# Nutlope/pdftochat

Chat with your PDFs with AI

Repository: https://github.com/Nutlope/pdftochat
Canonical: https://ross.abutalabs.com/products/pdftochat
Homepage: https://www.pdftochat.com/
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2026-06-26T14:13:24+00:00

## Health v2 (maintenance only)
Score: 68/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 89, release rhythm 35, longevity 77
- inputs: {"age_days": 1089, "days_push": 68, "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 1441, forks 301 (observed 2026-08-28T04:04:44.309003+00:00)

## What it is
PDFToChat is an open-source Next.js web application that lets users upload PDFs and chat with them using AI. It uses Together AI's Mixtral LLM, Chroma Cloud for hybrid vector search, and LangChain.js for the RAG pipeline.

## Use cases
- chat with pdf documents using ai
- ask questions about a pdf
- summarize and query research papers
- build a document question-answering app
- self-host a pdf chatbot
- deploy a rag app on vercel

## When to choose
- you want a ready-to-deploy open-source PDF chat app
- you need a reference implementation of RAG with Next.js and LangChain
- you want hybrid dense+sparse vector search over documents

## When to avoid
- you need fully local/offline processing since it depends on cloud services
- you need a production SaaS without setting up multiple third-party API keys
- you need to chat with non-PDF file formats

## Facets
- artifact type: application
- maturity: active
- function: rag, chatbot, llm-inference, pdf, vector-database, web-framework, auth
- domain: artificial-intelligence, large-language-models, pdf, web-development, chatbots
- platform: cloud
- tags: nextjs, langchain, together-ai, chroma, document-qa, open-source-template, retrieval-augmented-generation, nodejs, web-server, typescript

## Member repositories
- Nutlope/pdftochat (main) score 68

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:44.309003+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 2026-08-30T04:36:26.853292+00:00, confidence not recorded.
  - readme: https://github.com/Nutlope/pdftochat (fetched 2026-08-28T04:04:44.309003+00:00, sha 4d6457848b02)
  - homepage: https://www.pdftochat.com/ (fetched 2026-08-29T11:47:00.037470+00:00, sha fff06e61a0c4)
- Data as of 2026-08-30T08:39:29.467469+00:00.