YASSERRMD/barq-web-rag

A fully browser-native RAG application for document Q&A, powered by Rust and WebAssembly with local vector search, embeddings, and in-browser LLM inference.

44
/ 100
Emerging

Leverages a modular Rust/WASM architecture with parallel worker meshes for document ingestion, HNSW+BM25 hybrid retrieval with RRF reranking, and WebGPU-accelerated inference for local LLM execution—all without external APIs. Supports batch processing of PDF, DOCX, Markdown, and TXT with persistent vector storage, integrating transformers.js for client-side model deployment. Requires modern browsers with WebGPU and WebAssembly threading support (Chrome/Edge 113+, Safari 17+).

No Package No Dependents
Maintenance 13 / 25
Adoption 6 / 25
Maturity 9 / 25
Community 16 / 25

How are scores calculated?

Stars

22

Forks

6

Language

TypeScript

License

Apache-2.0

Last pushed

Mar 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/YASSERRMD/barq-web-rag"

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