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

Introduction to LangGraph and Graph Principles

• The case for graphs in LLM applications: orchestration versus linear chains
• Understanding nodes, edges, and state within LangGraph
• Getting started: creating your first executable graph

State Management and Prompt Chaining

• Structuring prompts as individual graph nodes
• Managing state transitions and handling node outputs
• Implementing memory strategies: short-term versus persisted context

Branching, Control Flow, and Error Management

• Implementing conditional routing and multi-path workflows
• Handling retries, timeouts, and defining fallback mechanisms
• Ensuring idempotency and enabling safe re-execution

Tools and External Integrations

• Invoking functions and tools from within graph nodes
• Integrating REST APIs and external services into the graph structure
• Processing and utilizing structured outputs

Retrieval-Augmented Workflows

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

Testing, Debugging, and Evaluation

• Writing unit-style tests for individual nodes and execution paths
• Implementing tracing and observability tools
• Performing quality assessments for factuality, safety, and determinism

Deployment and Packaging Basics

• Configuring environments and managing dependencies
• Exposing graph workflows via API endpoints
• Versioning workflows and managing rolling updates

Conclusion and Future Steps