# mmz-001/knowledge_gpt

Accurate answers and instant citations for your documents.

Repository: https://github.com/mmz-001/knowledge_gpt
Canonical: https://ross.abutalabs.com/products/knowledge_gpt
Homepage: https://knowledgegpt.streamlit.app/
Language: Python
License: MIT
License Family: permissive
Archived: true
Last push: 2024-05-29T21:23:51+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 93
- inputs: {"age_days": 1310, "days_push": 826, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1635, forks 786 (observed 2026-08-28T04:05:14.375006+00:00)

## What it is
KnowledgeGPT is a Streamlit web application that lets users upload documents (primarily PDFs) and ask questions about them, receiving answers with instant citations from the source text. It is built with LangChain and OpenAI's API, and can be run locally or via Docker.

## Use cases
- ask questions about my pdf documents and get cited answers
- chat with a document and see where answers come from
- build a self-hosted document Q&A app with citations
- summarize and query research papers with source references
- upload a pdf and get accurate answers with instant citations

## When to choose
- you want a ready-made document Q&A web app with citation support
- you need a simple self-hosted alternative built on LangChain and Streamlit
- you want to quickly deploy a PDF question-answering tool with Docker

## When to avoid
- you need production-grade multi-user document management
- you want local/offline LLM support (not yet implemented)
- you need OCR for scanned documents or formats beyond PDF
- you need an embeddable library or API rather than a web app

## Facets
- artifact type: application
- maturity: maintenance
- function: rag, llm-inference, chatbot, pdf, nlp
- domain: large-language-models, pdf, artificial-intelligence
- platform: python, self-hosted
- tags: streamlit, langchain, document-qa, citations, openai, retrieval-augmented-generation, docker, web-server

## Member repositories
- mmz-001/knowledge_gpt (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:14.375006+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 2026-08-30T03:47:01.893564+00:00, confidence not recorded.
  - readme: https://github.com/mmz-001/knowledge_gpt (fetched 2026-08-28T04:05:14.375006+00:00, sha fab5d3880afc)
- Data as of 2026-08-30T08:39:29.467469+00:00.