teamunitlab/rag-document-app

This FastAPI-based RAG service processes OCR data, generates embeddings using OpenAI, and utilizes Pinecone as a vector database for search. It answers questions based on search results using OpenAI.

23
/ 100
Experimental

Supports multi-format document ingestion (PDFs, images) with AWS S3 storage, implements rate limiting and Redis caching for performance, and includes API key authentication. The pipeline chains OCR extraction → tokenization → OpenAI embeddings → Pinecone vector storage → semantic search with LLM-generated answers, all deployable via Docker Compose.

No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 1 / 25
Community 16 / 25

How are scores calculated?

Stars

17

Forks

7

Language

Python

License

Last pushed

Jul 19, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/teamunitlab/rag-document-app"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.