Level 1 (Beginner)

  1. Understand the basics of LLM - you should just know how ChatGPT works at a high level
  2. Learn Prompt Engineering for Developers. How to write prompts to improve the response of an LLM.
  3. Learn to call closed and open-source LLM models, function calling, passing prompts, and parsing responses
  4. Learn to create and automate a sequence of operations - Chains using langchain.
  5. Basic app development using Streamlit or Gradio for POCs and demos.

Level 2 (Intermediate)

  1. Understanding vector embeddings and vector databases
  2. Learning how to use vector databases for your application
  3. Building retrieval-augmented Generation (RAG) - chat with your knowledge base

Level 3 (Advanced)

  1. Understanding hybrid search
  2. Evaluating RAG
  3. Build multi-modal applications - hybrid semantic search with text and image
  4. Building agents - iterative workflows to finish off a big task
  5. Building multi-agent applications where more than one agent works together to provide a better solution

Level 4 (Expert)

  1. Evaluate and benchmark the model performance
  2. LLMOps - build complete e2e pipelines with model registry, observability and automated testing