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.
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.
Stars
106
Forks
12
Language
TypeScript
License
MIT
Category
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.
Higher-rated alternatives
tonykipkemboi/ollama_pdf_rag
A full-stack demo showcasing a local RAG (Retrieval Augmented Generation) pipeline to chat with...
IDinsight/ask-a-question
Trustworthy question-answering AI plugin for chatbots in the social sector with advanced content...
reasonmethis/docdocgo-core
Automate web research way beyond the first page of search results; curate knowledge bases to chat with.
HaileyTQuach/docchat-docling
DocChat is an AI-powered Multi-Agent RAG system using Docling for structured document parsing...
pathway-labs/dropbox-ai-chat
AI-powered Dropbox search tool for private documents