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

LLM Applications

LLM Applications is a public Jupyter Notebook guide and example repository for developing retrieval-augmented generation applications, with workflows for document loading and chunking, embedding and indexing, serving, quality evaluation, LLM routing, and scaling components with Ray-related tooling.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

LLM Applications — 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 notebook-led example of the RAG development workflow and are prepared to configure model-provider credentials and a suitable compute environment.

Who it is for

  • Developers learning to build RAG-based LLM applications.
  • Teams exploring document ingestion and retrieval workflows for their own corpus.
  • Practitioners comparing retrieval configurations and overall application quality.

Documented uses

  • Build a question-answering application over a document collection.
  • Load, chunk, embed and index source documents.
  • Compare configurations using component-level retrieval scores and overall quality scores.
  • Route requests between open-source and closed LLM endpoints.
  • Learn how to scale and serve RAG application components.
Before you choose

Requirements & limits

The repository is public and licensed under CC-BY-4.0. The README requires OpenAI and Anyscale Endpoints credentials for its described model-provider setup.

  • The project is a guide and example repository, not a hosted RAG application.
  • The documented workflow uses OpenAI and Anyscale Endpoints and requires credentials for both.
  • The README says local compute is possible but recommends GPU access; its Anyscale instructions specify a Ray 2.6.2 Python 3.9 cluster environment.
  • The notebook covers document processing, evaluation, endpoint routing and scalable serving, rather than only retrieval setup.

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 repository and notebook environment

Prepare the documented repository, Python environment and provider credentials before opening the RAG notebook.

Before you start

  • Git and a Python environment capable of installing the repository requirements.
  • OpenAI and Anyscale Endpoints accounts and API credentials.
  • Compute with GPU access is recommended; the README also describes local compute.

Steps

  1. Clone the LLM Applications repository.

  2. Create a .env file and configure the OpenAI and Anyscale API base URLs, credentials and database connection string shown in the README.

  3. Install dependencies from requirements.txt and set PYTHONPATH as directed; install and update the pre-commit hooks.

  4. Open notebooks/rag.ipynb to begin the guide.

Expected outcome

The repository environment and credentials are prepared for working through the interactive RAG notebook.

Guide limitations

  • This is a setup guide; it does not claim that the notebook has been executed or that a deployment succeeds.
  • Use of the example provider endpoints requires accounts and credentials. The README recommends GPU-accessible compute and describes a specific Anyscale cluster environment for its cloud setup.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
ray-project/llm-applications · Official homepage title · retained in its source language
How we review sourcesSuggest a correction