RafalWilinski/cloudflare-rag

Fullstack "Chat with your PDFs" RAG (Retrieval Augmented Generation) app built fully on Cloudflare

38
/ 100
Emerging

Implements hybrid RAG combining full-text search (BM25 on D1) and vector search (Vectorize) with reciprocal rank fusion for result ranking. Uses Workers AI with multi-provider fallbacks (OpenAI, Groq, Anthropic) via AI Gateway, streams responses through Server-Sent Events, and performs OCR directly in Workers using unpdf. Rate limiting and document storage leverage Cloudflare's KV and R2 primitives respectively.

596 stars. No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 20 / 25

How are scores calculated?

Stars

596

Forks

89

Language

TypeScript

License

Last pushed

Sep 05, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/RafalWilinski/cloudflare-rag"

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