Developer documentation > API reference > Python API client > Generative AI > Prompting

Prompting¶

Chat¶

class datarobot.models.genai.chat.Chat

Metadata for a DataRobot GenAI chat.

Variables

Attribute	Type	Description
`id`	`str`	The chat ID.
`name`	`str`	The chat name.
`llm_blueprint_id`	`str`	The ID of the LLM blueprint associated with the chat.
`is_frozen`	`bool`	Checks whether the chat is frozen. Prompts cannot be submitted to frozen chats.
`creation_date`	`str`	The date when the chat was created.
`creation_user_id`	`str`	The ID of the creating user.
`warning`	`str` or `None`, optional	The warning about the contents of the chat.
`prompts_count`	`int`	The number of chat prompts in the chat.

create()¶

classmethod create()

Creates a new chat.

Parameters

Parameter	Type	Description
`name`	`str`	The chat name.
`llm_blueprint`	`LLMBlueprint` or `str`	The LLM blueprint associated with the created chat, either LLM blueprint or ID.

Returns

Returns	Description
chat	The created chat.

Return type: Chat

get()¶

classmethod get()

Retrieve a single chat.

Parameters

Parameter	Type	Description
`chat`	`Chat` or `str`	The chat you want to retrieve. Accepts chat or chat ID.

Returns

Returns	Description
chat	The requested chat.

Return type: Chat

list()¶

classmethod list()

List all chats available to the user. If the LLM blueprint is specified, results are restricted to only those chats associated with the LLM blueprint.

Parameters

Parameter	Type	Description
`llm_blueprint`	`Optional[Union[LLMBlueprint`, `str]]`, optional	Returns only those chats associated with a particular LLM blueprint, specified by either the entity or the ID.
`sort`	`Optional[str]`	The property to sort chats by. Prefix the attribute name with a dash ( - ) to sort responses in descending order, (for example, ‘-name’). Supported options are listed in ListChatsSortQueryParams, but the values can differ depending on platform version. The default sort parameter is None, which results in chats returning in order of creation time, descending.

Returns

Returns	Description
chats	Returns a list of chats.

Return type: list[Chat]

delete()¶

method delete()

Delete the single chat.

Return type: None

update()¶

method update()

Update the chat.

Parameters

Parameter	Type	Description
`name`	`str`	The new name for the chat.

Returns

Returns	Description
chat	The updated chat.

Return type: Chat

ChatPrompt¶

class datarobot.models.genai.chat_prompt.ChatPrompt

Metadata for a DataRobot GenAI chat prompt.

Variables

Attribute	Type	Description
`id`	`str`	Chat prompt ID.
`text`	`str`	The prompt text.
`llm_blueprint_id`	`str`	ID of the LLM blueprint associated with the chat prompt.
`llm_id`	`str`	ID of the LLM type. This must be one of the IDs returned by LLMDefinition.list for this user.
`llm_settings`	`dict` or `None`	The LLM settings for the LLM blueprint. The specific keys allowed and the constraints on the values are defined in the response from LLMDefinition.list, but this typically has dict fields. Either:- system_prompt - The system prompt that influences the LLM responses. - max_completion_length - The maximum number of tokens in the completion. - temperature - Controls the variability in the LLM response. - top_p - Sets whether the model considers next tokens with top_p probability mass. or - system_prompt - The system prompt that influences the LLM responses. - validation_id - The ID of the external model LLM validation. - external_llm_context_size - The external LLM’s context size, in tokens, for external model-based LLM blueprints.
`creation_date`	`str`	The date the chat prompt was created.
`creation_user_id`	`str`	ID of the creating user.
`vector_database_id`	`str` or `None`	ID of the vector database associated with the LLM blueprint, if any.
`vector_database_settings`	`VectorDatabaseSettings` or `None`	The settings for the vector database associated with the LLM blueprint, if any.
`result_metadata`	`ResultMetadata` or `None`	Metadata for the result of the chat prompt submission.
`result_text`	`str` or `None`	The result text from the chat prompt submission.
`confidence_scores`	`ConfidenceScores` or `None`	The confidence scores if there is a vector database associated with the chat prompt.
`citations`	`list[Citation]`	List of citations from text retrieved from the vector database, if any.
`execution_status`	`str`	The execution status of the chat prompt.
`chat_id`	`Optional[str]`	ID of the chat associated with the chat prompt.
`chat_context_id`	`Optional[str]`	The ID of the chat context for the chat prompt.
`chat_prompt_ids_included_in_history`	`Optional[list[str]]`	The IDs of the chat prompts included in the chat history for this chat prompt.
`metadata_filter`	`Optional[Dict[str`, `Any] \\| None]`	The metadata filter to apply to the vector database. Supports:- None or empty dict (no filters): Considers all documents - Multiple field filters (implicit AND): {“a”: 1, “b”: “b”} - Comparison operators: {“field”: {“$gt”: 5}} - Logical operators: {“$and”: […], “$or”: […]} - Nested combinations of the above Comparison operators:- $eq: equal to (string, int, float, bool) - $ne: not equal to (string, int, float, bool) - $gt: greater than (int, float) - $gte: greater than or equal to (int, float) - $lt: less than (int, float) - $lte: less than or equal to (int, float) - $in: a value is in list (string, int, float, bool) - $nin: a value is not in list (string, int, float, bool) - $contains: a string contains a value (string) - $not_contains: a string does not contain a value (string)

create()¶

classmethod create()

Create a new ChatPrompt. This submits the prompt text to the LLM. Either llm_blueprint or chat is required.

Parameters

Parameter	Type	Description
`text`	`str`	The prompt text.
`llm_blueprint`	`LLMBlueprint` or `str` or `None`, optional	The LLM blueprint associated with the created chat prompt, either LLMBlueprint or LLM blueprint ID.
`chat`	`Chat` or `str` or `None`, optional	The chat associated with the created chat prompt, either Chat or chat ID.
`llm`	`LLMDefinition`, `str`, or `None`, optional	The LLM to use for the chat prompt, either LLMDefinition or LLM blueprint ID.
`llm_settings`	`dict` or `None`	LLM settings to use for the chat prompt. The specific keys allowed and the constraints on the values are defined in the response from LLMDefinition.list but this typically has dict fields:- system_prompt - The system prompt that tells the LLM how to behave. - max_completion_length - The maximum number of tokens in the completion. - temperature - Controls the variability in the LLM response. - top_p - Whether the model considers next tokens with top_p probability mass. Or - system_prompt - The system prompt that tells the LLM how to behave. - validation_id - The ID of the custom model LLM validation for custom model LLM blueprints.
`vector_database`	`VectorDatabase`, `str`, or `None`, optional	The vector database to use with this chat prompt submission, either VectorDatabase or vector database ID.
`vector_database_settings`	`VectorDatabaseSettings` or `None`, optional	Settings for the vector database, if any.
`wait_for_completion`	`bool`	If set to True, chat prompt result response limit is up to 10 minutes, raising a timeout error after that. Otherwise, check current status by using ChatPrompt.get with returned ID.
`metadata_filter`	`Optional[Dict[str`, `Any] \\| None]`	The metadata filter to apply to the vector database. Supports:- None or empty dict (no filters): Considers all documents - Multiple field filters (implicit AND): {“a”: 1, “b”: “b”} - Comparison operators: {“field”: {“$gt”: 5}} - Logical operators: {“$and”: […], “$or”: […]} - Nested combinations of the above Comparison operators:- $eq: equal to (string, int, float, bool) - $ne: not equal to (string, int, float, bool) - $gt: greater than (int, float) - $gte: greater than or equal to (int, float) - $lt: less than (int, float) - $lte: less than or equal to (int, float) - $in: a value is in list (string, int, float, bool) - $nin: a value is not in list (string, int, float, bool) - $contains: a string contains a value (string) - $not_contains: a string does not contain a value (string)

Returns

Returns	Description
chat_prompt	The created chat prompt.

Return type: ChatPrompt

update()¶

method update()

Update the chat prompt.

Parameters

Parameter	Type	Description
`custom_metrics`	`Optional[list[MetricMetadata]]`, optional	The new custom metrics to add to the chat prompt.
`feedback_metadata`	`Optional[FeedbackMetadata]`, optional	The new feedback to add to the chat prompt.

Returns

Returns	Description
chat_prompt	The updated chat prompt.

Return type: ChatPrompt

get()¶

classmethod get()

Retrieve a single chat prompt.

Parameters

Parameter	Type	Description
`chat_prompt`	`ChatPrompt` or `str`	The chat prompt you want to retrieve, either ChatPrompt or chat prompt ID.

Returns

Returns	Description
chat_prompt	The requested chat prompt.

Return type: ChatPrompt

list()¶

classmethod list()

List all chat prompts available to the user. If the llm_blueprint, playground, or chat is specified then the results are restricted to the chat prompts associated with that entity.

Parameters

Parameter	Type	Description
`llm_blueprint`	`Optional[Union[LLMBlueprint`, `str]]`, optional	The returned chat prompts are filtered to those associated with a specific LLM blueprint if it is specified. Accepts either LLMBlueprint or LLM blueprint ID.
`playground`	`Optional[Union[Playground`, `str]]`, optional	The returned chat prompts are filtered to those associated with a specific playground if it is specified. Accepts either Playground or playground ID.
`chat`	`Optional[Union[Chat`, `str]]`, optional	The returned chat prompts are filtered to those associated with a specific chat if it is specified. Accepts either Chat or chat ID.

Returns

Returns	Description
chat_prompts	A list of chat prompts available to the user.

Return type: list[ChatPrompt]

delete()¶

method delete()

Delete the single chat prompt.

Return type: None

create_llm_blueprint()¶

method create_llm_blueprint()

Create a new LLM blueprint from an existing chat prompt.

Parameters

Parameter	Type	Description
`name`	`str`	LLM blueprint name.
`description`	`Optional[str]`	Description of the LLM blueprint, by default “”.

Returns

Returns	Description
llm_blueprint	The created LLM blueprint.

Return type: LLMBlueprint

ComparisonChat¶

class datarobot.models.genai.comparison_chat.ComparisonChat

Metadata for a DataRobot GenAI comparison chat.

Variables

Attribute	Type	Description
`id`	`str`	The comparison chat ID.
`name`	`str`	The comparison chat name.
`playground_id`	`str`	The ID of the playground associated with the comparison chat.
`creation_date`	`str`	The date when the comparison chat was created.
`creation_user_id`	`str`	The ID of the creating user.

create()¶

classmethod create()

Creates a new comparison chat.

Parameters

Parameter	Type	Description
`name`	`str`	The comparison chat name.
`playground`	`Playground` or `str`	The playground associated with the created comparison chat, either Playground or playground ID.

Returns

Returns	Description
comparison_chat	The created comparison chat.

Return type: ComparisonChat

get()¶

classmethod get()

Retrieve a single comparison chat.

Parameters

Parameter	Type	Description
`comparison_chat`	`ComparisonChat` or `str`	The comparison chat you want to retrieve. Accepts ComparisonChat or comparison chat ID.

Returns

Returns	Description
comparison_chat	The requested comparison chat.

Return type: ComparisonChat

list()¶

classmethod list()

List all comparison chats available to the user. If the playground is specified, results are restricted to only those comparison chats associated with the playground.

Parameters

Parameter	Type	Description
`playground`	`Optional[Union[Playground`, `str]]`, optional	Returns only those comparison chats associated with a particular playground, specified by either the Playground or the playground ID.
`sort`	`Optional[str]`	The property to sort comparison chats by. Prefix the attribute name with a dash ( - ) to sort responses in descending order, (for example, ‘-name’). Supported options are listed in ListComparisonChatsSortQueryParams, but the values can differ depending on platform version. The default sort parameter is None, which results in comparison chats returning in order of creation time, descending.

Returns

Returns	Description
comparison_chats	Returns a list of comparison chats.

Return type: list[ComparisonChat]

delete()¶

method delete()

Delete the single comparison chat.

Return type: None

update()¶

method update()

Update the comparison chat.

Parameters

Parameter	Type	Description
`name`	`str`	The new name for the comparison chat.

Returns

Returns	Description
comparison_chat	The updated comparison chat.

Return type: ComparisonChat

ComparisonPrompt¶

class datarobot.models.genai.comparison_prompt.ComparisonPrompt

Metadata for a DataRobot GenAI comparison prompt.

Variables

Attribute	Type	Description
`id`	`str`	Comparison prompt ID.
`text`	`str`	The prompt text.
`results`	`list[ComparisonPromptResult]`	The list of results for individual LLM blueprints that are part of the comparison prompt.
`creation_date`	`str`	The date when the playground was created.
`creation_user_id`	`str`	ID of the creating user.
`comparison_chat_id`	`str`	The ID of the comparison chat this comparison prompt is associated with.
`metadata_filter`	`Optional[Dict[str`, `Any] \\| None]`	The metadata filter to apply to the vector database. Supports:- None or empty dict (no filters): Considers all documents - Multiple field filters (implicit AND): {“a”: 1, “b”: “b”} - Comparison operators: {“field”: {“$gt”: 5}} - Logical operators: {“$and”: […], “$or”: […]} - Nested combinations of the above Comparison operators:- $eq: equal to (string, int, float, bool) - $ne: not equal to (string, int, float, bool) - $gt: greater than (int, float) - $gte: greater than or equal to (int, float) - $lt: less than (int, float) - $lte: less than or equal to (int, float) - $in: a value is in list (string, int, float, bool) - $nin: a value is not in list (string, int, float, bool) - $contains: a string contains a value (string) - $not_contains: a string does not contain a value (string)

update()¶

method update()

Update the comparison prompt.

Parameters

Parameter	Type	Description
`additional_llm_blueprints`	`list[LLMBlueprint` or `str]`	The additional LLM blueprints you want to submit the comparison prompt.

Returns

Returns	Description
comparison_prompt	The updated comparison prompt.

Return type: ComparisonPrompt

create()¶

classmethod create()

Create a new ComparisonPrompt. This submits the prompt text to the LLM blueprints that are specified.

Parameters

Parameter	Type	Description
`llm_blueprints`	`list[LLMBlueprint` or `str]`	The LLM blueprints associated with the created comparison prompt. Accepts LLM blueprints or IDs.
`text`	`str`	The prompt text.
`comparison_chat`	`Optional[ComparisonChat` or `str]`, optional	The comparison chat to add the comparison prompt to. Accepts ComparisonChat or comparison chat ID.
`wait_for_completion`	`bool`	If set to True code will wait for the chat prompt job to complete before returning the result (up to 10 minutes, raising timeout error after that). Otherwise, you can check current status by using ChatPrompt.get with returned ID.
`metadata_filter`	`Optional[Dict[str`, `Any] \\| None]`	The metadata filter to apply to the vector database. Supports:- None or empty dict (no filters): Considers all documents - Multiple field filters (implicit AND): {“a”: 1, “b”: “b”} - Comparison operators: {“field”: {“$gt”: 5}} - Logical operators: {“$and”: […], “$or”: […]} - Nested combinations of the above Comparison operators:- $eq: equal to (string, int, float, bool) - $ne: not equal to (string, int, float, bool) - $gt: greater than (int, float) - $gte: greater than or equal to (int, float) - $lt: less than (int, float) - $lte: less than or equal to (int, float) - $in: a value is in list (string, int, float, bool) - $nin: a value is not in list (string, int, float, bool) - $contains: a string contains a value (string) - $not_contains: a string does not contain a value (string)

Returns

Returns	Description
comparison_prompt	The created comparison prompt.

Return type: ComparisonPrompt

get()¶

classmethod get()

Retrieve a single comparison prompt.

Parameters

Parameter	Type	Description
`comparison_prompt`	`str`	The comparison prompt you want to retrieve. Accepts entity or ID.

Returns

Returns	Description
comparison_prompt	The requested comparison prompt.

Return type: ComparisonPrompt

list()¶

classmethod list()

List all comparison prompts available to the user that include the specified LLM blueprints or from the specified comparison chat.

Parameters

Parameter	Type	Description
`llm_blueprints`	`Optional[List[Union[LLMBlueprint`, `str]]]`, optional	The returned comparison prompts are only those associated with the specified LLM blueprints. Accepts either LLMBlueprint or LLM blueprint ID.
`comparison_chat`	`Optional[Union[ComparisonChat`, `str]]`, optional	The returned comparison prompts are only those associated with the specified comparison chat. Accepts either ComparisonChat or comparison chat ID.

Returns

Returns	Description
comparison_prompts	A list of comparison prompts available to the user that use the specified LLM blueprints.

Return type: list[ComparisonPrompt]

delete()¶

method delete()

Delete the single comparison prompt.

Return type: None

Playground¶

class datarobot.models.genai.playground.Playground

Metadata for a DataRobot GenAI playground.

Variables

Attribute	Type	Description
`id`	`str`	Playground ID.
`name`	`str`	Playground name.
`description`	`str`	Description of the playground.
`use_case_id`	`str`	Linked use case ID.
`creation_date`	`str`	The date when the playground was created.
`creation_user_id`	`str`	ID of the creating user.
`last_update_date`	`str`	Date when the playground was most recently updated.
`last_update_user_id`	`str`	ID of the user who most recently updated the playground.
`saved_llm_blueprints_count`	`int`	Number of saved LLM blueprints in the playground.
`llm_blueprints_count`	`int`	Number of LLM blueprints in the playground.
`user_name`	`str`	The name of the user who created the playground.
`playground_type`		(`Optional[PlaygroundType]`)

create()¶

classmethod create()

Create a new playground.

Parameters

Parameter	Type	Description
`name`	`str`	Playground name.
`description`	`Optional[str]`	Description of the playground, by default “”.
`use_case`	`Optional[Union[UseCase`, `str]]`, optional	Use case to link to the created playground.
`copy_insights`	`CopyInsightsRequest`, optional	If present, copies insights from the source playground to the created playground.

Returns

Returns	Description
playground	The created playground.

Return type: Playground

get()¶

classmethod get()

Retrieve a single playground.

Parameters

Parameter	Type	Description
`playground_id`	`str`	The ID of the playground you want to retrieve.

Returns

Returns	Description
playground	The requested playground.

Return type: Playground

list()¶

classmethod list()

List all playgrounds available to the user. If the use_case is specified or can be inferred from the Context then the results are restricted to the playgrounds associated with the UseCase.

Parameters

Parameter	Type	Description
`use_case`	`Optional[UseCaseLike]`, optional	The returned playgrounds are filtered to those associated with a specific Use Case or Cases if specified or can be inferred from the Context. Accepts either the entity or the ID.
`search`	`Optional[str]`	String for filtering playgrounds. Playgrounds that contain the string in name will be returned. If not specified, all playgrounds will be returned.
`sort`	`Optional[str]`	Property to sort playgrounds by. Prefix the attribute name with a dash to sort in descending order, e.g., sort=’-creationDate’. Currently supported options are listed in ListPlaygroundsSortQueryParams but the values can differ with different platform versions. By default, the sort parameter is None which will result in playgrounds being returned in order of creation time descending.

Returns

Returns	Description
playgrounds	A list of playgrounds available to the user.

Return type: list[Playground]

update()¶

method update()

Update the playground.

Parameters

Parameter	Type	Description
`name`	`str`	The new name for the playground.
`description`	`str`	The new description for the playground.

Returns

Returns	Description
playground	The updated playground.

Return type: Playground

delete()¶

method delete()

Delete the playground.

Return type: None

PromptType¶

class datarobot.enums.PromptType

Supported LLM blueprint prompting types.

UserLimits¶

class datarobot.models.genai.user_limits.UserLimits

Counts for user limits for LLM APIs and vector databases.

get_vector_database_count()¶

classmethod get_vector_database_count()

Get the count of vector databases for the user.

Return type: APIObject

get_llm_requests_count()¶

classmethod get_llm_requests_count()

Get the count of LLMs requests made by the user.

Return type: APIObject

ResultMetadata¶

class datarobot.models.genai.chat_prompt.ResultMetadata

Metadata for the result of a chat prompt submission.

Variables

Attribute	Type	Description
`output_token_count`	`int`	The number of tokens in the output.
`input_token_count`	`int`	The number of tokens in the input. This includes the chat history and documents retrieved from a vector database, if any.
`total_token_count`	`int`	The total number of tokens processed.
`estimated_docs_token_count`	`int`	The estimated number of tokens from the documents retrieved from a vector database, if any.
`latency_milliseconds`	`int`	The latency of the chat prompt submission in milliseconds.
`feedback_result`	`FeedbackResult`	The lists of user_ids providing positive and negative feedback.
`metrics`	`MetricMetadata`	The evaluation metrics for this prompt.
`final_prompt`	`Optional[Union[str`, `dict]]`, optional	Representation of the final prompt sent to the LLM.
`error_message`	`str` or `None`, optional	The error message from the LLM response.
`cost`	`float` or `None`, optional	The cost of the chat prompt submission.

PromptTrace¶

class datarobot.models.genai.prompt_trace.PromptTrace

Prompt trace contains aggregated information about a prompt execution.

Variables

Attribute	Type	Description
`timestamp`	`str`	The timestamp of the trace (ISO 8601 formatted).
`user`	`dict`	The user who submitted the prompt.
`chat_prompt_id`	`str`	The ID of the chat prompt associated with the trace.
`use_case_id`	`str`	The ID of the Use Case the playground is in.
`comparison_prompt_id`	`str`	The ID of the comparison prompts associated with the trace.
`llm_blueprint_id`	`str`	The ID of the LLM blueprint that the prompt was submitted to.
`llm_blueprint_name`	`str`	The name of the LLM blueprint.
`llm_name`	`str`	The name of the LLM in the LLM blueprint.
`llm_vendor`	`str`	The vendor name of the LLM.
`llm_license`	`str`	What type of license the LLM has.
`llm_settings`	`dict` or `None`	The LLM settings for the LLM blueprint. The specific keys allowed and the constraints on the values are defined in the response from LLMDefinition.list, but this typically has dict fields. Either:- system_prompt - The system prompt that influences the LLM responses. - max_completion_length - The maximum number of tokens in the completion. - temperature - Controls the variability in the LLM response. - top_p - Sets whether the model considers next tokens with top_p probability mass. or - system_prompt - The system prompt that influences the LLM responses. - validation_id - The ID of the external model LLM validation. - external_llm_context_size - The external LLM’s context size, in tokens, for external model-based LLM blueprints.
`chat_name`	`str` or `None`	The name of the chat associated with the Trace.
`chat_id`	`str` or `None`	The ID of the chat associated with the Trace.
`vector_database_id`	`str` or `None`	ID of the vector database associated with the LLM blueprint, if any.
`vector_database_settings`	`VectorDatabaseSettings` or `None`	The settings for the vector database associated with the LLM blueprint, if any.
`result_metadata`	`ResultMetadata` or `None`	Metadata for the result of the prompt submission.
`result_text`	`str` or `None`	The result text from the prompt submission.
`confidence_scores`	`ConfidenceScores` or `None`	The confidence scores if there is a vector database associated with the prompt.
`text`	`str`	The prompt text submitted to the LLM.
`execution_status`	`str`	The execution status of the chat prompt.
`prompt_type`	`str` or `None`	The type of prompting strategy, for example history aware.
`evaluation_dataset_configuration_id`	`str` or `None`	The ID of the evaluation dataset configuration associated with the trace.
`warning`	`str` or `None`	Any warnings associated with the trace.

list()¶

classmethod list()

List all prompt traces for a playground.

Parameters

Parameter	Type	Description
`playground`	`str`	The ID of the playground to list prompt traces for.

Returns

Returns	Description
prompt_traces	List of prompt traces for the playground.

Return type: list[PromptTrace]

export_to_ai_catalog()¶

classmethod export_to_ai_catalog()

Export prompt traces to AI Catalog as a CSV.

Parameters

Parameter	Type	Description
`playground`	`str`	The ID of the playground to export prompt traces for.

Returns

Returns	Description
status_url	The URL where the status of the job can be monitored

Return type: str

TraceMetadata¶

class datarobot.models.genai.prompt_trace.TraceMetadata

Trace metadata contains information about all the users and chats that are relevant to this playground.

Variables

Attribute	Type	Description
`users`	`list[dict]`	The users who submitted the prompt.

get()¶

classmethod get()

Get trace metadata for a playground.

Parameters

Parameter	Type	Description
`playground`	`str`	The ID of the playground to get trace metadata for.

Returns

Returns	Description
trace_metadata	The trace metadata for the playground.

Return type: TraceMetadata

PromptTemplate¶

class datarobot.models.genai.prompt_template.PromptTemplate

A prompt template that can have multiple versions.

Variables

Attribute	Type	Description
`id`	`str`	Prompt template ID.
`name`	`str`	Prompt template name.
`description`	`str`	Description of the prompt template.
`creation_date`	`str`	ISO-8601 formatted timestamp of when the template was created.
`creation_user_id`	`str`	ID of the user who created the template.
`last_update_date`	`str`	ISO-8601 formatted timestamp of when the template was last updated.
`last_update_user_id`	`str`	ID of the user who last updated the template.
`user_name`	`str`	Name of the user who created the template.
`version_count`	`int`	Number of versions this template has.

create()¶

classmethod create()

Create a new prompt template.

Parameters

Parameter	Type	Description
`name`	`str`	Name of the prompt template.
`description`	`str`, optional	Description of the prompt template.

Returns

Returns	Description
The created prompt template.

Return type: PromptTemplate

Raises

Exception	Description
datarobot.errors.ClientError	If the server responded with 4xx status.
datarobot.errors.ServerError	If the server responded with 5xx status.

Examples

>>> import datarobot as dr
>>> template = dr.genai.PromptTemplate.create(
...     name="Customer Support",
...     description="Template for support responses"
... )

list()¶

classmethod list()

List all prompt templates available to the user.

Parameters

Parameter	Type	Description
`sort`	`str`, optional	Prefix the attribute name with a dash to sort in descending order, e.g., sort=’-creationDate’.
`search`	`str`, optional	Filter templates by name containing this string.

Returns

Returns	Description
A list of prompt templates.

Return type: List[PromptTemplate]

Raises

Exception	Description
datarobot.errors.ClientError	If the server responded with 4xx status.
datarobot.errors.ServerError	If the server responded with 5xx status.

Examples

>>> import datarobot as dr
>>> templates = dr.genai.PromptTemplate.list(sort="-creationDate")

get()¶

classmethod get()

Get a prompt template by ID.

Parameters

Parameter	Type	Description
`prompt_template_id`	`str`	The ID of the prompt template to retrieve.

Returns

Returns	Description
The requested prompt template.

Return type: PromptTemplate

Raises

Exception	Description
datarobot.errors.ClientError	If the server responded with 4xx status.
datarobot.errors.ServerError	If the server responded with 5xx status.

Examples

>>> import datarobot as dr
>>> template = dr.genai.PromptTemplate.get("507f1f77bcf86cd799439011")

create_version()¶

method create_version()

Create a new version of this prompt template.

Parameters

Parameter	Type	Description
`prompt_text`	`str`	The prompt text with variables in {{ variable }} format.
`variables`	`List[Variable]`, optional	List of Variable objects defining the variables used in the prompt template. Defaults to None, which sends an empty list to the API.
`commit_comment`	`str`, optional	Comment describing this version.

Returns

Returns	Description
The created version.

Return type: PromptTemplateVersion

Raises

Exception	Description
datarobot.errors.ClientError	If the server responded with 4xx status.
datarobot.errors.ServerError	If the server responded with 5xx status.

Examples

>>> from datarobot.models.genai.prompt_template import Variable
>>> template.create_version(
...     prompt_text="Hello {{ name }}, regarding {{ issue }}",
...     variables=[
...         Variable(name="name", type="str", description="Customer name"),
...         Variable(name="issue", type="str", description="Issue type")
...     ],
...     commit_comment="Initial version"
... )

list_versions()¶

method list_versions()

List all versions of this prompt template.

Returns

Returns	Description
A list of versions for this template.

Return type: List[PromptTemplateVersion]

Raises

Exception	Description
datarobot.errors.ClientError	If the server responded with 4xx status.
datarobot.errors.ServerError	If the server responded with 5xx status.

Examples

>>> versions = template.list_versions()

get_version()¶

method get_version()

Get a specific version of this prompt template.

Parameters

Parameter	Type	Description
`prompt_template_version_id`	`str`	The ID of the version to retrieve.

Returns

Returns	Description
The requested version.

Return type: PromptTemplateVersion

Raises

Exception	Description
datarobot.errors.ClientError	If the server responded with 4xx status.
datarobot.errors.ServerError	If the server responded with 5xx status.

Examples

>>> import datarobot as dr
>>> template = dr.genai.PromptTemplate.get("507f1f77bcf86cd799439011")
>>> version = template.get_version("507f1f77bcf86cd799439012")

get_latest_version()¶

method get_latest_version()

Get the latest version of this prompt template.

Returns

Returns	Description
The latest version, or None if no versions exist.

Return type: Optional[PromptTemplateVersion]

Raises

Exception	Description
datarobot.errors.ClientError	If the server responded with 4xx status.
datarobot.errors.ServerError	If the server responded with 5xx status.

Examples

>>> import datarobot as dr
>>> template = dr.genai.PromptTemplate.get("507f1f77bcf86cd799439011")
>>> latest = template.get_latest_version()
>>> if latest:
...     print(f"Version {latest.version}")

PromptTemplateVersion¶

class datarobot.models.genai.prompt_template.PromptTemplateVersion

A specific version of a prompt template.

Variables

Attribute	Type	Description
`id`	`str`	Version ID.
`prompt_template_id`	`str`	ID of the parent prompt template.
`prompt_text`	`str`	The prompt text with variables in {{ variable }} format.
`commit_comment`	`str`	Comment describing this version.
`version`	`int`	Version number.
`variables`	`List[Variable]`	List of variables used in the prompt.
`creation_date`	`str`	ISO-8601 formatted timestamp of when the version was created.
`creation_user_id`	`str`	ID of the user who created the version.
`user_name`	`str`	Name of the user who created the version.

get()¶

classmethod get()

Get a specific prompt template version by ID.

Parameters

Parameter	Type	Description
`prompt_template_id`	`str`	The ID of the prompt template.
`prompt_template_version_id`	`str`	The ID of the version to retrieve.

Returns

Returns	Description
The requested prompt template version.

Return type: PromptTemplateVersion

Raises

Exception	Description
datarobot.errors.ClientError	If the server responded with 4xx status.
datarobot.errors.ServerError	If the server responded with 5xx status.

Examples

>>> import datarobot as dr
>>> version = dr.genai.PromptTemplateVersion.get("prompt_template_id", "prompt_template_version_id")

create()¶

classmethod create()

Create a new version of a prompt template.

Parameters

Parameter	Type	Description
`prompt_template_id`	`str`	The ID of the prompt template.
`prompt_text`	`str`	The prompt text with variables in {{ variable }} format.
`variables`	`List[Variable]`, optional	List of Variable objects defining the variables used in the prompt template.
`commit_comment`	`str`, optional	Comment describing this version.

Returns

Returns	Description
The created version.

Return type: PromptTemplateVersion

Raises

Exception	Description
datarobot.errors.ClientError	If the server responded with 4xx status.
datarobot.errors.ServerError	If the server responded with 5xx status.

Examples

>>> import datarobot as dr
>>> from datarobot.models.genai.prompt_template import Variable
>>> version = dr.genai.PromptTemplateVersion.create(
...     prompt_template_id="507f1f77bcf86cd799439011",
...     prompt_text="Hello {{ name }}, regarding {{ issue }}",
...     variables=[
...         Variable(name="name", type="str", description="Customer name"),
...         Variable(name="issue", type="str", description="Issue type")
...     ],
...     commit_comment="Initial version"
... )

list()¶

classmethod list()

List all versions of a prompt template.

Parameters

Parameter	Type	Description
`prompt_template_id`	`str`	The ID of the prompt template.

Returns

Returns	Description
A list of versions for the template.

Return type: List[PromptTemplateVersion]

Raises

Exception	Description
datarobot.errors.ClientError	If the server responded with 4xx status.
datarobot.errors.ServerError	If the server responded with 5xx status.

Examples

>>> import datarobot as dr
>>> versions = dr.genai.PromptTemplateVersion.list(
...     prompt_template_id="507f1f77bcf86cd799439011"
... )

list_all()¶

classmethod list_all()

List prompt template versions across multiple templates.

Parameters

Parameter	Type	Description
`prompt_template_ids`	`List[str]`, optional	Filter versions to only those belonging to these prompt template IDs. If not provided, returns versions for all accessible templates.

Returns

Returns	Description
A list of prompt template versions.

Return type: List[PromptTemplateVersion]

Raises

Exception	Description
datarobot.errors.ClientError	If the server responded with 4xx status.
datarobot.errors.ServerError	If the server responded with 5xx status.

Examples

>>> import datarobot as dr
>>> # List all versions across all templates
>>> versions = dr.genai.PromptTemplateVersion.list_all()
>>> # List versions for specific templates
>>> versions = dr.genai.PromptTemplateVersion.list_all(
...     prompt_template_ids=["template_id_1", "template_id_2"]
... )

render()¶

method render()

Render the prompt text by substituting variables.

Parameters

Parameter	Type	Description
`variables`	`Optional[Dict[str`, `Any]]`	Dictionary of variable names to values. * **kwargs (`Any`) – Variable values as keyword arguments. These override values in the variables dict.

Returns

Returns	Description
Rendered prompt text with variables substituted.

Return type: str

Raises

Exception	Description
ValueError	If required variables are missing.

Examples

>>> import datarobot as dr
>>> version = dr.genai.PromptTemplateVersion.get("template_id", "version_id")
>>> version.render(name="Alice", issue="billing")
'Hello Alice, regarding billing...'

to_fstring()¶

method to_fstring()

Convert the prompt text from {{ variable }} format to Python f-string {variable} format.

This method transforms template placeholders from double-brace format ({{ variable }}) to single-brace format ({variable}), making the template compatible with Python f-string syntax. Whitespace around variable names is automatically stripped.

Returns

Returns	Description
Prompt text with variables in f-string format.

Return type: str

Raises

Exception	Description
ValueError	If prompt_text is None.

Examples

>>> import datarobot as dr
>>> version = dr.genai.PromptTemplateVersion.get("template_id", "version_id")
>>> # Original: "Hello {{ name }}, regarding {{ issue }}"
>>> fstring_template = version.to_fstring()
>>> # Result: "Hello {name}, regarding {issue}"
>>> # Can now be used with f-string evaluation:
>>> name = "Alice"
>>> issue = "billing"
>>> result = eval(f'f"{fstring_template}"')

Variable¶

class datarobot.models.genai.prompt_template.Variable

A variable used in prompt templates.

Variables

Attribute	Type	Description
`name`	`str`	Variable name.
`type`	`str`	Variable type (e.g., “str”, “int”).
`description`	`str`	Description of the variable.