T2Required
AI Engineering Foundations
Python and data tools, LLM provider APIs and model choice, and open models from the Hugging Face Hub
3 modules40 notebooks
AI Engineering
Build LLM applications, retrieval pipelines and agents, from the first prompt to multi-agent systems.
- Tracks
- 14
- Notebooks
- 371
- By
- Sourav Banerjee
- 0%
- T3Required
Prompt & Context Engineering
Prompt patterns, reasoning prompts and multimodal prompting across providers
2 modules10 notebooks
0% - T4Required
LLM Application Frameworks: LangChain & LangGraph
LangChain models, prompts, parsers and LCEL; LangGraph state, routing, persistence, interrupts and streaming
4 modules47 notebooks
0% - T5Required
RAG Foundations: Ingestion & Indexing
Why retrieval exists, a measured baseline, and the ingestion pipeline: loaders, metadata, chunking, embeddings, vector stores and index design
6 modules52 notebooks
0% - T6Required
Retrieval Quality & RAG Applications
Hybrid search, query transformation and reranking, then complete RAG applications with citations, structured data, images and LlamaIndex
6 modules47 notebooks
0% - T7Required
Agent Foundations
The agent loop and tool calling by hand, ReAct with create_agent and middleware, and the five agentic workflow patterns
3 modules32 notebooks
0% - T8Required
Advanced Agents
Planning, reflection and search over reasoning paths; coding, computer-use and deep agents; human approval and applied single-agent builds
3 modules32 notebooks
0% - T9Required
Agentic RAG
Retrieval inside a control loop: grading and rewriting, CRAG and Self-RAG, adaptive routing, RAG as a tool, and feedback loops
5 modules16 notebooks
0% - T10Required
The Memory Layer
Short-term conversation state and context trimming, then long-term semantic, episodic and procedural memory for agents
2 modules21 notebooks
0% - T11Required
Multi-Agent Systems
When several agents beat one, the five architectures, supervisors, swarms, blackboards and parallel agents, and applied multi-agent builds
3 modules36 notebooks
0% - T12Required
Agent Protocols: MCP & A2A
Expose tools, data and whole agents as services with the Model Context Protocol and Agent-to-Agent
4 modules10 notebooks
0% - T13Optional
Knowledge Graphs & GraphRAG
Hierarchical and memory-augmented retrieval, knowledge graphs in Neo4j, and GraphRAG for global and multi-hop questions
3 modules14 notebooks
0% - T14Optional
Fine-Tuning & Model Adaptation
Whether to fine-tune or retrieve: when a model needs new behaviour rather than new facts, and how to adapt one through instruction tuning, data preparation, training and evaluation
1 modules13 notebooks
0% - T15Optional
Architecture Decisions
The decision that closes the course: which architecture to build for the capstone, and why each component beats a simpler one
1 modules1 notebook
0%