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

Introduction to LangGraph and Graphical Concepts

• The rationale for using graphs in LLM apps: orchestration versus linear chains
• Understanding nodes, edges, and state within LangGraph
• Getting started: executing a basic LangGraph structure

State Control and Prompt Sequencing

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

Branching, Control Logic, and Error Mitigation

• Implementing conditional routing and multi-path processes
• Handling retries, timeouts, and backup strategies
• Ensuring idempotency and secure re-execution

Tool Utilization and External Connections

• Executing function and tool calls from graph nodes
• Interacting with REST APIs and services inside the graph
• Processing structured data outputs

Workflows Enhanced by Retrieval

• Basics of document processing and segmentation
• Utilizing embeddings and vector databases (e.g., ChromaDB)
• Generating grounded answers with source citations

Verification, Troubleshooting, and Assessment

• Conducting unit-level tests for nodes and execution paths
• Implementing tracing and observability measures
• Quality assurance: verifying accuracy, safety, and consistency

Packaging and Deployment Basics

• Configuring the environment and managing dependencies
• Exposing graphs via API endpoints
• Managing workflow versions and implementing gradual updates

Recap and Future Directions