cursus.pipeline_catalog.core.agent_tool

Agent Tool Interface for Pipeline Catalog

Exposes pipeline catalog as tool calls for LLM agents. Compatible with MCP, OpenAI function calling, and Claude tool_use.

Usage:

# Agent receives tool schema, calls with parameters: result = pipeline_catalog_tool(action=”recommend”, data_type=”text”, needs_llm=True) result = pipeline_catalog_tool(action=”get_dag”, dag_id=”bedrock_pytorch_incremental_edx”) result = pipeline_catalog_tool(action=”get_config_guidance”, dag_id=”…”)

pipeline_catalog_tool(action, dag_id=None, data_type=None, has_labels=True, needs_llm=False, multi_task=False, incremental=False, framework=None, gpu_available=True)

Execute a pipeline catalog tool action. Returns structured response for the agent.