# guangzhengli/ChatFiles

Document Chatbot — multiple files. Powered by GPT / Embedding.

Repository: https://github.com/guangzhengli/ChatFiles
Canonical: https://ross.abutalabs.com/products/chatfiles
Language: TypeScript
License: MIT
License Family: permissive
Topics: chatbot, chatgpt, chatgpt-api, chatpdf, chatfile
Last push: 2024-12-17T10:26:50+00:00

## Health v2 (maintenance only)
Score: 21/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 89
- inputs: {"age_days": 1254, "days_push": 624, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3341, forks 462 (observed 2026-08-28T04:07:56.936875+00:00)

## What it is
ChatFiles is a Next.js web application that lets users upload documents and chat with them using GPT and embeddings via LangChainJS and a Supabase vector database. It can be deployed to Vercel with one click or run locally.

## Use cases
- chat with pdf documents
- ask questions about uploaded files
- build a document chatbot with GPT
- query multiple files with a chatbot
- self-host a chat-with-your-data app
- semantic search over documents with embeddings

## When to choose
- you want a ready-made UI to converse with your documents using OpenAI models
- you prefer a one-click Vercel deployment with Supabase as the vector store
- you want a TypeScript/LangChainJS codebase to customize for document Q&A

## When to avoid
- you need a production-grade RAG pipeline with advanced retrieval features
- you don't want to depend on OpenAI API keys and Supabase
- you need offline or local-only LLM inference
- you require enterprise features like access control or audit logs

## Facets
- artifact type: application
- maturity: maintenance
- function: rag, chatbot, chat-interface, vector-database, llm-inference
- domain: large-language-models, chatbots, web-development
- platform: self-hosted
- tags: chatpdf, chat-with-documents, langchain, supabase, nextjs, openai, embeddings, vercel, retrieval-augmented-generation, web-server, nodejs, docker

## Member repositories
- guangzhengli/ChatFiles (main) score 21

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:56.936875+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 2026-08-29T18:41:03.932337+00:00, confidence not recorded.
  - readme: https://github.com/guangzhengli/ChatFiles (fetched 2026-08-28T04:07:56.936875+00:00, sha cc74ff5cb406)
- Data as of 2026-08-30T08:39:29.467469+00:00.