Skip to main content
Glama

generate_fragment_synthesis

Create synthesized documents from fragmented data sources to build traceable, weighted documentary corpora for improved data quality before RAG implementation.

Instructions

Create a synthesis from salvaged fragments.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kwargsYes

Implementation Reference

  • The handler function for the 'generate_fragment_synthesis' tool, which orchestrates the creation of a synthesis.
    def _generate_fragment_synthesis(orchestrator: Orchestrator, _db: Session, _settings: AppSettings, arguments: dict[str, Any]) -> Any:
        synthesis = orchestrator.create_synthesis(arguments["query_id"], arguments.get("fragment_ids"))
        return {"synthesis_id": synthesis.id, "overall_confidence": synthesis.overall_confidence}
  • Registration of the 'generate_fragment_synthesis' tool in the MCP registry, including input schema definition and handler mapping.
    ToolDefinition(
        name="generate_fragment_synthesis",
        title="Generate Fragment Synthesis",
        description="Create a synthesis from salvaged fragments.",
        version="1.0.0",
        input_schema={
            "type": "object",
            "properties": {
                "query_id": {"type": "string"},
                "fragment_ids": {"type": "array", "items": {"type": "string"}},
            },
            "required": ["query_id"],
        },
        output_schema={"type": "object"},
        security=common_security,
        handler=_generate_fragment_synthesis,
    ),

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/fbailleux2/kfabric'

If you have feedback or need assistance with the MCP directory API, please join our Discord server