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

Introduction to LangGraph and Graph Theories

• The rationale for using graphs in LLM apps: advanced orchestration vs. simple chains
• Understanding nodes, edges, and state within the LangGraph ecosystem
• Getting started with LangGraph: building the first executable graph

State Management and Prompt Sequencing

• 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 Resilience

• Implementing conditional routing and multi-path workflow designs
• Handling retries, timeouts, and establishing fallback mechanisms
• Ensuring idempotency and safe re-execution

Tool Integration and External Services

• Executing function and tool calls directly from graph nodes
• Interacting with REST APIs and external services within the graph structure
• Processing and utilizing structured outputs

Retrieval-Augmented Generation (RAG) Workflows

• Basics of document ingestion and chunking strategies
• Utilizing embeddings and vector databases (such as ChromaDB)
• Generating grounded responses with accurate citations

Testing, Debugging, and Performance Evaluation

• Implementing unit-style tests for individual nodes and workflow paths
• Enhancing visibility through tracing and observability tools
• Quality assurance: verifying factuality, safety, and determinism

Deployment and Packaging Essentials

• Configuring environments and managing dependencies
• Exposing graph workflows via API endpoints
• Managing workflow versions and implementing rolling updates

Conclusion and Future Pathways