# jacoblee93/fully-local-pdf-chatbot

Yes, it's another chat over documents implementation... but this one is entirely local!

Repository: https://github.com/jacoblee93/fully-local-pdf-chatbot
Canonical: https://ross.abutalabs.com/products/fully-local-pdf-chatbot
Homepage: https://webml-demo.vercel.app
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2025-12-06T19:32:18+00:00

## Health v2 (maintenance only)
Score: 52/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 55, release rhythm 35, longevity 77
- inputs: {"age_days": 1081, "days_push": 270, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1817, forks 315 (observed 2026-08-28T04:05:40.642772+00:00)

## What it is
A Next.js web application that lets users chat with uploaded PDF documents entirely locally, performing chunking, embedding, vector storage, and RAG client-side. It supports running LLM inference via Ollama, WebLLM in-browser, or Chrome's experimental built-in Gemini Nano, so it works even with WiFi turned off.

## Use cases
- chat with pdf documents locally
- ask questions about a pdf without uploading to the cloud
- run retrieval augmented generation fully in the browser
- query documents offline with a local llm
- private document q&a with no data leaving my machine
- chat over documents using ollama
- in-browser rag with webllm

## When to choose
- you need privacy-sensitive document Q&A where data never leaves your device
- you want to demo or experiment with in-browser LLM inference and RAG
- you want a self-hosted chat-with-PDF app using Ollama

## When to avoid
- you need high-quality answers from large frontier models
- you need to index large document collections at scale
- you need multi-user or production deployment features

## Facets
- artifact type: application
- maturity: active
- function: rag, llm-inference, pdf, chatbot, web-scraping
- domain: large-language-models, pdf, privacy, web-development
- platform: browser, wasm, cross-platform
- tags: local-llm, ollama, webllm, gemini-nano, nextjs, langchain, client-side, vector-store, chat-with-documents, retrieval-augmented-generation, web-server

## Member repositories
- jacoblee93/fully-local-pdf-chatbot (main) score 52

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:40.642772+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:20:11.683173+00:00, confidence not recorded.
  - readme: https://github.com/jacoblee93/fully-local-pdf-chatbot (fetched 2026-08-28T04:05:40.642772+00:00, sha adc5ba86c098)
  - homepage: https://webml-demo.vercel.app (fetched 2026-08-29T10:59:20.038385+00:00, sha cb54ef92e9d5)
- Data as of 2026-08-30T08:39:29.467469+00:00.