ray-project/llm-applications
A production guide for building retrieval augmented generation (RAG) based LLM applications using Ray and Anyscale.
Not currently ranked — collecting fresh signals.
star history
This repository provides a comprehensive tutorial for developing RAG-based LLM applications from scratch. It covers key stages including document loading, chunking, embedding, indexing, serving, and evaluation. The guide also addresses scaling these components using Ray, implementing hybrid routing between open-source and closed LLMs, and optimizing both retrieval and quality scores through systematic evaluation.
Frequently asked
- What is ray-project/llm-applications?
- A production guide for building retrieval augmented generation (RAG) based LLM applications using Ray and Anyscale.
- Is llm-applications open source?
- Yes — ray-project/llm-applications is open source, released under the CC-BY-4.0 license.
- What language is llm-applications written in?
- ray-project/llm-applications is primarily written in Jupyter Notebook.
- How popular is llm-applications?
- ray-project/llm-applications has 1.9k stars on GitHub.
- Where can I find llm-applications?
- ray-project/llm-applications is on GitHub at https://github.com/ray-project/llm-applications.