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

LLM Document Chat

LLM Document Chat is a Jupyter notebook example for PDF question answering: Redis stores and retrieves document vectors, LlamaIndex searches document content semantically, and OpenAI provides a chatbot-like interaction using retrieved context.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

LLM Document 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 when you want to inspect or adapt a documented Jupyter notebook example of semantic document retrieval and PDF question answering.

Who it is for

  • Developers learning how to combine vector search and semantic retrieval for document question answering.
  • Readers evaluating a notebook-based reference for a Redis, LlamaIndex, and OpenAI workflow.

Documented uses

  • Explore a PDF question-answering flow that retrieves relevant document context before querying OpenAI.
  • Study Redis vector storage and retrieval alongside LlamaIndex semantic search.
  • Compare documented OpenAI and Redis provider configurations for a local or cloud-backed notebook setup.
Before you choose

Requirements & limits

The repository is public and MIT-licensed. Running the example requires Docker Desktop with Docker Compose and configured OpenAI or Azure OpenAI and Redis services.

  • The project is a notebook tutorial and reference implementation, not a documented hosted chat product.
  • Redis must provide Search and Query features, including vector similarity search.
  • The README documents both local Redis Stack and remote Redis options, and both direct OpenAI and Azure OpenAI configurations.

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

Start the Dockerized JupyterLab example

Configure the documented services and open the project’s JupyterLab environment.

Before you start

  • Docker Desktop with Docker Compose
  • An OpenAI API key or Azure OpenAI resource with text and embedding model deployments
  • Redis Search and Query with vector similarity search, using Redis Enterprise Cloud, Azure Redis Enterprise, or local Redis Stack

Steps

  1. Clone the repository and copy .env.template to .env.

  2. Configure .env for the selected OpenAI provider and Redis host, port, and password.

  3. For cloud or Azure Redis Enterprise, run the command below; for local Redis Stack, run the command below.

    Documented command
    docker compose -f docker/cloud/docker-compose.yml up
    Documented command
    docker compose -f docker/local/docker-compose.yml up

  4. Open the JupyterLab URL shown in the terminal logs, using the generated token.

Expected outcome

A JupyterLab session opens in the browser for exploring the notebook example.

Guide limitations

  • The README describes a tutorial environment; it does not establish that this setup is a hosted service.
  • Azure infrastructure deployment is a separate documented option and is not part of these steps.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
redis-developer/LLM-Document-Chat · Official homepage title · retained in its source language
How we review sourcesSuggest a correction