the randomness of model output, where higher values return more diverse output and lower values return more deterministic results.",
"title": "temperature"
},
"topP": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Top P sets a threshold that controls the selection of words included in the response, based on a cumulative probability cutoff for token selection. For example, 0.2 considers only the top 20% probability mass. Higher numbers return more diverse options for outputs.",
"title": "topP"
}
},
"title": "CommonLLMSettings",
"type": "object"
}
CommonLLMSettings
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| maxCompletionLength | any | false | Maximum number of tokens allowed in the completion. The combined count of this value and prompt tokens must be below the model's maximum context size, where prompt token count is comprised of system prompt, user prompt, recent chat history, and vector database citations. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | integer | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| systemPrompt | any | false | System prompt guides the style of the LLM response. It is a "universal" prompt, prepended to all individual prompts. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | maxLength: 500000 |
none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| temperature | any | false | Temperature controls the randomness of model output, where higher values return more diverse output and lower values return more deterministic results. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | number | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| topP | any | false | Top P sets a threshold that controls the selection of words included in the response, based on a cumulative probability cutoff for token selection. For example, 0.2 considers only the top 20% probability mass. Higher numbers return more diverse options for outputs. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | number | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
ComparisonChatResponse
{
"description": "Comparison chat object formatted for API output.",
"properties": {
"creationDate": {
"description": "The creation date of the comparison chat (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created the comparison chat.",
"title": "creationUserId",
"type": "string"
},
"id": {
"description": "The ID of the comparison chat.",
"title": "id",
"type": "string"
},
"name": {
"description": "The name of the comparison chat.",
"title": "name",
"type": "string"
},
"playgroundId": {
"description": "The ID of the playground associated with the comparison chat.",
"title": "playgroundId",
"type": "string"
},
"promptsCount": {
"description": "The number of comparison prompts in the comparison chat.",
"title": "promptsCount",
"type": "integer"
}
},
"required": [
"id",
"name",
"playgroundId",
"creationDate",
"creationUserId",
"promptsCount"
],
"title": "ComparisonChatResponse",
"type": "object"
}
ComparisonChatResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| creationDate | string(date-time) | true | The creation date of the comparison chat (ISO 8601 formatted). | |
| creationUserId | string | true | The ID of the user that created the comparison chat. | |
| id | string | true | The ID of the comparison chat. | |
| name | string | true | The name of the comparison chat. | |
| playgroundId | string | true | The ID of the playground associated with the comparison chat. | |
| promptsCount | integer | true | The number of comparison prompts in the comparison chat. |
ComparisonChatsSortQueryParam
{
"description": "Sort order values for listing comparison chats.",
"enum": [
"name",
"-name",
"creationDate",
"-creationDate"
],
"title": "ComparisonChatsSortQueryParam",
"type": "string"
}
ComparisonChatsSortQueryParam
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| ComparisonChatsSortQueryParam | string | false | Sort order values for listing comparison chats. |
Enumerated Values¶
| Property | Value |
|---|---|
| ComparisonChatsSortQueryParam | [name, -name, creationDate, -creationDate] |
ComparisonPromptFeedbackResult
{
"description": "Feedback metadata for a comparison prompt result.",
"properties": {
"comparisonPromptResultId": {
"description": "The ID of the comparison prompt result associated with this feedback.",
"title": "comparisonPromptResultId",
"type": "string"
},
"feedbackMetadata": {
"description": "Prompt feedback metadata.",
"properties": {
"feedback": {
"anyOf": [
{
"description": "The sentiment of the feedback.",
"enum": [
"1",
"0"
],
"title": "FeedbackSentiment",
"type": "string"
},
{
"type": "null"
}
],
"description": "The sentiment of the feedback."
}
},
"required": [
"feedback"
],
"title": "FeedbackMetadata",
"type": "object"
}
},
"required": [
"comparisonPromptResultId",
"feedbackMetadata"
],
"title": "ComparisonPromptFeedbackResult",
"type": "object"
}
ComparisonPromptFeedbackResult
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| comparisonPromptResultId | string | true | The ID of the comparison prompt result associated with this feedback. | |
| feedbackMetadata | FeedbackMetadata | true | The feedback metadata for the comparison prompt result. |
ComparisonPromptResponse
{
"description": "ComparisonPrompt object formatted for API output.",
"properties": {
"comparisonChatId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the comparison chat associated with the comparison prompt.",
"title": "comparisonChatId"
},
"creationDate": {
"description": "The creation date of the comparison prompt (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created the comparison prompt.",
"title": "creationUserId",
"type": "string"
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"id": {
"description": "The ID of the comparison prompt.",
"title": "id",
"type": "string"
},
"metadataFilter": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "The metadata filters applied to the comparison prompt.",
"title": "metadataFilter"
},
"results": {
"description": "The list of comparison prompt results.",
"items": {
"description": "API response object for a single comparison prompt result.",
"properties": {
"chatContextId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the chat context for this prompt.",
"title": "chatContextId"
},
"citations": {
"description": "The list of relevant vector database citations (in case of using a vector database).",
"items": {
"description": "API response object for a single vector database citation.",
"properties": {
"chunkId": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The ID of the chunk in the vector database index.",
"title": "chunkId"
},
"metadata": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "LangChain Document metadata information holder.",
"title": "metadata"
},
"page": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The source page number where the citation was found.",
"title": "page"
},
"similarityScore": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The similarity score between the citation and the user prompt.",
"title": "similarityScore"
},
"source": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The source of the citation (e.g., a filename in the original dataset).",
"title": "source"
},
"startIndex": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The chunk's start character index in the source document.",
"title": "startIndex"
},
"text": {
"description": "The text of the citation.",
"title": "text",
"type": "string"
}
},
"required": [
"text",
"source"
],
"title": "Citation",
"type": "object"
},
"title": "citations",
"type": "array"
},
"comparisonPromptResultIdsIncludedInHistory": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of IDs of the comparison prompt results included in this prompt's history.",
"title": "comparisonPromptResultIdsIncludedInHistory"
},
"confidenceScores": {
"anyOf": [
{
"description": "API response object for confidence scores.",
"properties": {
"bleu": {
"description": "BLEU score.",
"title": "bleu",
"type": "number"
},
"meteor": {
"description": "METEOR score.",
"title": "meteor",
"type": "number"
},
"rouge": {
"description": "ROUGE score.",
"title": "rouge",
"type": "number"
}
},
"required": [
"rouge",
"meteor",
"bleu"
],
"title": "ConfidenceScores",
"type": "object"
},
{
"type": "null"
}
],
"description": "The confidence scores that measure the similarity between the prompt context and the prompt completion."
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"id": {
"description": "The ID of the comparison prompt result.",
"title": "id",
"type": "string"
},
"llmBlueprintId": {
"description": "The ID of the LLM blueprint that produced the result.",
"title": "llmBlueprintId",
"type": "string"
},
"resultMetadata": {
"anyOf": [
{
"description": "The additional information about prompt execution results.",
"properties": {
"blockedResultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The message to replace the result text if it is non empty, which represents a blocked response.",
"title": "blockedResultText"
},
"cost": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The estimated cost of executing the prompt.",
"title": "cost"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message for the prompt (in case of an errored prompt).",
"title": "errorMessage"
},
"estimatedDocsTokenCount": {
"default": 0,
"description": "The estimated number of tokens in the documents retrieved from the vector database.",
"title": "estimatedDocsTokenCount",
"type": "integer"
},
"feedbackResult": {
"description": "Prompt feedback included in the result metadata.",
"properties": {
"negativeUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is negative.",
"items": {
"type": "string"
},
"title": "negativeUserIds",
"type": "array"
},
"positiveUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is positive.",
"items": {
"type": "string"
},
"title": "positiveUserIds",
"type": "array"
}
},
"title": "FeedbackResult",
"type": "object"
},
"finalPrompt": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
]
},
"type": "object"
},
"type": "array"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
"type": "array"
},
{
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
{
"type": "null"
}
],
"description": "The final representation of the prompt that was submitted to the LLM.",
"title": "finalPrompt"
},
"inputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM input. This number includes the tokens in the system prompt, the user prompt, the chat history (for history-aware chats) and the documents retrieved from the vector database (in case of using a vector database).",
"title": "inputTokenCount",
"type": "integer"
},
"latencyMilliseconds": {
"description": "The latency of the LLM response (in milliseconds).",
"title": "latencyMilliseconds",
"type": "integer"
},
"metrics": {
"default": [],
"description": "The evaluation metrics for the prompt.",
"items": {
"description": "Prompt metric metadata.",
"properties": {
"costConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the cost configuration.",
"title": "costConfigurationId"
},
"customModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model used for the metric.",
"title": "customModelId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the metric computation.",
"title": "errorMessage"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset configuration.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database."
},
"formattedName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted name of the metric.",
"title": "formattedName"
},
"formattedValue": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted value of the metric.",
"title": "formattedValue"
},
"llmIsDeprecated": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "llmIsDeprecated"
},
"name": {
"description": "The name of the metric.",
"title": "name",
"type": "string"
},
"nemoMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the NeMo Pipeline configuration.",
"title": "nemoMetricId"
},
"ootbMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the OOTB metric configuration.",
"title": "ootbMetricId"
},
"sidecarModelMetricValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the sidecar model validation(in case of using a sidecar model deployment for the metric).",
"title": "sidecarModelMetricValidationId"
},
"stage": {
"anyOf": [
{
"description": "Enum that describes at which stage the metric may be calculated.",
"enum": [
"prompt_pipeline",
"response_pipeline"
],
"title": "PipelineStage",
"type": "string"
},
{
"type": "null"
}
],
"description": "The stage (prompt or response) that the metric applies to."
},
"value": {
"description": "The value of the metric.",
"title": "value"
}
},
"required": [
"name",
"value"
],
"title": "MetricMetadata",
"type": "object"
},
"title": "metrics",
"type": "array"
},
"outputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM output.",
"title": "outputTokenCount",
"type": "integer"
},
"providerLLMGuards": {
"anyOf": [
{
"items": {
"description": "Info on the provider guard metrics.",
"properties": {
"name": {
"description": "The name of the provider guard metric.",
"title": "name",
"type": "string"
},
"satisfyCriteria": {
"description": "Whether the configured provider guard metric satisfied its hidden internal guard criteria.",
"title": "satisfyCriteria",
"type": "boolean"
},
"stage": {
"description": "The data stage where the provider guard metric is acting upon.",
"enum": [
"prompt",
"response"
],
"title": "ProviderGuardStage",
"type": "string"
},
"value": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The value of the provider guard metric.",
"title": "value"
}
},
"required": [
"satisfyCriteria",
"name",
"value",
"stage"
],
"title": "ProviderGuardsMetadata",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The provider llm guards metadata.",
"title": "providerLLMGuards"
},
"totalTokenCount": {
"default": 0,
"description": "The combined number of tokens in the LLM input and output.",
"title": "totalTokenCount",
"type": "integer"
}
},
"required": [
"latencyMilliseconds"
],
"title": "ResultMetadata",
"type": "object"
},
{
"type": "null"
}
],
"description": "The additional information about the prompt result."
},
"resultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The text of the prompt completion.",
"title": "resultText"
}
},
"required": [
"id",
"llmBlueprintId",
"resultText",
"confidenceScores",
"citations",
"executionStatus"
],
"title": "ComparisonPromptResult",
"type": "object"
},
"title": "results",
"type": "array"
},
"text": {
"description": "The text of the user prompt.",
"title": "text",
"type": "string"
},
"userName": {
"description": "The name of the user that created the comparison prompt.",
"title": "userName",
"type": "string"
}
},
"required": [
"id",
"text",
"results",
"creationDate",
"creationUserId",
"userName",
"executionStatus"
],
"title": "ComparisonPromptResponse",
"type": "object"
}
ComparisonPromptResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| comparisonChatId | any | false | The ID of the comparison chat associated with the comparison prompt. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| creationDate | string(date-time) | true | The creation date of the comparison prompt (ISO 8601 formatted). | |
| creationUserId | string | true | The ID of the user that created the comparison prompt. | |
| executionStatus | ExecutionStatus | true | The execution status of the entire comparison prompt. | |
| id | string | true | The ID of the comparison prompt. | |
| metadataFilter | any | false | The metadata filters applied to the comparison prompt. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | object | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| results | [ComparisonPromptResult] | true | The list of comparison prompt results. | |
| text | string | true | The text of the user prompt. | |
| userName | string | true | The name of the user that created the comparison prompt. |
ComparisonPromptResult
{
"description": "API response object for a single comparison prompt result.",
"properties": {
"chatContextId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the chat context for this prompt.",
"title": "chatContextId"
},
"citations": {
"description": "The list of relevant vector database citations (in case of using a vector database).",
"items": {
"description": "API response object for a single vector database citation.",
"properties": {
"chunkId": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The ID of the chunk in the vector database index.",
"title": "chunkId"
},
"metadata": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "LangChain Document metadata information holder.",
"title": "metadata"
},
"page": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The source page number where the citation was found.",
"title": "page"
},
"similarityScore": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The similarity score between the citation and the user prompt.",
"title": "similarityScore"
},
"source": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The source of the citation (e.g., a filename in the original dataset).",
"title": "source"
},
"startIndex": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The chunk's start character index in the source document.",
"title": "startIndex"
},
"text": {
"description": "The text of the citation.",
"title": "text",
"type": "string"
}
},
"required": [
"text",
"source"
],
"title": "Citation",
"type": "object"
},
"title": "citations",
"type": "array"
},
"comparisonPromptResultIdsIncludedInHistory": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of IDs of the comparison prompt results included in this prompt's history.",
"title": "comparisonPromptResultIdsIncludedInHistory"
},
"confidenceScores": {
"anyOf": [
{
"description": "API response object for confidence scores.",
"properties": {
"bleu": {
"description": "BLEU score.",
"title": "bleu",
"type": "number"
},
"meteor": {
"description": "METEOR score.",
"title": "meteor",
"type": "number"
},
"rouge": {
"description": "ROUGE score.",
"title": "rouge",
"type": "number"
}
},
"required": [
"rouge",
"meteor",
"bleu"
],
"title": "ConfidenceScores",
"type": "object"
},
{
"type": "null"
}
],
"description": "The confidence scores that measure the similarity between the prompt context and the prompt completion."
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"id": {
"description": "The ID of the comparison prompt result.",
"title": "id",
"type": "string"
},
"llmBlueprintId": {
"description": "The ID of the LLM blueprint that produced the result.",
"title": "llmBlueprintId",
"type": "string"
},
"resultMetadata": {
"anyOf": [
{
"description": "The additional information about prompt execution results.",
"properties": {
"blockedResultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The message to replace the result text if it is non empty, which represents a blocked response.",
"title": "blockedResultText"
},
"cost": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The estimated cost of executing the prompt.",
"title": "cost"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message for the prompt (in case of an errored prompt).",
"title": "errorMessage"
},
"estimatedDocsTokenCount": {
"default": 0,
"description": "The estimated number of tokens in the documents retrieved from the vector database.",
"title": "estimatedDocsTokenCount",
"type": "integer"
},
"feedbackResult": {
"description": "Prompt feedback included in the result metadata.",
"properties": {
"negativeUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is negative.",
"items": {
"type": "string"
},
"title": "negativeUserIds",
"type": "array"
},
"positiveUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is positive.",
"items": {
"type": "string"
},
"title": "positiveUserIds",
"type": "array"
}
},
"title": "FeedbackResult",
"type": "object"
},
"finalPrompt": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
]
},
"type": "object"
},
"type": "array"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
"type": "array"
},
{
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
{
"type": "null"
}
],
"description": "The final representation of the prompt that was submitted to the LLM.",
"title": "finalPrompt"
},
"inputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM input. This number includes the tokens in the system prompt, the user prompt, the chat history (for history-aware chats) and the documents retrieved from the vector database (in case of using a vector database).",
"title": "inputTokenCount",
"type": "integer"
},
"latencyMilliseconds": {
"description": "The latency of the LLM response (in milliseconds).",
"title": "latencyMilliseconds",
"type": "integer"
},
"metrics": {
"default": [],
"description": "The evaluation metrics for the prompt.",
"items": {
"description": "Prompt metric metadata.",
"properties": {
"costConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the cost configuration.",
"title": "costConfigurationId"
},
"customModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model used for the metric.",
"title": "customModelId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the metric computation.",
"title": "errorMessage"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset configuration.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database."
},
"formattedName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted name of the metric.",
"title": "formattedName"
},
"formattedValue": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted value of the metric.",
"title": "formattedValue"
},
"llmIsDeprecated": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "llmIsDeprecated"
},
"name": {
"description": "The name of the metric.",
"title": "name",
"type": "string"
},
"nemoMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the NeMo Pipeline configuration.",
"title": "nemoMetricId"
},
"ootbMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the OOTB metric configuration.",
"title": "ootbMetricId"
},
"sidecarModelMetricValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the sidecar model validation(in case of using a sidecar model deployment for the metric).",
"title": "sidecarModelMetricValidationId"
},
"stage": {
"anyOf": [
{
"description": "Enum that describes at which stage the metric may be calculated.",
"enum": [
"prompt_pipeline",
"response_pipeline"
],
"title": "PipelineStage",
"type": "string"
},
{
"type": "null"
}
],
"description": "The stage (prompt or response) that the metric applies to."
},
"value": {
"description": "The value of the metric.",
"title": "value"
}
},
"required": [
"name",
"value"
],
"title": "MetricMetadata",
"type": "object"
},
"title": "metrics",
"type": "array"
},
"outputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM output.",
"title": "outputTokenCount",
"type": "integer"
},
"providerLLMGuards": {
"anyOf": [
{
"items": {
"description": "Info on the provider guard metrics.",
"properties": {
"name": {
"description": "The name of the provider guard metric.",
"title": "name",
"type": "string"
},
"satisfyCriteria": {
"description": "Whether the configured provider guard metric satisfied its hidden internal guard criteria.",
"title": "satisfyCriteria",
"type": "boolean"
},
"stage": {
"description": "The data stage where the provider guard metric is acting upon.",
"enum": [
"prompt",
"response"
],
"title": "ProviderGuardStage",
"type": "string"
},
"value": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The value of the provider guard metric.",
"title": "value"
}
},
"required": [
"satisfyCriteria",
"name",
"value",
"stage"
],
"title": "ProviderGuardsMetadata",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The provider llm guards metadata.",
"title": "providerLLMGuards"
},
"totalTokenCount": {
"default": 0,
"description": "The combined number of tokens in the LLM input and output.",
"title": "totalTokenCount",
"type": "integer"
}
},
"required": [
"latencyMilliseconds"
],
"title": "ResultMetadata",
"type": "object"
},
{
"type": "null"
}
],
"description": "The additional information about the prompt result."
},
"resultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The text of the prompt completion.",
"title": "resultText"
}
},
"required": [
"id",
"llmBlueprintId",
"resultText",
"confidenceScores",
"citations",
"executionStatus"
],
"title": "ComparisonPromptResult",
"type": "object"
}
ComparisonPromptResult
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| chatContextId | any | false | The ID of the chat context for this prompt. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| citations | [Citation] | true | The list of relevant vector database citations (in case of using a vector database). | |
| comparisonPromptResultIdsIncludedInHistory | any | false | The list of IDs of the comparison prompt results included in this prompt's history. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | [string] | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| confidenceScores | any | true | The confidence scores that measure the similarity between the prompt context and the prompt completion. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | ConfidenceScores | false | API response object for confidence scores. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| executionStatus | ExecutionStatus | true | The execution status of the comparison prompt by this LLM blueprint. | |
| id | string | true | The ID of the comparison prompt result. | |
| llmBlueprintId | string | true | The ID of the LLM blueprint that produced the result. | |
| resultMetadata | any | false | The additional information about the prompt result. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | ResultMetadata | false | The additional information about prompt execution results. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| resultText | any | true | The text of the prompt completion. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
ConfidenceScores
{
"description": "API response object for confidence scores.",
"properties": {
"bleu": {
"description": "BLEU score.",
"title": "bleu",
"type": "number"
},
"meteor": {
"description": "METEOR score.",
"title": "meteor",
"type": "number"
},
"rouge": {
"description": "ROUGE score.",
"title": "rouge",
"type": "number"
}
},
"required": [
"rouge",
"meteor",
"bleu"
],
"title": "ConfidenceScores",
"type": "object"
}
ConfidenceScores
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| bleu | number | true | BLEU score. | |
| meteor | number | true | METEOR score. | |
| rouge | number | true | ROUGE score. |
CreateChatPromptRequest
{
"description": "The body of the \"Create chat prompt\" request.",
"properties": {
"chatId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the chat this prompt belongs to. If LLM and vector database settings are not specified in the request, then the prompt will use the current settings of the chat.",
"title": "chatId"
},
"llmBlueprintId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the LLM blueprint this prompt belongs to. If LLM and vector database settings are not specified in the request, then the prompt will use the current settings of the LLM blueprint.",
"title": "llmBlueprintId"
},
"llmId": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "If specified, uses this LLM ID for the prompt and updates the settings of the corresponding chat or LLM blueprint to use this LLM ID."
},
"llmSettings": {
"anyOf": [
{
"additionalProperties": false,
"description": "The settings that are available for all non-custom LLMs.",
"properties": {
"maxCompletionLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Maximum number of tokens allowed in the completion. The combined count of this value and prompt tokens must be below the model's maximum context size, where prompt token count is comprised of system prompt, user prompt, recent chat history, and vector database citations.",
"title": "maxCompletionLength"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Temperature controls the randomness of model output, where higher values return more diverse output and lower values return more deterministic results.",
"title": "temperature"
},
"topP": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Top P sets a threshold that controls the selection of words included in the response, based on a cumulative probability cutoff for token selection. For example, 0.2 considers only the top 20% probability mass. Higher numbers return more diverse options for outputs.",
"title": "topP"
}
},
"title": "CommonLLMSettings",
"type": "object"
},
{
"additionalProperties": false,
"description": "The settings that are available for custom model LLMs.",
"properties": {
"externalLlmContextSize": {
"anyOf": [
{
"maximum": 128000,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The external LLM's context size, in tokens. This value is only used for pruning documents supplied to the LLM when a vector database is associated with the LLM blueprint. It does not affect the external LLM's actual context size in any way and is not supplied to the LLM.",
"title": "externalLlmContextSize"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model LLM.",
"title": "validationId"
}
},
"title": "CustomModelLLMSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "If specified, uses these LLM settings for the prompt and updates the settings of the corresponding chat or LLM blueprint to use these LLM settings.",
"title": "llmSettings"
},
"metadataFilter": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "The metadata fields to add to the chat prompt.",
"title": "metadataFilter"
},
"text": {
"description": "The text of the user prompt.",
"maxLength": 500000,
"title": "text",
"type": "string"
},
"vectorDatabaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "If specified, uses this vector database ID for the prompt and updates the settings of the corresponding chat or LLM blueprint to use this vector database ID.",
"title": "vectorDatabaseId"
},
"vectorDatabaseSettings": {
"anyOf": [
{
"description": "Vector database retrieval settings.",
"properties": {
"addNeighborChunks": {
"default": false,
"description": "Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1.",
"title": "addNeighborChunks",
"type": "boolean"
},
"maxDocumentsRetrievedPerPrompt": {
"anyOf": [
{
"maximum": 10,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of chunks to retrieve from the vector database.",
"title": "maxDocumentsRetrievedPerPrompt"
},
"maxTokens": {
"anyOf": [
{
"maximum": 51200,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of tokens to retrieve from the vector database.",
"title": "maxTokens"
},
"retriever": {
"description": "The method used to retrieve relevant chunks from the vector database.",
"enum": [
"SINGLE_LOOKUP_RETRIEVER",
"CONVERSATIONAL_RETRIEVER",
"MULTI_STEP_RETRIEVER"
],
"title": "VectorDatabaseRetrievers",
"type": "string"
}
},
"title": "VectorDatabaseSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "If specified, uses these vector database settings for the prompt and updates the settings of the corresponding chat or LLM blueprint to use these vector database settings."
}
},
"required": [
"text"
],
"title": "CreateChatPromptRequest",
"type": "object"
}
CreateChatPromptRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| chatId | any | false | The ID of the chat this prompt belongs to. If LLM and vector database settings are not specified in the request, then the prompt will use the current settings of the chat. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| llmBlueprintId | any | false | The ID of the LLM blueprint this prompt belongs to. If LLM and vector database settings are not specified in the request, then the prompt will use the current settings of the LLM blueprint. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| llmId | any | false | If specified, uses this LLM ID for the prompt and updates the settings of the corresponding chat or LLM blueprint to use this LLM ID. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | LanguageModelTypeId | false | The ID that defines the type of the LLM. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| llmSettings | any | false | If specified, uses these LLM settings for the prompt and updates the settings of the corresponding chat or LLM blueprint to use these LLM settings. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | CommonLLMSettings | false | The settings that are available for all non-custom LLMs. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | CustomModelLLMSettings | false | The settings that are available for custom model LLMs. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| metadataFilter | any | false | The metadata fields to add to the chat prompt. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | object | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| text | string | true | maxLength: 500000 |
The text of the user prompt. |
| vectorDatabaseId | any | false | If specified, uses this vector database ID for the prompt and updates the settings of the corresponding chat or LLM blueprint to use this vector database ID. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| vectorDatabaseSettings | any | false | If specified, uses these vector database settings for the prompt and updates the settings of the corresponding chat or LLM blueprint to use these vector database settings. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | VectorDatabaseSettings | false | Vector database retrieval settings. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
CreateChatRequest
{
"description": "The body of the \"Create chat\" request.",
"properties": {
"llmBlueprintId": {
"description": "The ID of the LLM blueprint to associate with the chat.",
"title": "llmBlueprintId",
"type": "string"
},
"name": {
"description": "The name of the chat.",
"maxLength": 5000,
"minLength": 1,
"title": "name",
"type": "string"
}
},
"required": [
"name",
"llmBlueprintId"
],
"title": "CreateChatRequest",
"type": "object"
}
CreateChatRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| llmBlueprintId | string | true | The ID of the LLM blueprint to associate with the chat. | |
| name | string | true | maxLength: 5000 minLength: 1 minLength: 1 |
The name of the chat. |
CreateComparisonChatRequest
{
"description": "The body of the \"Create comparison chat\" request.",
"properties": {
"name": {
"description": "The name of the comparison chat.",
"maxLength": 5000,
"minLength": 1,
"title": "name",
"type": "string"
},
"playgroundId": {
"description": "The ID of the playground to associate with the comparison chat.",
"title": "playgroundId",
"type": "string"
}
},
"required": [
"name",
"playgroundId"
],
"title": "CreateComparisonChatRequest",
"type": "object"
}
CreateComparisonChatRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| name | string | true | maxLength: 5000 minLength: 1 minLength: 1 |
The name of the comparison chat. |
| playgroundId | string | true | The ID of the playground to associate with the comparison chat. |
CreateComparisonPromptRequest
{
"description": "The body of the \"Create comparison prompt\" request.",
"properties": {
"comparisonChatId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the comparison chat to associate the comparison prompt with.",
"title": "comparisonChatId"
},
"llmBlueprintIds": {
"description": "The list of LLM blueprint IDs that should execute the comparison prompt.",
"items": {
"type": "string"
},
"maxItems": 10,
"title": "llmBlueprintIds",
"type": "array"
},
"metadataFilter": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "The metadata dict that defines filters that the retrieved documents need to match.",
"title": "metadataFilter"
},
"text": {
"description": "The text of the user prompt.",
"maxLength": 500000,
"title": "text",
"type": "string"
}
},
"required": [
"llmBlueprintIds",
"text"
],
"title": "CreateComparisonPromptRequest",
"type": "object"
}
CreateComparisonPromptRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| comparisonChatId | any | false | The ID of the comparison chat to associate the comparison prompt with. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| llmBlueprintIds | [string] | true | maxItems: 10 |
The list of LLM blueprint IDs that should execute the comparison prompt. |
| metadataFilter | any | false | The metadata dict that defines filters that the retrieved documents need to match. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | object | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| text | string | true | maxLength: 500000 |
The text of the user prompt. |
CustomModelLLMSettings
{
"additionalProperties": false,
"description": "The settings that are available for custom model LLMs.",
"properties": {
"externalLlmContextSize": {
"anyOf": [
{
"maximum": 128000,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The external LLM's context size, in tokens. This value is only used for pruning documents supplied to the LLM when a vector database is associated with the LLM blueprint. It does not affect the external LLM's actual context size in any way and is not supplied to the LLM.",
"title": "externalLlmContextSize"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model LLM.",
"title": "validationId"
}
},
"title": "CustomModelLLMSettings",
"type": "object"
}
CustomModelLLMSettings
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| externalLlmContextSize | any | false | The external LLM's context size, in tokens. This value is only used for pruning documents supplied to the LLM when a vector database is associated with the LLM blueprint. It does not affect the external LLM's actual context size in any way and is not supplied to the LLM. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | integer | false | maximum: 128000 minimum: 128 |
none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| systemPrompt | any | false | System prompt guides the style of the LLM response. It is a "universal" prompt, prepended to all individual prompts. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | maxLength: 500000 |
none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| validationId | any | false | The validation ID of the custom model LLM. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
EditChatPromptRequest
{
"description": "The body of the \"Update chat prompt\" request.",
"properties": {
"customMetrics": {
"anyOf": [
{
"items": {
"description": "Prompt metric metadata.",
"properties": {
"costConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the cost configuration.",
"title": "costConfigurationId"
},
"customModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model used for the metric.",
"title": "customModelId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the metric computation.",
"title": "errorMessage"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset configuration.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database."
},
"formattedName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted name of the metric.",
"title": "formattedName"
},
"formattedValue": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted value of the metric.",
"title": "formattedValue"
},
"llmIsDeprecated": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "llmIsDeprecated"
},
"name": {
"description": "The name of the metric.",
"title": "name",
"type": "string"
},
"nemoMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the NeMo Pipeline configuration.",
"title": "nemoMetricId"
},
"ootbMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the OOTB metric configuration.",
"title": "ootbMetricId"
},
"sidecarModelMetricValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the sidecar model validation(in case of using a sidecar model deployment for the metric).",
"title": "sidecarModelMetricValidationId"
},
"stage": {
"anyOf": [
{
"description": "Enum that describes at which stage the metric may be calculated.",
"enum": [
"prompt_pipeline",
"response_pipeline"
],
"title": "PipelineStage",
"type": "string"
},
{
"type": "null"
}
],
"description": "The stage (prompt or response) that the metric applies to."
},
"value": {
"description": "The value of the metric.",
"title": "value"
}
},
"required": [
"name",
"value"
],
"title": "MetricMetadata",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of metric results to add to the chat prompt.",
"title": "customMetrics"
},
"feedbackMetadata": {
"anyOf": [
{
"description": "Prompt feedback metadata.",
"properties": {
"feedback": {
"anyOf": [
{
"description": "The sentiment of the feedback.",
"enum": [
"1",
"0"
],
"title": "FeedbackSentiment",
"type": "string"
},
{
"type": "null"
}
],
"description": "The sentiment of the feedback."
}
},
"required": [
"feedback"
],
"title": "FeedbackMetadata",
"type": "object"
},
{
"type": "null"
}
],
"description": "The feedback metadata to add to the chat prompt."
}
},
"title": "EditChatPromptRequest",
"type": "object"
}
EditChatPromptRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| customMetrics | any | false | The list of metric results to add to the chat prompt. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | [MetricMetadata] | false | [Prompt metric metadata.] |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| feedbackMetadata | any | false | The feedback metadata to add to the chat prompt. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | FeedbackMetadata | false | Prompt feedback metadata. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
EditChatRequest
{
"description": "The body of the \"Edit chat\" request.",
"properties": {
"name": {
"description": "The new name of the chat.",
"maxLength": 5000,
"minLength": 1,
"title": "name",
"type": "string"
}
},
"required": [
"name"
],
"title": "EditChatRequest",
"type": "object"
}
EditChatRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| name | string | true | maxLength: 5000 minLength: 1 minLength: 1 |
The new name of the chat. |
EditComparisonChatRequest
{
"description": "The body of the \"Edit comparison chat\" request.",
"properties": {
"name": {
"description": "The new name of the comparison chat.",
"maxLength": 5000,
"minLength": 1,
"title": "name",
"type": "string"
}
},
"required": [
"name"
],
"title": "EditComparisonChatRequest",
"type": "object"
}
EditComparisonChatRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| name | string | true | maxLength: 5000 minLength: 1 minLength: 1 |
The new name of the comparison chat. |
EditComparisonPromptRequest
{
"description": "The body of the \"Edit comparison prompt\" request.",
"properties": {
"additionalLLMBlueprintIds": {
"default": [],
"description": "The list of additional LLM blueprint IDs that should execute this comparison prompt.",
"items": {
"type": "string"
},
"maxItems": 10,
"title": "additionalLLMBlueprintIds",
"type": "array"
},
"feedbackResult": {
"anyOf": [
{
"description": "Feedback metadata for a comparison prompt result.",
"properties": {
"comparisonPromptResultId": {
"description": "The ID of the comparison prompt result associated with this feedback.",
"title": "comparisonPromptResultId",
"type": "string"
},
"feedbackMetadata": {
"description": "Prompt feedback metadata.",
"properties": {
"feedback": {
"anyOf": [
{
"description": "The sentiment of the feedback.",
"enum": [
"1",
"0"
],
"title": "FeedbackSentiment",
"type": "string"
},
{
"type": "null"
}
],
"description": "The sentiment of the feedback."
}
},
"required": [
"feedback"
],
"title": "FeedbackMetadata",
"type": "object"
}
},
"required": [
"comparisonPromptResultId",
"feedbackMetadata"
],
"title": "ComparisonPromptFeedbackResult",
"type": "object"
},
{
"type": "null"
}
],
"description": "The feedback information to add to the comparison prompt."
}
},
"title": "EditComparisonPromptRequest",
"type": "object"
}
EditComparisonPromptRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| additionalLLMBlueprintIds | [string] | false | maxItems: 10 |
The list of additional LLM blueprint IDs that should execute this comparison prompt. |
| feedbackResult | any | false | The feedback information to add to the comparison prompt. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | ComparisonPromptFeedbackResult | false | Feedback metadata for a comparison prompt result. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
ExecutionStatus
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
}
ExecutionStatus
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| ExecutionStatus | string | false | Job and entity execution status. |
Enumerated Values¶
| Property | Value |
|---|---|
| ExecutionStatus | [NEW, RUNNING, COMPLETED, REQUIRES_USER_INPUT, SKIPPED, ERROR] |
FeedbackMetadata
{
"description": "Prompt feedback metadata.",
"properties": {
"feedback": {
"anyOf": [
{
"description": "The sentiment of the feedback.",
"enum": [
"1",
"0"
],
"title": "FeedbackSentiment",
"type": "string"
},
{
"type": "null"
}
],
"description": "The sentiment of the feedback."
}
},
"required": [
"feedback"
],
"title": "FeedbackMetadata",
"type": "object"
}
FeedbackMetadata
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| feedback | any | true | The sentiment of the feedback. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | FeedbackSentiment | false | The sentiment of the feedback. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
FeedbackResult
{
"description": "Prompt feedback included in the result metadata.",
"properties": {
"negativeUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is negative.",
"items": {
"type": "string"
},
"title": "negativeUserIds",
"type": "array"
},
"positiveUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is positive.",
"items": {
"type": "string"
},
"title": "positiveUserIds",
"type": "array"
}
},
"title": "FeedbackResult",
"type": "object"
}
FeedbackResult
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| negativeUserIds | [string] | false | The list of user IDs whose feedback is negative. | |
| positiveUserIds | [string] | false | The list of user IDs whose feedback is positive. |
FeedbackSentiment
{
"description": "The sentiment of the feedback.",
"enum": [
"1",
"0"
],
"title": "FeedbackSentiment",
"type": "string"
}
FeedbackSentiment
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| FeedbackSentiment | string | false | The sentiment of the feedback. |
Enumerated Values¶
| Property | Value |
|---|---|
| FeedbackSentiment | [1, 0] |
HTTPValidationErrorResponse
{
"properties": {
"detail": {
"items": {
"properties": {
"loc": {
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
]
},
"title": "loc",
"type": "array"
},
"msg": {
"title": "msg",
"type": "string"
},
"type": {
"title": "type",
"type": "string"
}
},
"required": [
"loc",
"msg",
"type"
],
"title": "ValidationError",
"type": "object"
},
"title": "detail",
"type": "array"
}
},
"title": "HTTPValidationErrorResponse",
"type": "object"
}
HTTPValidationErrorResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| detail | [ValidationError] | false | none |
LanguageModelTypeId
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
}
LanguageModelTypeId
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| LanguageModelTypeId | string | false | The ID that defines the type of the LLM. |
Enumerated Values¶
| Property | Value |
|---|---|
| LanguageModelTypeId | [azure-openai-gpt-3.5-turbo, azure-openai-gpt-3.5-turbo-16k, azure-openai-gpt-4, azure-openai-gpt-4-32k, azure-openai-gpt-4-turbo, azure-openai-gpt-4-o, azure-openai-gpt-4-o-mini, amazon-titan, amazon-nova-micro, amazon-nova-lite, amazon-nova-pro, anthropic-claude-2, anthropic-claude-3-haiku, anthropic-claude-3-sonnet, anthropic-claude-3-opus, anthropic-claude-3.5-sonnet-v1, amazon-anthropic-claude-3.5-sonnet-v2, google-bison, google-gemini-1.5-flash, google-gemini-1.5-pro, custom-model] |
ListChatPromptsResponse
{
"description": "Paginated list of chat prompts.",
"properties": {
"count": {
"description": "The number of records on this page.",
"title": "count",
"type": "integer"
},
"data": {
"description": "The list of records.",
"items": {
"description": "API response object for a single chat prompt.",
"properties": {
"chatContextId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the chat context for this prompt.",
"title": "chatContextId"
},
"chatId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the chat this chat prompt belongs to.",
"title": "chatId"
},
"chatPromptIdsIncludedInHistory": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of IDs of the chat prompts included in this prompt's history.",
"title": "chatPromptIdsIncludedInHistory"
},
"citations": {
"description": "The list of relevant vector database citations (in case of using a vector database).",
"items": {
"description": "API response object for a single vector database citation.",
"properties": {
"chunkId": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The ID of the chunk in the vector database index.",
"title": "chunkId"
},
"metadata": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "LangChain Document metadata information holder.",
"title": "metadata"
},
"page": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The source page number where the citation was found.",
"title": "page"
},
"similarityScore": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The similarity score between the citation and the user prompt.",
"title": "similarityScore"
},
"source": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The source of the citation (e.g., a filename in the original dataset).",
"title": "source"
},
"startIndex": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The chunk's start character index in the source document.",
"title": "startIndex"
},
"text": {
"description": "The text of the citation.",
"title": "text",
"type": "string"
}
},
"required": [
"text",
"source"
],
"title": "Citation",
"type": "object"
},
"title": "citations",
"type": "array"
},
"confidenceScores": {
"anyOf": [
{
"description": "API response object for confidence scores.",
"properties": {
"bleu": {
"description": "BLEU score.",
"title": "bleu",
"type": "number"
},
"meteor": {
"description": "METEOR score.",
"title": "meteor",
"type": "number"
},
"rouge": {
"description": "ROUGE score.",
"title": "rouge",
"type": "number"
}
},
"required": [
"rouge",
"meteor",
"bleu"
],
"title": "ConfidenceScores",
"type": "object"
},
{
"type": "null"
}
],
"description": "The confidence scores that measure the similarity between the prompt context and the prompt completion."
},
"creationDate": {
"description": "The creation date of the chat prompt (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created the chat prompt.",
"title": "creationUserId",
"type": "string"
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"id": {
"description": "The ID of the chat prompt.",
"title": "id",
"type": "string"
},
"llmBlueprintId": {
"description": "The ID of the LLM blueprint the chat prompt belongs to.",
"title": "llmBlueprintId",
"type": "string"
},
"llmId": {
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
"llmSettings": {
"anyOf": [
{
"additionalProperties": false,
"description": "The settings that are available for all non-custom LLMs.",
"properties": {
"maxCompletionLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Maximum number of tokens allowed in the completion. The combined count of this value and prompt tokens must be below the model's maximum context size, where prompt token count is comprised of system prompt, user prompt, recent chat history, and vector database citations.",
"title": "maxCompletionLength"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Temperature controls the randomness of model output, where higher values return more diverse output and lower values return more deterministic results.",
"title": "temperature"
},
"topP": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Top P sets a threshold that controls the selection of words included in the response, based on a cumulative probability cutoff for token selection. For example, 0.2 considers only the top 20% probability mass. Higher numbers return more diverse options for outputs.",
"title": "topP"
}
},
"title": "CommonLLMSettings",
"type": "object"
},
{
"additionalProperties": false,
"description": "The settings that are available for custom model LLMs.",
"properties": {
"externalLlmContextSize": {
"anyOf": [
{
"maximum": 128000,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The external LLM's context size, in tokens. This value is only used for pruning documents supplied to the LLM when a vector database is associated with the LLM blueprint. It does not affect the external LLM's actual context size in any way and is not supplied to the LLM.",
"title": "externalLlmContextSize"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model LLM.",
"title": "validationId"
}
},
"title": "CustomModelLLMSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of LLM settings.",
"title": "llmSettings"
},
"metadataFilter": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "The metadata dictionary defining the filters that documents must match in order to be retrieved.",
"title": "metadataFilter"
},
"resultMetadata": {
"anyOf": [
{
"description": "The additional information about prompt execution results.",
"properties": {
"blockedResultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The message to replace the result text if it is non empty, which represents a blocked response.",
"title": "blockedResultText"
},
"cost": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The estimated cost of executing the prompt.",
"title": "cost"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message for the prompt (in case of an errored prompt).",
"title": "errorMessage"
},
"estimatedDocsTokenCount": {
"default": 0,
"description": "The estimated number of tokens in the documents retrieved from the vector database.",
"title": "estimatedDocsTokenCount",
"type": "integer"
},
"feedbackResult": {
"description": "Prompt feedback included in the result metadata.",
"properties": {
"negativeUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is negative.",
"items": {
"type": "string"
},
"title": "negativeUserIds",
"type": "array"
},
"positiveUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is positive.",
"items": {
"type": "string"
},
"title": "positiveUserIds",
"type": "array"
}
},
"title": "FeedbackResult",
"type": "object"
},
"finalPrompt": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
]
},
"type": "object"
},
"type": "array"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
"type": "array"
},
{
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
{
"type": "null"
}
],
"description": "The final representation of the prompt that was submitted to the LLM.",
"title": "finalPrompt"
},
"inputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM input. This number includes the tokens in the system prompt, the user prompt, the chat history (for history-aware chats) and the documents retrieved from the vector database (in case of using a vector database).",
"title": "inputTokenCount",
"type": "integer"
},
"latencyMilliseconds": {
"description": "The latency of the LLM response (in milliseconds).",
"title": "latencyMilliseconds",
"type": "integer"
},
"metrics": {
"default": [],
"description": "The evaluation metrics for the prompt.",
"items": {
"description": "Prompt metric metadata.",
"properties": {
"costConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the cost configuration.",
"title": "costConfigurationId"
},
"customModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model used for the metric.",
"title": "customModelId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the metric computation.",
"title": "errorMessage"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset configuration.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database."
},
"formattedName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted name of the metric.",
"title": "formattedName"
},
"formattedValue": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted value of the metric.",
"title": "formattedValue"
},
"llmIsDeprecated": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "llmIsDeprecated"
},
"name": {
"description": "The name of the metric.",
"title": "name",
"type": "string"
},
"nemoMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the NeMo Pipeline configuration.",
"title": "nemoMetricId"
},
"ootbMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the OOTB metric configuration.",
"title": "ootbMetricId"
},
"sidecarModelMetricValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the sidecar model validation(in case of using a sidecar model deployment for the metric).",
"title": "sidecarModelMetricValidationId"
},
"stage": {
"anyOf": [
{
"description": "Enum that describes at which stage the metric may be calculated.",
"enum": [
"prompt_pipeline",
"response_pipeline"
],
"title": "PipelineStage",
"type": "string"
},
{
"type": "null"
}
],
"description": "The stage (prompt or response) that the metric applies to."
},
"value": {
"description": "The value of the metric.",
"title": "value"
}
},
"required": [
"name",
"value"
],
"title": "MetricMetadata",
"type": "object"
},
"title": "metrics",
"type": "array"
},
"outputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM output.",
"title": "outputTokenCount",
"type": "integer"
},
"providerLLMGuards": {
"anyOf": [
{
"items": {
"description": "Info on the provider guard metrics.",
"properties": {
"name": {
"description": "The name of the provider guard metric.",
"title": "name",
"type": "string"
},
"satisfyCriteria": {
"description": "Whether the configured provider guard metric satisfied its hidden internal guard criteria.",
"title": "satisfyCriteria",
"type": "boolean"
},
"stage": {
"description": "The data stage where the provider guard metric is acting upon.",
"enum": [
"prompt",
"response"
],
"title": "ProviderGuardStage",
"type": "string"
},
"value": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The value of the provider guard metric.",
"title": "value"
}
},
"required": [
"satisfyCriteria",
"name",
"value",
"stage"
],
"title": "ProviderGuardsMetadata",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The provider llm guards metadata.",
"title": "providerLLMGuards"
},
"totalTokenCount": {
"default": 0,
"description": "The combined number of tokens in the LLM input and output.",
"title": "totalTokenCount",
"type": "integer"
}
},
"required": [
"latencyMilliseconds"
],
"title": "ResultMetadata",
"type": "object"
},
{
"type": "null"
}
],
"description": "The additional information about the chat prompt results."
},
"resultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The text of the prompt completion.",
"title": "resultText"
},
"text": {
"description": "The text of the user prompt.",
"title": "text",
"type": "string"
},
"userName": {
"description": "The name of the user that created the chat prompt.",
"title": "userName",
"type": "string"
},
"vectorDatabaseFamilyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database family this chat prompt belongs to.",
"title": "vectorDatabaseFamilyId"
},
"vectorDatabaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database linked to this LLM blueprint.",
"title": "vectorDatabaseId"
},
"vectorDatabaseSettings": {
"anyOf": [
{
"description": "Vector database retrieval settings.",
"properties": {
"addNeighborChunks": {
"default": false,
"description": "Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1.",
"title": "addNeighborChunks",
"type": "boolean"
},
"maxDocumentsRetrievedPerPrompt": {
"anyOf": [
{
"maximum": 10,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of chunks to retrieve from the vector database.",
"title": "maxDocumentsRetrievedPerPrompt"
},
"maxTokens": {
"anyOf": [
{
"maximum": 51200,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of tokens to retrieve from the vector database.",
"title": "maxTokens"
},
"retriever": {
"description": "The method used to retrieve relevant chunks from the vector database.",
"enum": [
"SINGLE_LOOKUP_RETRIEVER",
"CONVERSATIONAL_RETRIEVER",
"MULTI_STEP_RETRIEVER"
],
"title": "VectorDatabaseRetrievers",
"type": "string"
}
},
"title": "VectorDatabaseSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of vector database settings."
}
},
"required": [
"llmId",
"id",
"text",
"llmBlueprintId",
"creationDate",
"creationUserId",
"userName",
"resultMetadata",
"resultText",
"confidenceScores",
"citations",
"executionStatus"
],
"title": "ChatPromptResponse",
"type": "object"
},
"title": "data",
"type": "array"
},
"next": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the next page, or `null` if there is no such page.",
"title": "next"
},
"previous": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the previous page, or `null` if there is no such page.",
"title": "previous"
},
"totalCount": {
"description": "The total number of records.",
"title": "totalCount",
"type": "integer"
}
},
"required": [
"totalCount",
"count",
"next",
"previous",
"data"
],
"title": "ListChatPromptsResponse",
"type": "object"
}
ListChatPromptsResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| count | integer | true | The number of records on this page. | |
| data | [ChatPromptResponse] | true | The list of records. | |
| next | any | true | The URL to the next page, or null if there is no such page. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| previous | any | true | The URL to the previous page, or null if there is no such page. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| totalCount | integer | true | The total number of records. |
ListChatsResponse
{
"description": "Paginated list of chats.",
"properties": {
"count": {
"description": "The number of records on this page.",
"title": "count",
"type": "integer"
},
"data": {
"description": "The list of records.",
"items": {
"description": "Chat object formatted for API output.",
"properties": {
"creationDate": {
"description": "The creation date of the chat (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created the chat.",
"title": "creationUserId",
"type": "string"
},
"id": {
"description": "The ID of the chat.",
"title": "id",
"type": "string"
},
"isFrozen": {
"description": "Whether the chat is frozen (e.g., an evaluation chat). If the chat is frozen, it does not accept new prompts.",
"title": "isFrozen",
"type": "boolean"
},
"llmBlueprintId": {
"description": "The ID of the LLM blueprint associated with the chat.",
"title": "llmBlueprintId",
"type": "string"
},
"name": {
"description": "The name of the chat.",
"title": "name",
"type": "string"
},
"promptsCount": {
"description": "The number of chat prompts in the chat.",
"title": "promptsCount",
"type": "integer"
},
"warning": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Warning about the contents of the chat.",
"title": "warning"
}
},
"required": [
"id",
"name",
"llmBlueprintId",
"isFrozen",
"warning",
"creationDate",
"creationUserId",
"promptsCount"
],
"title": "ChatResponse",
"type": "object"
},
"title": "data",
"type": "array"
},
"next": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the next page, or `null` if there is no such page.",
"title": "next"
},
"previous": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the previous page, or `null` if there is no such page.",
"title": "previous"
},
"totalCount": {
"description": "The total number of records.",
"title": "totalCount",
"type": "integer"
}
},
"required": [
"totalCount",
"count",
"next",
"previous",
"data"
],
"title": "ListChatsResponse",
"type": "object"
}
ListChatsResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| count | integer | true | The number of records on this page. | |
| data | [ChatResponse] | true | The list of records. | |
| next | any | true | The URL to the next page, or null if there is no such page. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| previous | any | true | The URL to the previous page, or null if there is no such page. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| totalCount | integer | true | The total number of records. |
ListComparisonChatsResponse
{
"description": "Paginated list of comparison chats.",
"properties": {
"count": {
"description": "The number of records on this page.",
"title": "count",
"type": "integer"
},
"data": {
"description": "The list of records.",
"items": {
"description": "Comparison chat object formatted for API output.",
"properties": {
"creationDate": {
"description": "The creation date of the comparison chat (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created the comparison chat.",
"title": "creationUserId",
"type": "string"
},
"id": {
"description": "The ID of the comparison chat.",
"title": "id",
"type": "string"
},
"name": {
"description": "The name of the comparison chat.",
"title": "name",
"type": "string"
},
"playgroundId": {
"description": "The ID of the playground associated with the comparison chat.",
"title": "playgroundId",
"type": "string"
},
"promptsCount": {
"description": "The number of comparison prompts in the comparison chat.",
"title": "promptsCount",
"type": "integer"
}
},
"required": [
"id",
"name",
"playgroundId",
"creationDate",
"creationUserId",
"promptsCount"
],
"title": "ComparisonChatResponse",
"type": "object"
},
"title": "data",
"type": "array"
},
"next": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the next page, or `null` if there is no such page.",
"title": "next"
},
"previous": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the previous page, or `null` if there is no such page.",
"title": "previous"
},
"totalCount": {
"description": "The total number of records.",
"title": "totalCount",
"type": "integer"
}
},
"required": [
"totalCount",
"count",
"next",
"previous",
"data"
],
"title": "ListComparisonChatsResponse",
"type": "object"
}
ListComparisonChatsResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| count | integer | true | The number of records on this page. | |
| data | [ComparisonChatResponse] | true | The list of records. | |
| next | any | true | The URL to the next page, or null if there is no such page. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| previous | any | true | The URL to the previous page, or null if there is no such page. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| totalCount | integer | true | The total number of records. |
ListComparisonPromptsResponse
{
"description": "Paginated list of comparison prompts.",
"properties": {
"count": {
"description": "The number of records on this page.",
"title": "count",
"type": "integer"
},
"data": {
"description": "The list of records.",
"items": {
"description": "ComparisonPrompt object formatted for API output.",
"properties": {
"comparisonChatId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the comparison chat associated with the comparison prompt.",
"title": "comparisonChatId"
},
"creationDate": {
"description": "The creation date of the comparison prompt (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created the comparison prompt.",
"title": "creationUserId",
"type": "string"
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"id": {
"description": "The ID of the comparison prompt.",
"title": "id",
"type": "string"
},
"metadataFilter": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "The metadata filters applied to the comparison prompt.",
"title": "metadataFilter"
},
"results": {
"description": "The list of comparison prompt results.",
"items": {
"description": "API response object for a single comparison prompt result.",
"properties": {
"chatContextId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the chat context for this prompt.",
"title": "chatContextId"
},
"citations": {
"description": "The list of relevant vector database citations (in case of using a vector database).",
"items": {
"description": "API response object for a single vector database citation.",
"properties": {
"chunkId": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The ID of the chunk in the vector database index.",
"title": "chunkId"
},
"metadata": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "LangChain Document metadata information holder.",
"title": "metadata"
},
"page": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The source page number where the citation was found.",
"title": "page"
},
"similarityScore": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The similarity score between the citation and the user prompt.",
"title": "similarityScore"
},
"source": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The source of the citation (e.g., a filename in the original dataset).",
"title": "source"
},
"startIndex": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The chunk's start character index in the source document.",
"title": "startIndex"
},
"text": {
"description": "The text of the citation.",
"title": "text",
"type": "string"
}
},
"required": [
"text",
"source"
],
"title": "Citation",
"type": "object"
},
"title": "citations",
"type": "array"
},
"comparisonPromptResultIdsIncludedInHistory": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of IDs of the comparison prompt results included in this prompt's history.",
"title": "comparisonPromptResultIdsIncludedInHistory"
},
"confidenceScores": {
"anyOf": [
{
"description": "API response object for confidence scores.",
"properties": {
"bleu": {
"description": "BLEU score.",
"title": "bleu",
"type": "number"
},
"meteor": {
"description": "METEOR score.",
"title": "meteor",
"type": "number"
},
"rouge": {
"description": "ROUGE score.",
"title": "rouge",
"type": "number"
}
},
"required": [
"rouge",
"meteor",
"bleu"
],
"title": "ConfidenceScores",
"type": "object"
},
{
"type": "null"
}
],
"description": "The confidence scores that measure the similarity between the prompt context and the prompt completion."
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"id": {
"description": "The ID of the comparison prompt result.",
"title": "id",
"type": "string"
},
"llmBlueprintId": {
"description": "The ID of the LLM blueprint that produced the result.",
"title": "llmBlueprintId",
"type": "string"
},
"resultMetadata": {
"anyOf": [
{
"description": "The additional information about prompt execution results.",
"properties": {
"blockedResultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The message to replace the result text if it is non empty, which represents a blocked response.",
"title": "blockedResultText"
},
"cost": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The estimated cost of executing the prompt.",
"title": "cost"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message for the prompt (in case of an errored prompt).",
"title": "errorMessage"
},
"estimatedDocsTokenCount": {
"default": 0,
"description": "The estimated number of tokens in the documents retrieved from the vector database.",
"title": "estimatedDocsTokenCount",
"type": "integer"
},
"feedbackResult": {
"description": "Prompt feedback included in the result metadata.",
"properties": {
"negativeUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is negative.",
"items": {
"type": "string"
},
"title": "negativeUserIds",
"type": "array"
},
"positiveUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is positive.",
"items": {
"type": "string"
},
"title": "positiveUserIds",
"type": "array"
}
},
"title": "FeedbackResult",
"type": "object"
},
"finalPrompt": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
]
},
"type": "object"
},
"type": "array"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
"type": "array"
},
{
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
{
"type": "null"
}
],
"description": "The final representation of the prompt that was submitted to the LLM.",
"title": "finalPrompt"
},
"inputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM input. This number includes the tokens in the system prompt, the user prompt, the chat history (for history-aware chats) and the documents retrieved from the vector database (in case of using a vector database).",
"title": "inputTokenCount",
"type": "integer"
},
"latencyMilliseconds": {
"description": "The latency of the LLM response (in milliseconds).",
"title": "latencyMilliseconds",
"type": "integer"
},
"metrics": {
"default": [],
"description": "The evaluation metrics for the prompt.",
"items": {
"description": "Prompt metric metadata.",
"properties": {
"costConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the cost configuration.",
"title": "costConfigurationId"
},
"customModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model used for the metric.",
"title": "customModelId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the metric computation.",
"title": "errorMessage"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset configuration.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database."
},
"formattedName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted name of the metric.",
"title": "formattedName"
},
"formattedValue": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted value of the metric.",
"title": "formattedValue"
},
"llmIsDeprecated": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "llmIsDeprecated"
},
"name": {
"description": "The name of the metric.",
"title": "name",
"type": "string"
},
"nemoMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the NeMo Pipeline configuration.",
"title": "nemoMetricId"
},
"ootbMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the OOTB metric configuration.",
"title": "ootbMetricId"
},
"sidecarModelMetricValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the sidecar model validation(in case of using a sidecar model deployment for the metric).",
"title": "sidecarModelMetricValidationId"
},
"stage": {
"anyOf": [
{
"description": "Enum that describes at which stage the metric may be calculated.",
"enum": [
"prompt_pipeline",
"response_pipeline"
],
"title": "PipelineStage",
"type": "string"
},
{
"type": "null"
}
],
"description": "The stage (prompt or response) that the metric applies to."
},
"value": {
"description": "The value of the metric.",
"title": "value"
}
},
"required": [
"name",
"value"
],
"title": "MetricMetadata",
"type": "object"
},
"title": "metrics",
"type": "array"
},
"outputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM output.",
"title": "outputTokenCount",
"type": "integer"
},
"providerLLMGuards": {
"anyOf": [
{
"items": {
"description": "Info on the provider guard metrics.",
"properties": {
"name": {
"description": "The name of the provider guard metric.",
"title": "name",
"type": "string"
},
"satisfyCriteria": {
"description": "Whether the configured provider guard metric satisfied its hidden internal guard criteria.",
"title": "satisfyCriteria",
"type": "boolean"
},
"stage": {
"description": "The data stage where the provider guard metric is acting upon.",
"enum": [
"prompt",
"response"
],
"title": "ProviderGuardStage",
"type": "string"
},
"value": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The value of the provider guard metric.",
"title": "value"
}
},
"required": [
"satisfyCriteria",
"name",
"value",
"stage"
],
"title": "ProviderGuardsMetadata",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The provider llm guards metadata.",
"title": "providerLLMGuards"
},
"totalTokenCount": {
"default": 0,
"description": "The combined number of tokens in the LLM input and output.",
"title": "totalTokenCount",
"type": "integer"
}
},
"required": [
"latencyMilliseconds"
],
"title": "ResultMetadata",
"type": "object"
},
{
"type": "null"
}
],
"description": "The additional information about the prompt result."
},
"resultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The text of the prompt completion.",
"title": "resultText"
}
},
"required": [
"id",
"llmBlueprintId",
"resultText",
"confidenceScores",
"citations",
"executionStatus"
],
"title": "ComparisonPromptResult",
"type": "object"
},
"title": "results",
"type": "array"
},
"text": {
"description": "The text of the user prompt.",
"title": "text",
"type": "string"
},
"userName": {
"description": "The name of the user that created the comparison prompt.",
"title": "userName",
"type": "string"
}
},
"required": [
"id",
"text",
"results",
"creationDate",
"creationUserId",
"userName",
"executionStatus"
],
"title": "ComparisonPromptResponse",
"type": "object"
},
"title": "data",
"type": "array"
},
"next": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the next page, or `null` if there is no such page.",
"title": "next"
},
"previous": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the previous page, or `null` if there is no such page.",
"title": "previous"
},
"totalCount": {
"description": "The total number of records.",
"title": "totalCount",
"type": "integer"
}
},
"required": [
"totalCount",
"count",
"next",
"previous",
"data"
],
"title": "ListComparisonPromptsResponse",
"type": "object"
}
ListComparisonPromptsResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| count | integer | true | The number of records on this page. | |
| data | [ComparisonPromptResponse] | true | The list of records. | |
| next | any | true | The URL to the next page, or null if there is no such page. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| previous | any | true | The URL to the previous page, or null if there is no such page. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| totalCount | integer | true | The total number of records. |
MetricMetadata
{
"description": "Prompt metric metadata.",
"properties": {
"costConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the cost configuration.",
"title": "costConfigurationId"
},
"customModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model used for the metric.",
"title": "customModelId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the metric computation.",
"title": "errorMessage"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset configuration.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database."
},
"formattedName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted name of the metric.",
"title": "formattedName"
},
"formattedValue": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted value of the metric.",
"title": "formattedValue"
},
"llmIsDeprecated": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "llmIsDeprecated"
},
"name": {
"description": "The name of the metric.",
"title": "name",
"type": "string"
},
"nemoMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the NeMo Pipeline configuration.",
"title": "nemoMetricId"
},
"ootbMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the OOTB metric configuration.",
"title": "ootbMetricId"
},
"sidecarModelMetricValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the sidecar model validation(in case of using a sidecar model deployment for the metric).",
"title": "sidecarModelMetricValidationId"
},
"stage": {
"anyOf": [
{
"description": "Enum that describes at which stage the metric may be calculated.",
"enum": [
"prompt_pipeline",
"response_pipeline"
],
"title": "PipelineStage",
"type": "string"
},
{
"type": "null"
}
],
"description": "The stage (prompt or response) that the metric applies to."
},
"value": {
"description": "The value of the metric.",
"title": "value"
}
},
"required": [
"name",
"value"
],
"title": "MetricMetadata",
"type": "object"
}
MetricMetadata
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| costConfigurationId | any | false | The ID of the cost configuration. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| customModelId | any | false | The ID of the custom model used for the metric. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| errorMessage | any | false | The error message associated with the metric computation. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| evaluationDatasetConfigurationId | any | false | The ID of the evaluation dataset configuration. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| executionStatus | any | false | The creation status of the vector database. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | ExecutionStatus | false | Job and entity execution status. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| formattedName | any | false | The formatted name of the metric. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| formattedValue | any | false | The formatted value of the metric. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| llmIsDeprecated | any | false | Whether the LLM is deprecated and will be removed in a future release. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | boolean | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| name | string | true | The name of the metric. | |
| nemoMetricId | any | false | The id of the NeMo Pipeline configuration. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| ootbMetricId | any | false | The id of the OOTB metric configuration. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| sidecarModelMetricValidationId | any | false | The validation ID of the sidecar model validation(in case of using a sidecar model deployment for the metric). |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| stage | any | false | The stage (prompt or response) that the metric applies to. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | PipelineStage | false | Enum that describes at which stage the metric may be calculated. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| value | any | true | The value of the metric. |
PipelineStage
{
"description": "Enum that describes at which stage the metric may be calculated.",
"enum": [
"prompt_pipeline",
"response_pipeline"
],
"title": "PipelineStage",
"type": "string"
}
PipelineStage
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| PipelineStage | string | false | Enum that describes at which stage the metric may be calculated. |
Enumerated Values¶
| Property | Value |
|---|---|
| PipelineStage | [prompt_pipeline, response_pipeline] |
ProviderGuardStage
{
"description": "The data stage where the provider guard metric is acting upon.",
"enum": [
"prompt",
"response"
],
"title": "ProviderGuardStage",
"type": "string"
}
ProviderGuardStage
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| ProviderGuardStage | string | false | The data stage where the provider guard metric is acting upon. |
Enumerated Values¶
| Property | Value |
|---|---|
| ProviderGuardStage | [prompt, response] |
ProviderGuardsMetadata
{
"description": "Info on the provider guard metrics.",
"properties": {
"name": {
"description": "The name of the provider guard metric.",
"title": "name",
"type": "string"
},
"satisfyCriteria": {
"description": "Whether the configured provider guard metric satisfied its hidden internal guard criteria.",
"title": "satisfyCriteria",
"type": "boolean"
},
"stage": {
"description": "The data stage where the provider guard metric is acting upon.",
"enum": [
"prompt",
"response"
],
"title": "ProviderGuardStage",
"type": "string"
},
"value": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The value of the provider guard metric.",
"title": "value"
}
},
"required": [
"satisfyCriteria",
"name",
"value",
"stage"
],
"title": "ProviderGuardsMetadata",
"type": "object"
}
ProviderGuardsMetadata
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| name | string | true | The name of the provider guard metric. | |
| satisfyCriteria | boolean | true | Whether the configured provider guard metric satisfied its hidden internal guard criteria. | |
| stage | ProviderGuardStage | true | The data stage where the provider guard metric is acting upon. | |
| value | any | true | The value of the provider guard metric. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | number | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | integer | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
ResultMetadata
{
"description": "The additional information about prompt execution results.",
"properties": {
"blockedResultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The message to replace the result text if it is non empty, which represents a blocked response.",
"title": "blockedResultText"
},
"cost": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The estimated cost of executing the prompt.",
"title": "cost"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message for the prompt (in case of an errored prompt).",
"title": "errorMessage"
},
"estimatedDocsTokenCount": {
"default": 0,
"description": "The estimated number of tokens in the documents retrieved from the vector database.",
"title": "estimatedDocsTokenCount",
"type": "integer"
},
"feedbackResult": {
"description": "Prompt feedback included in the result metadata.",
"properties": {
"negativeUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is negative.",
"items": {
"type": "string"
},
"title": "negativeUserIds",
"type": "array"
},
"positiveUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is positive.",
"items": {
"type": "string"
},
"title": "positiveUserIds",
"type": "array"
}
},
"title": "FeedbackResult",
"type": "object"
},
"finalPrompt": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
]
},
"type": "object"
},
"type": "array"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
"type": "array"
},
{
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
{
"type": "null"
}
],
"description": "The final representation of the prompt that was submitted to the LLM.",
"title": "finalPrompt"
},
"inputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM input. This number includes the tokens in the system prompt, the user prompt, the chat history (for history-aware chats) and the documents retrieved from the vector database (in case of using a vector database).",
"title": "inputTokenCount",
"type": "integer"
},
"latencyMilliseconds": {
"description": "The latency of the LLM response (in milliseconds).",
"title": "latencyMilliseconds",
"type": "integer"
},
"metrics": {
"default": [],
"description": "The evaluation metrics for the prompt.",
"items": {
"description": "Prompt metric metadata.",
"properties": {
"costConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the cost configuration.",
"title": "costConfigurationId"
},
"customModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model used for the metric.",
"title": "customModelId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the metric computation.",
"title": "errorMessage"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset configuration.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database."
},
"formattedName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted name of the metric.",
"title": "formattedName"
},
"formattedValue": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted value of the metric.",
"title": "formattedValue"
},
"llmIsDeprecated": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "llmIsDeprecated"
},
"name": {
"description": "The name of the metric.",
"title": "name",
"type": "string"
},
"nemoMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the NeMo Pipeline configuration.",
"title": "nemoMetricId"
},
"ootbMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the OOTB metric configuration.",
"title": "ootbMetricId"
},
"sidecarModelMetricValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the sidecar model validation(in case of using a sidecar model deployment for the metric).",
"title": "sidecarModelMetricValidationId"
},
"stage": {
"anyOf": [
{
"description": "Enum that describes at which stage the metric may be calculated.",
"enum": [
"prompt_pipeline",
"response_pipeline"
],
"title": "PipelineStage",
"type": "string"
},
{
"type": "null"
}
],
"description": "The stage (prompt or response) that the metric applies to."
},
"value": {
"description": "The value of the metric.",
"title": "value"
}
},
"required": [
"name",
"value"
],
"title": "MetricMetadata",
"type": "object"
},
"title": "metrics",
"type": "array"
},
"outputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM output.",
"title": "outputTokenCount",
"type": "integer"
},
"providerLLMGuards": {
"anyOf": [
{
"items": {
"description": "Info on the provider guard metrics.",
"properties": {
"name": {
"description": "The name of the provider guard metric.",
"title": "name",
"type": "string"
},
"satisfyCriteria": {
"description": "Whether the configured provider guard metric satisfied its hidden internal guard criteria.",
"title": "satisfyCriteria",
"type": "boolean"
},
"stage": {
"description": "The data stage where the provider guard metric is acting upon.",
"enum": [
"prompt",
"response"
],
"title": "ProviderGuardStage",
"type": "string"
},
"value": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The value of the provider guard metric.",
"title": "value"
}
},
"required": [
"satisfyCriteria",
"name",
"value",
"stage"
],
"title": "ProviderGuardsMetadata",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The provider llm guards metadata.",
"title": "providerLLMGuards"
},
"totalTokenCount": {
"default": 0,
"description": "The combined number of tokens in the LLM input and output.",
"title": "totalTokenCount",
"type": "integer"
}
},
"required": [
"latencyMilliseconds"
],
"title": "ResultMetadata",
"type": "object"
}
ResultMetadata
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| blockedResultText | any | false | The message to replace the result text if it is non empty, which represents a blocked response. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| cost | any | false | The estimated cost of executing the prompt. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | number | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| errorMessage | any | false | The error message for the prompt (in case of an errored prompt). |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| estimatedDocsTokenCount | integer | false | The estimated number of tokens in the documents retrieved from the vector database. | |
| feedbackResult | FeedbackResult | false | The user feedback associated with the prompt. | |
| finalPrompt | any | false | The final representation of the prompt that was submitted to the LLM. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | [object] | false | none | |
| »» additionalProperties | any | false | none |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| »»» anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| »»» anonymous | [object] | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| »»» anonymous | null | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | [object] | false | none | |
| »» additionalProperties | any | false | none |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| »»» anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| »»» anonymous | [object] | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | object | false | none | |
| »» additionalProperties | any | false | none |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| »»» anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| »»» anonymous | [object] | false | none | |
| »»»» additionalProperties | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| inputTokenCount | integer | false | The number of tokens in the LLM input. This number includes the tokens in the system prompt, the user prompt, the chat history (for history-aware chats) and the documents retrieved from the vector database (in case of using a vector database). | |
| latencyMilliseconds | integer | true | The latency of the LLM response (in milliseconds). | |
| metrics | [MetricMetadata] | false | The evaluation metrics for the prompt. | |
| outputTokenCount | integer | false | The number of tokens in the LLM output. | |
| providerLLMGuards | any | false | The provider llm guards metadata. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | [ProviderGuardsMetadata] | false | [Info on the provider guard metrics.] |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| totalTokenCount | integer | false | The combined number of tokens in the LLM input and output. |
ValidationError
{
"properties": {
"loc": {
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
]
},
"title": "loc",
"type": "array"
},
"msg": {
"title": "msg",
"type": "string"
},
"type": {
"title": "type",
"type": "string"
}
},
"required": [
"loc",
"msg",
"type"
],
"title": "ValidationError",
"type": "object"
}
ValidationError
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| loc | [anyOf] | true | none |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | integer | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| msg | string | true | none | |
| type | string | true | none |
VectorDatabaseRetrievers
{
"description": "The method used to retrieve relevant chunks from the vector database.",
"enum": [
"SINGLE_LOOKUP_RETRIEVER",
"CONVERSATIONAL_RETRIEVER",
"MULTI_STEP_RETRIEVER"
],
"title": "VectorDatabaseRetrievers",
"type": "string"
}
VectorDatabaseRetrievers
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| VectorDatabaseRetrievers | string | false | The method used to retrieve relevant chunks from the vector database. |
Enumerated Values¶
| Property | Value |
|---|---|
| VectorDatabaseRetrievers | [SINGLE_LOOKUP_RETRIEVER, CONVERSATIONAL_RETRIEVER, MULTI_STEP_RETRIEVER] |
VectorDatabaseSettings
{
"description": "Vector database retrieval settings.",
"properties": {
"addNeighborChunks": {
"default": false,
"description": "Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1.",
"title": "addNeighborChunks",
"type": "boolean"
},
"maxDocumentsRetrievedPerPrompt": {
"anyOf": [
{
"maximum": 10,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of chunks to retrieve from the vector database.",
"title": "maxDocumentsRetrievedPerPrompt"
},
"maxTokens": {
"anyOf": [
{
"maximum": 51200,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of tokens to retrieve from the vector database.",
"title": "maxTokens"
},
"retriever": {
"description": "The method used to retrieve relevant chunks from the vector database.",
"enum": [
"SINGLE_LOOKUP_RETRIEVER",
"CONVERSATIONAL_RETRIEVER",
"MULTI_STEP_RETRIEVER"
],
"title": "VectorDatabaseRetrievers",
"type": "string"
}
},
"title": "VectorDatabaseSettings",
"type": "object"
}
VectorDatabaseSettings
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| addNeighborChunks | boolean | false | Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1. | |
| maxDocumentsRetrievedPerPrompt | any | false | The maximum number of chunks to retrieve from the vector database. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | integer | false | maximum: 10 minimum: 1 |
none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| maxTokens | any | false | The maximum number of tokens to retrieve from the vector database. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | integer | false | maximum: 51200 minimum: 1 |
none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| retriever | VectorDatabaseRetrievers | false | The method used to retrieve relevant chunks from the vector database. |