manbot/_board/TASKS/P4-03_RAG_SERVICE.md

Task: P4-03 Implement RAG Service

Description

Implement a Retrieval-Augmented Generation (RAG) service using the FAISS vector database to provide the system with long-term semantic memory and document access.

Requirements

• Create src/services/rag-service.ts.
• Use FAISS (via node bindings or a Python microservice with a bridge).
• Implement methods:
  • addDocument(content, metadata): Embeds and stores a document.
  • search(query, limit): Returns relevant snippets based on semantic similarity.
• Use a dedicated embedding model (e.g., text-embedding-v3) via the Lemonade Adapter.

Definition of Done

• RAG Service can index text and retrieve relevant matches for a given query.
• Search performance is consistent with the local system requirements.