メタデータを使用したLLMプロバイダーの設定¶

cd infra/infra
ln -sf ../configurations/llm/<chosen_configuration>.py 

# Your DataRobot API token.
# Refer to https://docs.datarobot.com/en/docs/api/dev-learning/api-quickstart.html#configure-your-environment for help.
DATAROBOT_API_TOKEN=

# The URL of your DataRobot instance API.
DATAROBOT_ENDPOINT=https://app.datarobot.com/api/v2

# The Pulumi stack name to use for this project.
PULUMI_STACK=dev

# If empty, a blank passphrase will be used
PULUMI_CONFIG_PASSPHRASE=123

# Set to 1 to skip Pulumi update check and prevent issues with rate limiting
PULUMI_SKIP_UPDATE_CHECK=0

# If empty, a new use case will be created
DATAROBOT_DEFAULT_USE_CASE=

# If empty, a new execution environment will be created for each agent using the docker_context folder
DATAROBOT_DEFAULT_EXECUTION_ENVIRONMENT="[DataRobot] Python 3.11 GenAI Agents"

# This is set to a specific version of `[DataRobot] Python 3.11 GenAI Agents` to preserve compatibility of the templates
DATAROBOT_DEFAULT_EXECUTION_ENVIRONMENT_VERSION_ID="6936d3af440bcb12397f4203"

# LLM Configuration:
# Agent templates support multiple flexible LLM options including:
# - LLM Gateway Direct (default)
# - LLM Blueprint with an External LLM
# - Already deployed LLM in DataRobot
#
# You can edit the LLM configuration by manually changing which configuration is
# active (recommended option).
# Simply run `ln -sf ../configurations/llm/<chosen_configuration>.py`
# from the `infra/infra` folder
#
# If you want to do it dynamically however, you can also set it as a configuration value with:
# INFRA_ENABLE_LLM=<chosen_configuration>
# from the list of options in the infra/configurations/llm folder
# Here are some examples of each of those configuration using the dynamic option described above:

# If you want to use the LLM gateway direct (default)
# INFRA_ENABLE_LLM=gateway_direct.py

# If you want to choose an existing LLM Deployment in DataRobot
# uncomment and configure these:
# LLM_DEPLOYMENT_ID=<your_deployment_id>
# INFRA_ENABLE_LLM=deployed_llm.py

# If you want to configure an LLM with an external LLM provider
# like Azure, Bedrock, Anthropic, or VertexAI (or all 4). Here we provide
# an Azure AI example, see:
# https://docs.datarobot.com/en/docs/gen-ai/playground-tools/deploy-llm.html
# for details on other providers and details:
# INFRA_ENABLE_LLM=blueprint_with_external_llm.py
# LLM_DEFAULT_MODEL="azure/gpt-4o"
# OPENAI_API_VERSION='2024-08-01-preview'
# OPENAI_API_BASE='https://<your_custom_endpoint>.openai.azure.com'
# OPENAI_API_DEPLOYMENT_ID='<your deployment_id>'
# OPENAI_API_KEY='<your_api_key>' 

from datarobot_genai.core.agents import make_system_prompt
from langchain.agents import create_agent

def graph_factory(llm, tools, verbose=False):
    planner = create_agent(
        llm,
        tools=tools,
        system_prompt=make_system_prompt(
            "You are a content planner. Plan engaging and factually accurate content on {topic}."
        ),
        name="planner_agent",
        debug=verbose,
    )
    writer = create_agent(
        llm,
        tools=tools,
        system_prompt=make_system_prompt(
            "You are a content writer. Write insightful and factually accurate opinion piece about the topic: {topic}."
        ),
        name="writer_agent",
        debug=verbose,
    )
    ... 

from datarobot_genai.core.agents import make_system_prompt
from langchain.agents import create_agent
from langchain_litellm.chat_models import ChatLiteLLM

def _llm_for_gateway_model(self, model: str) -> ChatLiteLLM:
    """Chat model for a specific LLM gateway catalog model."""
    api_base = self.litellm_api_base(self.config.llm_deployment_id)
    return ChatLiteLLM(
        model=model,
        api_base=api_base,
        api_key=self.api_key,
        timeout=self.timeout,
        streaming=True,
        max_retries=3,
    )

@property
def agent_planner(self) -> Any:
    return create_agent(
        self._llm_for_gateway_model("datarobot/azure/gpt-5-mini-2025-08-07"),
        tools=self.mcp_tools,
        system_prompt=make_system_prompt(
            "You are a content planner. Plan engaging and factually accurate content on {topic}."
        ),
        name="planner_agent",
    )

@property
def agent_writer(self) -> Any:
    return create_agent(
        self._llm_for_gateway_model("datarobot/azure/gpt-4o-2024-11-20"),
        tools=self.mcp_tools,
        system_prompt=make_system_prompt(
            "You are a content writer. Write insightful and factually accurate opinion piece about the topic: {topic}."
        ),
        name="writer_agent",
    ) 

default_model: str = "datarobot/azure/gpt-5-mini-2025-08-07"  # Used when nodes call self.llm() and for fallbacks 

LLM_DEPLOYMENT_ID=<your_deployment_id>
INFRA_ENABLE_LLM=deployed_llm.py 

INFRA_ENABLE_LLM=gateway_direct.py 

runtimeParameterDefinitions:
  - fieldName: COHERE_API_KEY
    type: credential
  - fieldName: COHERE_MODEL
    type: string
    defaultValue: "command-r-plus" 

from pydantic import Field
class Config(BaseConfig):
    # ... existing fields ...
    cohere_api_key: str
    cohere_model: str = "command-r-plus" 

from langchain_openai import ChatOpenAI
def llm(
    self,
    preferred_model: str | None = None,
    auto_model_override: bool = True,
) -> ChatOpenAI:
    """Returns a ChatOpenAI instance configured to use Cohere via LiteLLM.
    Args:
        preferred_model: The model to use. If None, uses COHERE_MODEL from config.
        auto_model_override: Ignored for direct LiteLLM integration.
    """
    return ChatOpenAI(
        model=self.config.cohere_model,  # Override the model with the configured one
        api_key=self.config.cohere_api_key,
        base_url="https://api.cohere.ai/v1",  # Cohere's OpenAI-compatible endpoint
        timeout=self.timeout,
    ) 

...existing code
# Create the Cohere credential
cohere_credential = datarobot.ApiTokenCredential(
    resource_name=f"{pulumi.get_project()} Cohere API Key Credential",
    api_token=os.environ.get("COHERE_API_KEY"),
)
# Update the runtime parameters arrays
app_runtime_parameters = [
    datarobot.ApplicationSourceRuntimeParameterValueArgs(
        key="COHERE_API_KEY",
        type="credential",
        value=cohere_credential.id,
    ),
    datarobot.ApplicationSourceRuntimeParameterValueArgs(
        key="COHERE_MODEL",
        type="string",
        value=os.environ.get("COHERE_MODEL", "command-r-plus"),
    ),
]
custom_model_runtime_parameters = [
    datarobot.CustomModelRuntimeParameterValueArgs(
        key="COHERE_API_KEY",
        type="credential",
        value=cohere_credential.id,
    ),
    datarobot.CustomModelRuntimeParameterValueArgs(
        key="COHERE_MODEL",
        type="string",
        value=os.environ.get("COHERE_MODEL", "command-r-plus"),
    ),
] 

INFRA_ENABLE_LLM=gateway_direct.py
COHERE_API_KEY='<your_api_key>'
COHERE_MODEL='command-r-plus' 

task infra:deploy