Get in Touch
 Duration 14 hours

Course Outline

Introduction to LangGraph and Graph Architectures

  • The rationale for using graphs in LLM applications: orchestration versus linear chains
  • Understanding nodes, edges, and state within the LangGraph ecosystem
  • Getting started with LangGraph: building and executing your first graph

State Management and Prompt Orchestration

  • Architecting prompts as individual graph nodes
  • Managing state transitions between nodes and processing outputs
  • Implementing memory strategies: distinguishing between short-term and persistent context

Conditional Branching, Control Flow, and Resilience

  • Implementing conditional routing and multi-path workflow logic
  • Configuring retries, timeouts, and fallback mechanisms
  • Ensuring idempotency and safe re-execution capabilities

Tool Integration and External Connectors

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

Retrieval-Augmented Generation Workflows

  • Foundations of document ingestion and text chunking
  • Utilizing embeddings and vector databases (such as ChromaDB)
  • Generating grounded responses with appropriate citations

Quality Assurance: Testing, Debugging, and Evaluation

  • Developing unit-style tests for individual nodes and workflow paths
  • Implementing tracing and observability practices
  • Enforcing quality standards: verifying factuality, safety, and determinism

Deployment and Packaging Essentials

  • Setting up development environments and managing dependencies
  • Exposing graph workflows via API endpoints
  • Managing workflow versioning and implementing rolling updates

Concluding Summary and Future Directions

Requirements

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

Target Audience

  • Software developers and engineers exploring graph-based LLM orchestration for the first time
  • Prompt engineers and AI specialists developing complex, multi-step LLM applications
  • Data practitioners investigating the automation of workflows using LLM technology

Upcoming Courses

Related Categories