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.
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+).
Stars
22
Forks
6
Language
TypeScript
License
Apache-2.0
Category
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.
Higher-rated alternatives
ConardLi/easy-dataset
A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval
ItzCrazyKns/Vane
Vane is an AI-powered answering engine.
DS4SD/deepsearch-toolkit
Interact with the Deep Search platform for new knowledge explorations and discoveries
xuwei95/ezdata
基于python和llm大模型开发的数据处理和任务调度系统。...
ModelEngine-Group/DataMate
DataMate is an enterprise-level data processing platform designed for model fine-tuning and RAG...