Level 1 (Beginner)
- Understand the basics of LLM - you should just know how ChatGPT works at a high level
- Learn Prompt Engineering for Developers. How to write prompts to improve the response of an LLM.
- Learn to call closed and open-source LLM models, function calling, passing prompts, and parsing responses
- Learn to create and automate a sequence of operations - Chains using langchain.
- Basic app development using Streamlit or Gradio for POCs and demos.
Level 2 (Intermediate)
- Understanding vector embeddings and vector databases
- Learning how to use vector databases for your application
- Building retrieval-augmented Generation (RAG) - chat with your knowledge base
Level 3 (Advanced)
- Understanding hybrid search
- Evaluating RAG
- Build multi-modal applications - hybrid semantic search with text and image
- Building agents - iterative workflows to finish off a big task
- Building multi-agent applications where more than one agent works together to provide a better solution
Level 4 (Expert)
- Evaluate and benchmark the model performance
- LLMOps - build complete e2e pipelines with model registry, observability and automated testing