# run-llama/rags

Build ChatGPT over your data, all with natural language

Repository: https://github.com/run-llama/rags
Canonical: https://ross.abutalabs.com/products/rags
Language: Python
License: MIT
License Family: permissive
Topics: agent, chatbot, chatgpt, gpts, llamaindex, llm, openai, rag, streamlit
Last push: 2024-04-05T05:36:59+00:00

## Health v2 (maintenance only)
Score: 27/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 72
- inputs: {"age_days": 1021, "days_push": 880, "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 6549, forks 656 (observed 2026-08-28T04:09:45.152027+00:00)

## What it is
A Streamlit web app that lets users build a RAG (retrieval-augmented generation) pipeline over their data using natural language instructions. A builder agent generates RAG parameters (top-k, chunk size, models, system prompt) which users can edit, then chat with the resulting agent.

## Use cases
- build a chatgpt over my documents without code
- create a custom gpt from a web page or local file
- generate a rag pipeline by describing it in natural language
- chat with an ai agent over my data
- tune rag parameters like top-k and chunk size via a ui
- self-host a private chatgpt alternative over my own sources

## When to choose
- you want a no-code/low-code UI to spin up RAG agents over a single file or web page
- you want an OpenAI GPTs-like experience that you self-host
- you want to inspect and tweak generated RAG configuration parameters

## When to avoid
- you need production-grade, multi-source or enterprise RAG deployments
- you want to avoid OpenAI API dependency or costs
- you need to ingest large document collections rather than a single file or page
- you need a programmable library rather than a Streamlit app

## Facets
- artifact type: application
- maturity: maintenance
- function: rag, agent-framework, chatbot, llm-inference
- domain: large-language-models, chatbots
- platform: python, self-hosted
- tags: streamlit, llamaindex, openai, gpts, natural-language-configuration, retrieval-augmented-generation, ai-agents, natural-language-processing, web-server

## Member repositories
- run-llama/rags (main) score 27

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:45.152027+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 2026-08-29T17:44:04.570583+00:00, confidence not recorded.
  - readme: https://github.com/run-llama/rags (fetched 2026-08-28T04:09:45.152027+00:00, sha 18ad31a5c7bb)
- Data as of 2026-08-30T08:39:29.467469+00:00.