Get in Touch
 Duration 14 hours

Course Outline

Introduction to LangGraph and Graph-Based Concepts

  • The rationale for using graphs in LLM apps: orchestration compared to simple chains
  • Understanding nodes, edges, and state within LangGraph
  • Hello LangGraph: creating your first executable graph

State Management and Prompt Chaining

  • Designing prompts as distinct graph nodes
  • Transferring state between nodes and processing outputs
  • Memory strategies: distinguishing between short-term and persistent context

Branching, Control Flow, and Error Management

  • Implementing conditional routing and multi-path workflows
  • Managing retries, timeouts, and fallback mechanisms
  • Ensuring idempotency and safe re-execution

Tools and External Integrations

  • Executing function and tool calls from graph nodes
  • Invoking REST APIs and services within the graph structure
  • Handling structured outputs effectively

Retrieval-Augmented Workflows

  • Basics of document ingestion and chunking
  • Utilizing embeddings and vector stores (e.g., ChromaDB)
  • Providing grounded answers with citations

Testing, Debugging, and Evaluation

  • Writing unit-style tests for individual nodes and paths
  • Implementing tracing and observability
  • Conducting quality checks for factuality, safety, and determinism

Foundations of Packaging and Deployment

  • Setting up environments and managing dependencies
  • Serving graphs via APIs
  • Versioning workflows and executing rolling updates

Conclusion and Next Steps

Requirements

  • A solid grasp of basic Python programming
  • Practical experience with REST APIs or command-line tools
  • Acquaintance with LLM concepts and the fundamentals of prompt engineering

Target Audience

  • Developers and software engineers beginning their journey with graph-based LLM orchestration
  • Prompt engineers and AI practitioners building multi-step LLM applications
  • Data professionals exploring workflow automation using LLMs

Upcoming Courses

Related Categories