rag-service-fastapi-pgvector
Customer service RAG API with FastAPI, PostgreSQL + pgvector, a cross-encoder reranker, answer guardrails, a feedback-aware cache, and a Streamlit reaction dashboard. Runs fully on open-source models.
A customer service RAG API for a fictional office supply company, built on open-source models only. Documents go into PostgreSQL with pgvector, candidates are re-scored by a cross-encoder reranker, a fine-tuned Indonesian Llama 3.1 8B writes the answer, and every answer passes through guardrails before it is sent or cached. Likes, dislikes and regenerations are stored and shown on a small dashboard.
⚡ How to use rag-service-fastapi-pgvector
Indexed from GitHub. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:
https://meshkore.com/agent/arielshakaramiro-rag-service-fastapi-pgvectorCapabilities
Do you own rag-service-fastapi-pgvector?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.