#8787th of 110 in Learning and cookbooks
llm-twin-course
Course and code for building an end-to-end LLM and RAG system
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 4.4k
- License
- MIT
- Last commit
- Apr 2026
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
A free, self-paced course with 12 lessons and matching Python code that builds an "LLM twin", an LLM fine-tuned to write in your style. It covers four services: crawling into MongoDB with CDC via RabbitMQ, a Bytewax feature pipeline into Qdrant, LoRA/QLoRA fine-tuning on AWS SageMaker, and a RAG inference pipeline with a Gradio UI. Opik and Comet ML handle evaluation and monitoring.
Who it is for: ML and software engineers learning production LLM and RAG systems
Strengths
- Covers the full path from crawling to deployed inference, not isolated notebooks
- Each lesson maps to a specific src/ directory and a written article
- Includes bonus lessons on Superlinked-based multi-index RAG with Redis
- MIT licensed; stated cost is about $1 OpenAI plus under $10 AWS
Weaknesses
- Training and inference depend on AWS SageMaker, so a cloud account is required
- Also needs Comet ML, Qdrant, OpenAI and Opik accounts or services
- Reference course code, not a reusable library or deployable product
- Lesson articles are hosted on Medium, outside the repository
What it needs
- no GPU
- Compose
- Needs AWS SageMaker, MongoDB, RabbitMQ, Qdrant, Comet ML, Opik, OpenAI API, Hugging Face, Bytewax, Superlinked, Redis
- Models: LoRA/QLoRA fine-tuned LLMs, Hugging Face model registry
Also in Learning and cookbooks
See all 110| Rank | Project | Score |
|---|---|---|
| 1 | ai-engineering-from-scratchHands-on AI engineering curriculum with 542 lessons across 20 phases | 92 out of 100 |
| 2 | generative-ai-for-beginners21-lesson course on building generative AI apps in Python and TypeScript | 83 out of 100 |
| 3 | rag_techniquesCollection of 42 runnable notebooks implementing RAG techniques | 82 out of 100 |
| #4 | cs249r_bookOpen textbook and course materials for machine learning systems engineering | 82 out of 100 |
| #5 | agents-towards-productionJupyter tutorials for taking LLM agents from prototype to production | 82 out of 100 |