# ray-project/llm-applications

A comprehensive guide to building RAG-based LLM applications for production.

Repository: https://github.com/ray-project/llm-applications
Canonical: https://ross.abutalabs.com/products/llm-applications
Language: Jupyter Notebook
License: CC-BY-4.0
License Family: other
Topics: llms, machine-learning, ray, anyscale, fine-tuning, llama2, openai, serving
Last push: 2026-08-15T00:14:04+00:00

## Health v2 (maintenance only)
Score: 62/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 8, longevity 79
- inputs: {"age_days": 1113, "days_push": 19, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1855, forks 257 (observed 2026-08-28T04:05:44.715340+00:00)

## What it is
A comprehensive tutorial repository (Jupyter notebooks plus guide) for building production-grade RAG-based LLM applications using Ray. It covers developing, scaling, evaluating, and serving RAG pipelines end to end.

## Use cases
- learn how to build a rag application from scratch
- scale embedding and indexing pipelines for llm apps
- evaluate rag configurations for retrieval quality
- serve a rag llm application in production
- fine-tune and route between open and closed llms

## When to choose
- you want a hands-on, end-to-end RAG tutorial with runnable notebooks
- you plan to use Ray or Anyscale to scale LLM workloads
- you need guidance on evaluating and optimizing RAG pipelines

## When to avoid
- you need a ready-made production RAG framework rather than a guide
- you don't want dependencies on OpenAI or Anyscale services
- you need a maintained software library with a stable API

## Facets
- artifact type: learning-resource
- maturity: active
- function: rag, llm-inference, machine-learning, benchmarking, documentation
- domain: large-language-models, machine-learning, tutorials
- platform: python, cloud
- tags: jupyter-notebook, ray, llamaindex, production-guide, fine-tuning, vector-search, retrieval-augmented-generation, gpu

## Member repositories
- ray-project/llm-applications (main) score 62

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:44.715340+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:16:45.290596+00:00, confidence not recorded.
  - readme: https://github.com/ray-project/llm-applications (fetched 2026-08-28T04:05:44.715340+00:00, sha b0d677225f29)
- Data as of 2026-08-30T08:39:29.467469+00:00.