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

Introduction to LangGraph and Graph Principles

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

State Management and Prompt Chaining

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

Branching, Control Flow, and Error Management

• Implementing conditional routing and multi-path workflows
• Configuring retries, timeouts, and fallback mechanisms
• Ensuring idempotency and secure re-execution

Tools and External Integrations

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

Retrieval-Augmented Workflows

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

Testing, Debugging, and Assessment

• Writing unit-style tests for nodes and paths
• Implementing tracing and observability
• Conducting quality checks for factuality, safety, and determinism

Package Management and Deployment Basics

• Setting up environments and managing dependencies
• Hosting graphs behind APIs
• Versioning workflows and managing rolling updates

Conclusion and Future Directions