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

Introduction to LangGraph and Graph Concepts

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

State Management and Prompt Chaining

• Structuring prompts as distinct graph nodes
• Transferring state between nodes and managing outputs
• Memory patterns: differentiating between short-term and persisted context

Branching, Control Flow, and Error Handling

• Implementing conditional routing and multi-path workflows
• Managing retries, timeouts, and fallback strategies
• Ensuring idempotency for safe re-executions

Tools and External Integrations

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

Retrieval-Augmented 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 paths
• Implementing tracing and observability techniques
• Conducting quality checks for factuality, safety, and determinism

Packaging and Deployment Fundamentals

• Setting up environments and managing dependencies
• Serving graphs via API endpoints
• Managing workflow versioning and implementing rolling updates

Summary and Next Steps