zyuanlim / LLM-Ops-Cohort-1

Following emerging Large Language Model Operations (LLM Ops) best practices in the industry, you’ll learn all about the key technologies that enable Generative AI practitioners like you to leverage tools like LangChain, LLamaIndex, and more, to build complex LLM applications.

👋 Welcome to LLM Ops: LLMs in Production, Cohort 1!

Access all of the concepts and code directly YouTube to start building, shipping, and sharing with LLM Ops!

Async Learning Outcomes

1. Build complex apps with LLM Ops frameworks including LangChain and LlamaIndex.
2. Understand LLM product development methods, from prompting to retrieval and beyond.
3. Build, deploy, evaluate, and operate your own end-to-end production RAG system.

Note: This course was taught from August, 15, 2023 to September 7, 2023. As such, there may be aspects of the code that require updates for full functionality. Please submit pull requests directly if you find something that you can help improve!

LLM Ops Cohort 1, Session Videos

Session	Video Link	Code	Slides
Session 1: Course Intro, Building Your First RAG App with LangChain, Chainlit, and Hugging Face	🎥 Video	🐙 Repo	💻 Slides
Session 2: Taking RAG to the Next Level with LangChain Agents	🎥 Video	🐙 Repo	💻 Slides
Session 3: Building a More Robust RAG System with LlamaIndex Data Agents	🎥 Video	🐙 Repo	💻 Slides
Session 4: Project Ideation, Chainlit, and Fine-Tuning of an E2E RAG App with LlamaIndex	🎥 Video	🐙 Repo	💻 Slides
Session 5: Building a Production-Grade Open-Source RAG System with Llama 2, FastAPI, and Chainlit	🎥 Video	🐙 Repo	💻 Slides
Session 6: Scalable Llama 2 Endpoints for RAG, Evaluation with RAGAS and Eluether AI Harness	🎥 Video	🐙 Repo	💻 Slides
Session 7: Visibility and Observability Tooling for LLM Ops, WandB and LangSmith	🎥 Video	🐙 Repo	💻 Slides