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

Introduction to LangGraph and Graph Theory

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

State Management and Prompt Chaining

• Structuring prompts as individual graph nodes
• Managing state transfer between nodes and processing outputs
• Memory strategies: distinguishing between short-term and persisted context

Branching, Control Flow, and Error Management

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

Tools and External Integrations

• Executing function and tool calls from graph nodes
• Interacting with REST APIs and services within the graph structure
• Handling structured data outputs

Retrieval-Augmented Generation Workflows

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

Testing, Debugging, and Evaluation

• Writing unit-style tests for individual nodes and pathways
• Implementing tracing and observability practices
• Quality assurance: assessing factuality, safety, and determinism

Packaging and Deployment Essentials

• Setting up environments and managing dependencies
• Exposing graphs via API endpoints
• Versioning workflows and implementing rolling updates

Summary and Future Directions