LangGraph Foundations: Graph-Based LLM Prompting and Chaining Training Course

Introduction to LangGraph and Graph-Based Concepts

• The rationale for using graphs in LLM apps: orchestration versus simple chains
• Understanding nodes, edges, and state within LangGraph
• Getting started with LangGraph: building your first executable graph

State Management and Prompt Chaining

• Structuring prompts as individual graph nodes
• Transferring state between nodes and managing outputs
• Memory patterns: distinguishing between short-term and persisted context

Branching, Control Flow, and Error Management

• Implementing conditional routing and multi-path workflows
• Handling retries, timeouts, and fallback mechanisms
• Ensuring idempotency and the safety of re-runs

Tools and External Integrations

• Invoking functions and tools from within graph nodes
• Interacting with REST APIs and services inside the graph structure
• Processing structured outputs effectively

Retrieval-Augmented Workflows

• Basics of document ingestion and chunking
• Utilizing embeddings and vector stores (e.g., ChromaDB)
• Generating grounded answers with proper citations

Testing, Debugging, and Evaluation

• Writing unit-style tests for nodes and execution paths
• Implementing tracing and observability features
• Performing quality checks on factuality, safety, and determinism

Packaging and Deployment Fundamentals

• Configuring the environment and managing dependencies
• Exposing graphs as services behind APIs
• Managing workflow versions and executing rolling updates

Summary and Future Directions