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

Multitype LLM Chat

Multitype LLM Chat is a self-hosted RAG chatbot application that indexes user-provided YouTube videos, PDFs and web links, then uses the indexed content to ground questions answered with GPT models.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Multitype LLM Chat — 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 for a focused research chat, such as exploring one large legal document or a curated set of related sources. The project cautions that mixing unrelated documents can produce confusing or mixed results.

Who it is for

  • Researchers who want to ask questions about a defined set of documents or other supported source material.
  • Developers prepared to set up and run a web app, indexing API and supporting databases locally.

Documented uses

  • Add PDFs, YouTube videos or web links as research material.
  • Ask questions grounded in indexed content.
  • Keep separate research topics in distinct chat instances.
Before you choose

Requirements & limits

The README documents local setup. It describes the project as in development and not ready for production use.

  • The documented stack includes a MySQL-compatible database, Weaviate, a Flask indexing API and a TypeScript web app.
  • Starting the vector database uses Docker Compose; the README also requires pnpm and Python setup.
  • The README advises keeping each chat focused on a singular purpose.

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 the app locally

Initialize the documented database, vector database, indexing API and web app.

Before you start

  • A local MySQL server or a remote MySQL-compatible database
  • pnpm
  • Python and the repository's indexing-service requirements
  • Docker Compose

Steps

  1. Create a database, add its connection string as DATABASE_URL in the .env file, and run pnpm run db:push.

  2. From indexing-service, start Weaviate with docker-compose up.

  3. Create and activate a Python virtual environment in indexing-service, install requirements.txt, and start the Flask API with python main.py.

  4. In web, run pnpm install and then pnpm dev.

Expected outcome

The documented startup process initializes the app's components for local use.

Guide limitations

  • The repository describes the app as a development-stage proof of concept that is not ready for production use.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
18 October 2026
Original website title
sebi75/multitype-llm-chat · Official homepage title · retained in its source language
How we review sourcesSuggest a correction