OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Rags

Rags is an open-source Python Streamlit application for creating a retrieval-augmented generation pipeline over a single local file or web page. Users describe the task and desired retrieval behavior in natural language, inspect and edit generated settings, and query the resulting chatbot about the selected data.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Rags — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Rags when you want to build and tune a question-answering pipeline over one supported source, then query that source through a chatbot.

Who it is for

  • People who want a configurable chatbot for questions about one local file or web page.
  • Developers who want to self-host a Streamlit RAG application and adjust model or retrieval settings.

Documented uses

  • Create a RAG pipeline from a local file or web page using natural-language instructions.
  • Review and change the system prompt, top-k, chunk size, embedding model and LLM.
  • Add summarization as an option alongside top-k vector retrieval.
  • Ask questions about the data through the generated chatbot.
Before you choose

Requirements & limits

The repository is public and lists an MIT license. The documented default setup requires an OpenAI key for both the builder and generated RAG agent.

  • The documented source scope is one local file or one web page.
  • OpenAI is the default for both agents; other documented generated-agent model options require explicit model IDs.
  • Hugging Face embedding models can be selected using the documented local: model naming convention.
  • The builder agent is customizable; the README includes an Anthropic example and cautions that Claude did not work for the authors at the time of writing.
  • The configuration controls retrieval depth, chunk size, prompt, embedding model, LLM and optional summarization.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install and launch Rags locally

Set up the Streamlit application and start its home page using the documented default OpenAI configuration.

Before you start

  • Python and Poetry
  • An OpenAI API key
  • A local copy of the Rags repository

Steps

  1. Clone the repository and enter the rags project folder.

  2. Create a Python virtual environment, as recommended in the README.

  3. Install dependencies with poetry install --with dev.

  4. Add .streamlit/secrets.toml in the home folder with openai_key = "".

  5. Start the app with streamlit run 1_🏠_Home.py.

Expected outcome

The Streamlit app launches at its Home page, where a RAG pipeline can be configured.

Guide limitations

  • This setup uses OpenAI by default for both the builder and generated RAG agent.
  • The instructions do not specify deployment beyond running the local app.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Retrieval-augmented applications

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
RagsCreate a RAG pipeline from a local file or web page using natural-language instructions.Self-hosted, WebThe repository is public and lists an MIT license. The documented default setup requires an OpenAI key for both the builder and generated RAG agent.
Rag Powered AI Assistant Transforming Data Retrieval And Analysis Across The Web And PdfsRetrieve relevant passages from web and PDF content to answer a question.Web
LangChain in Supabase Edge FunctionsInitialize and start a Supabase project locally.Cloud, Server
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
run-llama/rags · Official homepage title · retained in its source language
How we review sourcesSuggest a correction