# techleadhd/chatgpt-retrieval

Repository: https://github.com/techleadhd/chatgpt-retrieval
Canonical: https://ross.abutalabs.com/products/chatgpt-retrieval
Language: Python
License Family: other
Last push: 2024-03-04T16:52:28+00:00

## Health v2 (maintenance only)
Score: 29/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 83
- inputs: {"age_days": 1172, "days_push": 912, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1701, forks 766 (observed 2026-08-28T04:05:24.302836+00:00)

## What it is
A simple Python script that lets you ask ChatGPT questions about your own files using LangChain and a Chroma vector store. It loads text or PDF data, embeds it, and answers queries from the command line.

## Use cases
- ask questions about my own text files with chatgpt
- query a pdf with chatgpt
- build a simple retrieval chatbot over personal documents
- chat with my data using openai api
- simple rag script for custom files

## When to choose
- you want a minimal, easy-to-understand RAG example over your own txt or pdf files
- you are learning how LangChain retrieval works
- you need a quick command-line Q&A over a small document

## When to avoid
- you need a production-grade RAG pipeline with scaling, auth, or a web UI
- you want support for many file formats or large corpora
- you need an actively maintained project with tests and a license

## Facets
- artifact type: cli-tool
- maturity: maintenance
- function: rag, llm-inference, search-engine, cli
- domain: large-language-models, artificial-intelligence, developer-tools
- platform: python, cli, cross-platform
- tags: chatgpt, langchain, chromadb, question-answering, custom-documents, openai, retrieval-augmented-generation

## Member repositories
- techleadhd/chatgpt-retrieval (main) score 29

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:24.302836+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 2026-08-30T03:37:44.224408+00:00, confidence not recorded.
  - readme: https://github.com/techleadhd/chatgpt-retrieval (fetched 2026-08-28T04:05:24.302836+00:00, sha 152e830d72d5)
- Data as of 2026-08-30T08:39:29.467469+00:00.