match_concepts
Match project descriptions to knowledge graph concepts using embedding similarity to identify relevant architectural patterns and generate consultation sessions.
Instructions
ENTRY POINT — Deterministically match a project description to knowledge graph concepts via embedding similarity. Returns ranked concepts with scores and creates a consultation_id that tracks the session. The same description always produces the same concept ranking and fingerprint. Pass the returned consultation_id to get_subgraph and ask_book for step logging.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| project_description | Yes | Free-text description of the user's project, architecture, and pain points | |
| max_results | No | Maximum concepts to return (1-50, default: 15) | |
| similarity_threshold | No | Minimum cosine similarity to include (0.0-1.0, default: 0.3) |