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

Rag Chatbot

Rag Chatbot is an open-source Python application that runs a Gradio chat interface for asking questions across multiple PDF documents, using models from Hugging Face or Ollama. Its repository provides local and Kaggle setup paths.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Rag Chatbot — 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 it when you want a locally run or Kaggle-based chat workflow for questions spanning multiple PDFs, and are comfortable setting up the project and its model environment.

Who it is for

  • Readers and researchers who want to ask questions across a collection of PDF documents.
  • Developers seeking a self-hosted, Python-based starting point for multi-PDF chat.
  • People experimenting with document question answering through Hugging Face or Ollama models.

Documented uses

  • Ask questions across multiple PDF files in a chat interface.
  • Set up a local PDF question-answering application.
  • Prepare the provided Kaggle notebook route for multi-PDF chat experiments.
Before you choose

Requirements & limits

The project is a public GitHub repository under the Apache-2.0 license. Its README documents local and Kaggle setup paths.

  • The documented interface is Gradio, and the application is Python-based.
  • Model choices named in the README include Hugging Face and Ollama.
  • The Kaggle path calls for an Ngrok token; the local README also provides launch instructions without the Ngrok option.
  • Docker Compose, a setup script and manual dependency installation are documented routes.
  • Multilingual chat is listed as coming soon, not as a current documented feature.

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

Set up Rag Chatbot locally

Install and start the documented local Gradio application.

Before you start

  • A local environment for the repository’s documented setup.
  • The project README specifies installing uv and ensuring its default ~/.local/bin location is on PATH.
  • Docker Compose is documented as an alternative installation route.

Steps

  1. Clone https://github.com/datvodinh/rag-chatbot and change into the rag-chatbot directory.

  2. Install uv and ensure ~/.local/bin is on PATH.

  3. Choose a documented installation path: run docker compose up --build, use bash ./scripts/install_extra.sh, or install Ollama and Ngrok as needed and run uv sync --locked.

  4. Start the app with bash ./scripts/run.sh or uv run python -m rag_chatbot --host localhost.

  5. Open the local address given in the README, or use the Ngrok option with bash ./scripts/run.sh --ngrok.

Expected outcome

The README describes opening the Gradio interface at http://0.0.0.0:7860/ or an Ngrok link after setup.

Guide limitations

  • The Ngrok launch option presupposes Ngrok setup; the README’s basic local launch command is separate.
Documentation 1 ↗
Source-based practical guide

Prepare the Kaggle notebook setup

Configure the documented Kaggle notebook route before use.

Before you start

  • Access to Kaggle and the project notebook.
  • An Ngrok token, as required by the notebook setup instructions.

Steps

  1. Import notebooks/kaggle.ipynb into Kaggle.

  2. Replace in the notebook with your token.

Expected outcome

The notebook has the two setup changes specified in the repository instructions.

Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
9 October 2026
Original website title
datvodinh/rag-chatbot · Official homepage title · retained in its source language
How we review sourcesSuggest a correction