dataflow.api.base

Attributes

AI_MODELS
app

Classes

LLMConfigRequest	Request model for LLM configuration.
LLMGenerationResponse	Response model for LLM generation.
ToolConfig	Configuration for a tool to be used with the LLM.

Functions

generate_response(request[, query])	Generate a response using dynamically configured LLM.
get_env_api_key(provider)	Retrieve API key from environment variables based on provider.
root()	Root.

Module Contents

class dataflow.api.base.LLMConfigRequest(/, **data: Any)

Bases: pydantic.BaseModel

Request model for LLM configuration.

Parameters:

data (Any)

api_key: str | None = None

extra_params: dict[str, Any] | None = None

model: str = None

model_config

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

provider: haive.dataflow.api.models.llm.provider_types.LLMProvider = None

system_prompt: str | None = None

temperature: float | None = None

tools: list[ToolConfig] | None = None

class dataflow.api.base.LLMGenerationResponse(/, **data: Any)

Bases: pydantic.BaseModel

Response model for LLM generation.

Parameters:

data (Any)

model: str = None

model_config

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

provider: haive.dataflow.api.models.llm.provider_types.LLMProvider = None

response: str = None

class dataflow.api.base.ToolConfig(/, **data: Any)

Bases: pydantic.BaseModel

Configuration for a tool to be used with the LLM.

Parameters:

data (Any)

description: str | None = None

model_config

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

name: str = None

result: str | None = None

async dataflow.api.base.generate_response(request: LLMConfigRequest, query: str = Query(..., description='The input query or message to generate a response for'))

Generate a response using dynamically configured LLM.

Parameters:

• request (LLMConfigRequest) – LLM configuration details

• query (str) – User’s input query

dataflow.api.base.get_env_api_key(provider: haive.dataflow.api.models.llm.provider_types.LLMProvider) → str | None

Retrieve API key from environment variables based on provider.

Parameters:

provider (haive.dataflow.api.models.llm.provider_types.LLMProvider)

Return type:

str | None

async dataflow.api.base.root()

Root.

dataflow.api.base.AI_MODELS

dataflow.api.base.app