Skip to content

Latest commit

 

History

History
96 lines (61 loc) · 2.54 KB

File metadata and controls

96 lines (61 loc) · 2.54 KB

GenAI Starter Pack Learning Path

Use this path when you want to move from simple cloneable LLM apps to stronger agentic systems without getting lost in random demos.

1. Start With Beginner-Friendly Apps

Goal: learn how Hugging Face Spaces, Gradio, Streamlit, dependencies, secrets, and simple LLM app structure work.

Start with:

What to study:

  • Where the app entry point lives.
  • How dependencies are declared.
  • How API keys and environment variables are handled.
  • How the UI calls model or retrieval logic.

2. Learn RAG Foundations

Goal: understand document ingestion, chunking, embeddings, vector stores, retrieval, prompting, and answer generation.

Start with:

What to study:

  • PDF loading and text extraction.
  • Chunking strategy.
  • FAISS, ChromaDB, Qdrant, Pinecone, or other vector store usage.
  • Prompt structure and citation handling.
  • Separation between UI, retrieval, and generation code.

3. Move Into Agentic RAG

Goal: learn how retrieval becomes part of a tool-using workflow rather than a single question-answer call.

Start with:

What to study:

  • Tool definitions.
  • Agent state.
  • Routing decisions.
  • Retry/error paths.
  • How retrieval is triggered and validated.

4. Study Multi-Agent Systems

Goal: understand when multiple agents help, when they add complexity, and how orchestration is represented in code.

Start with:

What to study:

  • Agent roles.
  • Shared state or memory.
  • Task delegation.
  • Human-readable traces.
  • Where the workflow can fail.

5. Learn MCP Patterns

Goal: understand how model-facing tools can be exposed as reusable protocol servers and app wrappers.

Start with:

What to study:

  • Tool schema design.
  • Server/app boundaries.
  • How the MCP server is launched.
  • How an LLM client discovers and calls tools.

6. Build Your Own Starter App

After studying three to five projects, build a small project with:

  • One clean README.
  • One reproducible setup path.
  • One sample input.
  • One obvious app entry point.
  • One test or smoke-check script.

The best portfolio projects are not the biggest. They are the easiest to understand, clone, run, and extend.