Package opengradient.alphasense

OpenGradient AlphaSense Tools

Functions

Create read workflow tool

def create_read_workflow_tool(tool_type: opengradient.alphasense.types.ToolType, workflow_contract_address: str, tool_name: str, tool_description: str, output_formatter: Callable[..., str] = <function <lambda>>) ‑> langchain_core.tools.base.BaseTool

Creates a tool that reads results from a workflow contract on OpenGradient.

This function generates a tool that can be integrated into either a LangChain pipeline or a Swarm system, allowing the workflow results to be retrieved and formatted as part of a chain of operations.

Returns

BaseTool: For ToolType.LANGCHAIN, returns a LangChain StructuredTool. Callable: For ToolType.SWARM, returns a decorated function with appropriate metadata.

Raises

• ValueError: If an invalid tool_type is provided.

Create run model tool

def create_run_model_tool(tool_type: opengradient.alphasense.types.ToolType, model_cid: str, tool_name: str, model_input_provider: Callable, model_output_formatter: Callable[[InferenceResult], str], tool_input_schema: Optional[Type[BaseModel]] = None, tool_description: str = 'Executes the given ML model', inference_mode: opengradient.types.InferenceMode = 0) ‑> langchain_core.tools.base.BaseTool

Creates a tool that wraps an OpenGradient model for inference.

This function generates a tool that can be integrated into either a LangChain pipeline or a Swarm system, allowing the model to be executed as part of a chain of operations. The tool uses the provided model_input_provider function to obtain both the necessary input data and any additional inputs from the Agent itself -- specified through the tool_input_schema -- and runs inference on the specified OpenGradient model.

The model_output_formatter then allows users to specify the format of their tools response after receiving the model inference result.

Returns

BaseTool: For ToolType.LANGCHAIN, returns a LangChain StructuredTool. Callable: For ToolType.SWARM, returns a decorated function with appropriate metadata.

Raises

• ValueError: If an invalid tool_type is provided.

Classes

ToolType

class ToolType(*args, **kwds)

Indicates the framework the tool is compatible with.

Variables

• static LANGCHAIN

• static SWARM