Spaces:
Running
Running
|
Download README.md from DataDrivenAlex/rag-document-qa: direct link, hf CLI and curl.
- Browser
- Download file 1.05 kB
-
https://huggingface.co/spaces/DataDrivenAlex/rag-document-qa/resolve/main/README.md
- Command line
-
hf download hf://spaces/DataDrivenAlex/rag-document-qa/README.md
-
curl -L -o README.md https://huggingface.co/spaces/DataDrivenAlex/rag-document-qa/resolve/main/README.md
1.05 kB
metadata
title: RAG Document Q&A
emoji: π
colorFrom: blue
colorTo: indigo
sdk: static
pinned: true
license: mit
short_description: 'In-browser RAG: ask questions about your own PDFs'
tags:
- rag
- retrieval
- question-answering
- transformers.js
- semantic-search
π RAG Document Q&A
Retrieval-Augmented Generation pipeline that runs entirely in the browser: document loading (PDF via pdf.js, TXT, pasted text), chunking with overlap, sentence embeddings (Xenova/all-MiniLM-L6-v2), cosine-similarity vector search and extractive answering (Xenova/distilbert-base-cased-distilled-squad). Retrieved passages are shown with similarity scores so every answer is traceable. Documents never leave the user's device.
Runs fully client-side with Transformers.js (ONNX Runtime Web) β no server, no API keys.
Author: Alexandru Cojocari Β· GitHub β Junior AI Developer (Generative AI, RAG, Agentic AI, Secure AI)