Get in Touch
 Duration 14 hours

Course Outline

Foundations of LangGraph and Graph Theory

  • The advantage of using graphs for LLM applications: orchestration versus simple linear chains
  • Defining and utilizing nodes, edges, and state within LangGraph
  • Getting started: Executing your first LangGraph application

State Management and Prompt Orchestration

  • Structuring prompts as discrete graph nodes
  • Managing state transfer between nodes and processing outputs effectively
  • Implementing memory patterns: distinguishing between short-term and persisted context

Conditional Branching, Control Flow, and Resilience

  • Implementing conditional routing and complex multi-path workflows
  • Configuring retries, timeouts, and robust fallback mechanisms
  • Ensuring idempotency and facilitating safe re-execution of tasks

Tool Integration and External Connectivity

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

Retrieval-Augmented Generation Workflows

  • Basics of document ingestion and efficient chunking strategies
  • Leveraging embeddings and vector stores (such as ChromaDB)
  • Generating grounded answers with accurate citations

Testing, Debugging, and Performance Evaluation

  • Implementing unit-style tests for individual nodes and workflow paths
  • Utilizing tracing tools to enhance observability
  • Conducting quality assurance checks for factuality, safety, and determinism

Packaging and Deployment Essentials

  • Configuring development environments and managing project dependencies
  • Exposing graph logic via API endpoints
  • Versioning workflows and executing rolling updates

Concluding Summary and Future Directions

Requirements

  • A solid grasp of basic Python programming principles
  • Practical experience interacting with REST APIs or command-line interface (CLI) tools
  • Working knowledge of LLM concepts and the fundamentals of prompt engineering

Intended Audience

  • Developers and software engineers newly exploring graph-based LLM orchestration techniques
  • Prompt engineers and AI specialists constructing complex, multi-step LLM applications
  • Data professionals investigating the automation of workflows using LLMs

Number of participants


Price per participant

Upcoming Courses

Related Categories