https://github.com/samshad/fastapi-ollama-rag
Production-grade Retrieval-Augmented Generation (RAG) backend. Engineered with FastAPI, Neon Serverless Postgres, and Ollama, privacy-first AI. Includes structlog observability and pure-Python semantic chunking.
https://github.com/samshad/fastapi-ollama-rag
async fastapi llm neon-postgres ollama pgvector postgresql python rag
Last synced: 3 months ago
JSON representation
Production-grade Retrieval-Augmented Generation (RAG) backend. Engineered with FastAPI, Neon Serverless Postgres, and Ollama, privacy-first AI. Includes structlog observability and pure-Python semantic chunking.
- Host: GitHub
- URL: https://github.com/samshad/fastapi-ollama-rag
- Owner: samshad
- License: mit
- Created: 2026-02-22T06:01:04.000Z (4 months ago)
- Default Branch: master
- Last Pushed: 2026-02-25T06:34:26.000Z (4 months ago)
- Last Synced: 2026-02-25T11:32:15.432Z (4 months ago)
- Topics: async, fastapi, llm, neon-postgres, ollama, pgvector, postgresql, python, rag
- Language: Python
- Homepage:
- Size: 173 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE