GH Repository · decodingai-magazine
llm-twin-course
🤖 𝗟𝗲𝗮𝗿𝗻 for 𝗳𝗿𝗲𝗲 how to 𝗯𝘂𝗶𝗹𝗱 an end-to-end 𝗽𝗿𝗼𝗱𝘂𝗰𝘁𝗶𝗼𝗻-𝗿𝗲𝗮𝗱𝘆 𝗟𝗟𝗠 & 𝗥𝗔𝗚 𝘀𝘆𝘀𝘁𝗲𝗺 using 𝗟𝗟𝗠𝗢𝗽𝘀 best practices: ~ 𝘴𝘰𝘶𝘳𝘤𝘦 𝘤𝘰𝘥𝘦 + 12 𝘩𝘢𝘯𝘥𝘴-𝘰𝘯 𝘭𝘦𝘴𝘴𝘰𝘯𝘴
- stars
- 4,385
- 30-day movement
- +21/day
- Related entries
- 60
- Connections
- 1
python/poetryPythonpulumillmopsinfrastructure-as-codebytewaxraggenerative-aiawssuperlinkedmakedockercomet-mllarge-language-modelspythonqwakmachine-learning-engineeringml-system-designqdrantmlopscourse
A free course teaching you how to build an end-to-end, production-ready LLM and RAG system using LLMOps best practices. It includes source code and 12 hands-on lessons, with tooling spanning AWS, Qdrant, Bytewax, Comet ML, Superlinked, Qwak, Docker, and Pulumi.
You want structured, hands-on practice building a complete production RAG pipeline rather than isolated examples.
Use it to
- Follow 12 hands-on lessons to build an LLM & RAG system
- Study LLMOps and ML system design practices
- Learn infrastructure-as-code with Pulumi for ML systems
- Work with Qdrant for vector retrieval in RAG
- Reuse the course source code as a reference implementation
For Machine learning engineers wanting production LLM/RAG skills
- Role
- rag
- Language
- Python
- Licence
- MIT
- Forks
- 730
- Open issues
- 5
- Last push
- 2026-04-20
topicsragllmopscoursemlopsmachine-learning-engineeringgenerative-ai