Get in Touch
 Duration 14 hours

Course Outline

LangGraph and Agent Architectures: A Practical Foundation

  • Comparing graphs and linear chains: identifying optimal use cases
  • Understanding agents, tools, and planner-executor patterns
  • Creating a basic agentic graph: your first workflow

Managing State, Memory, and Context

  • Structuring graph state and defining node interfaces
  • Distinguishing between short-term and persistent memory
  • Handling context windows, summarization, and state restoration

Implementing Branching Logic and Control Flow

  • Establishing conditional routing and multi-path decision making
  • Applying retries, timeouts, and circuit breaker patterns
  • Managing fallbacks, dead-ends, and recovery mechanisms

Leveraging Tools and External Integrations

  • Executing function and tool calls from nodes and agents
  • Interacting with REST APIs and databases via the graph
  • Parsing and validating structured outputs

Building Retrieval-Augmented Agent Workflows

  • Strategies for document ingestion and chunking
  • Utilizing embeddings and vector stores with ChromaDB
  • Generating grounded responses with citations and safety measures

Evaluating, Debugging, and Ensuring Observability

  • Tracing execution paths and analyzing node interactions
  • Creating golden sets, evaluations, and regression tests
  • Monitoring quality, safety, and performance metrics

Packaging and Deployment

  • Serving applications with FastAPI and managing dependencies
  • Version control for graphs and rollback procedures
  • Developing operational playbooks and incident response plans

Summary and Future Directions

Requirements

  • Solid proficiency in Python
  • Practical experience in developing LLM applications or prompt chains
  • Proficiency with REST APIs and JSON formats

Target Audience

  • AI Engineers
  • Product Managers
  • Developers specializing in interactive LLM-driven solutions

Related Categories