nico-martin/ask-my-pdf

A Webapp that uses Retrieval Augmented Generation (RAG) and Large Language Models to interact with a PDF directly in the browser.

39
/ 100
Emerging

Executes the entire RAG pipeline in-browser using PDF.js for extraction, TransformersJS with all-MiniLM-L6-v2 for semantic vector embedding, and an in-memory VectorDB for cosine similarity retrieval. Generates responses via Gemma 2B/9B models compiled to WebAssembly/WebGPU with MLC LLM, with optional fallback to Google's experimental Prompt API for supported browsers.

106 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

106

Forks

12

Language

TypeScript

License

MIT

Last pushed

Nov 24, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/nico-martin/ask-my-pdf"

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