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

Introduction to LangGraph and Graph Theories

• The case for graphs in LLM applications: orchestration versus simple chaining
• Understanding nodes, edges, and state within LangGraph
• Getting started: executing your first LangGraph structure

State Management and Prompt Chaining

• Structuring prompts as individual graph nodes
• Managing state transfer between nodes and processing outputs
• Memory strategies: distinguishing short-term vs. 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 inside the graph structure
• Handling structured data outputs

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

• Developing unit-style tests for nodes and execution paths
• Implementing tracing and observability measures
• Conducting quality assurance checks for factuality, safety, and determinism

Packaging and Deployment Essentials

• Setting up environments and managing dependencies
• Exposing graphs via API endpoints
• Workflow versioning and implementing rolling updates

Conclusion and Future Directions