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

Introduction to LangGraph and Graph Concepts

• The rationale for utilizing graphs in LLM applications: orchestration versus simple chains
• Core definitions of nodes, edges, and state within LangGraph
• First executable graph: Hello LangGraph

State Management and Prompt Chaining

• Configuring prompts as individual graph nodes
• Facilitating state transfer between nodes and managing output data
• Memory architectures: contrasting short-term and persisted context

Branching, Control Flow, and Error Handling

• Implementing conditional routing and multi-path operational flows
• Managing retries, timeouts, and fallback protocols
• Ensuring idempotency and secure re-execution

Tools and External Integrations

• Executing function and tool calls from graph nodes
• Interacting with REST APIs and services inside the graph structure
• Processing structured output data

Retrieval-Augmented Workflows

• Basics of document ingestion and chunking strategies
• Utilizing embeddings and vector stores (such as ChromaDB)
• Generating grounded responses with appropriate citations

Testing, Debugging, and Evaluation

• Creating unit-level tests for specific nodes and execution paths
• Implementing tracing mechanisms and observability features
• Enforcing quality standards: factuality, safety, and determinism

Packaging and Deployment Fundamentals

• Configuring environments and managing dependencies
• Exposing graphs via API endpoints
• Managing workflow versions and executing rolling updates

Summary and Next Steps