Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Duration 14 hours
Course Outline
Foundations of LangGraph and Graph Theory
- The role of graphs in LLM applications: orchestration versus linear chains
- Core components: nodes, edges, and state in LangGraph
- Getting started: executing the first LangGraph instance
State Control and Prompt Sequencing
- Structuring prompts as individual graph nodes
- Managing state transfer between nodes and processing outputs
- Memory strategies: differentiating between temporary and persistent context
Branching Logic, Control Flows, and Error Management
- Implementing conditional routing and complex multi-path workflows
- Configuring retries, timeouts, and fallback mechanisms
- Ensuring idempotency and safe re-execution
Tool Usage and External Integrations
- Executing function and tool calls from graph nodes
- Interacting with REST APIs and services within the graph structure
- Handling structured output formats
Retrieval-Augmented Generation Workflows
- Basics of document ingestion and chunking
- Utilizing embeddings and vector databases (e.g., ChromaDB)
- Generating grounded responses with proper citations
Testing, Debugging, and Assessment
- Implementing unit-style tests for nodes and pathways
- Enhancing tracing and system observability
- Quality assurance: verifying factuality, safety, and determinism
Packaging and Deployment Basics
- Configuring environments and managing dependencies
- Exposing graphs via API endpoints
- Managing workflow versions and executing rolling updates
Wrap-up and Future Directions
Requirements
- Proficiency in fundamental Python programming
- Practical experience with REST APIs or command-line tools
- Basic knowledge of LLM principles and prompt engineering techniques
Target Audience
- Software engineers and developers new to graph-based LLM orchestration
- Prompt engineers and emerging AI specialists developing multi-step LLM applications
- Data professionals investigating workflow automation via LLMs