# openai/chatgpt-retrieval-plugin

The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.

Repository: https://github.com/openai/chatgpt-retrieval-plugin
Canonical: https://ross.abutalabs.com/products/chatgpt-retrieval-plugin
Language: Python
License: MIT
License Family: permissive
Topics: chatgpt, chatgpt-plugins
Last push: 2024-07-04T22:00:16+00:00

## Health v2 (maintenance only)
Score: 30/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 89
- inputs: {"age_days": 1259, "days_push": 790, "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 21213, forks 3574 (observed 2026-08-28T04:11:31.456079+00:00)

## What it is
A FastAPI-based retrieval backend that provides semantic search over personal or organizational documents using natural language queries, with pluggable vector database providers. It can back ChatGPT custom GPTs, function calling, or the Assistants API.

## Use cases
- search my personal documents with natural language questions
- build a custom GPT that answers from my own files
- add semantic document retrieval to a chatbot
- self-host a retrieval API over organizational documents
- query embeddings stored in a vector database via an API

## When to choose
- you need fine-grained control over chunking, embedding models, or vector store choice
- you want a self-hosted retrieval backend for ChatGPT or the Assistants API
- you need to search documents across multiple vector database providers

## When to avoid
- you only need simple file upload retrieval, which ChatGPT and the Assistants API support natively
- you want an actively developed turnkey RAG product rather than a reference implementation
- you cannot self-host or expose an API endpoint

## Facets
- artifact type: service
- maturity: maintenance
- function: rag, search-engine, vector-database, api-framework, llm-inference
- domain: large-language-models, artificial-intelligence, chatbots
- platform: python, self-hosted
- tags: chatgpt, semantic-search, embeddings, fastapi, document-retrieval, openai, retrieval-augmented-generation, search, docker, web-server

## Member repositories
- openai/chatgpt-retrieval-plugin (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:31.456079+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 2026-08-29T16:58:28.120476+00:00, confidence not recorded.
  - readme: https://github.com/openai/chatgpt-retrieval-plugin (fetched 2026-08-28T04:11:31.456079+00:00, sha f558f73690dd)
- Data as of 2026-08-30T08:39:29.467469+00:00.