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

Introduction to LangGraph and Graphical Concepts

• The advantage of graphs in LLM applications: orchestration versus linear chains
• Defining nodes, edges, and state within LangGraph
• Getting started: Building your first executable graph

State Management and Prompt Chaining

• Structuring prompts as distinct graph nodes
• Transferring state 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

Tool Integration and External Connections

• Executing function and tool calls from graph nodes
• Interacting with REST APIs and services within 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 citations

Testing, Debugging, and Evaluation

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

Foundations of Packaging and Deployment

• Setting up environments and managing dependencies
• Exposing graphs through API services
• Workflow versioning and implementing rolling updates

Recap and Future Directions