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
Introduction to LangGraph and Graph Principles
- The rationale for using graphs in LLM applications: orchestrating complex tasks versus simple chains
- Understanding nodes, edges, and state within LangGraph
- Initial setup: executing a basic LangGraph example
State Management and Prompt Chaining
- Structuring prompts as individual graph nodes
- Transmitting state across nodes and managing output data
- Implementing memory strategies: distinguishing between short-term and persistent context
Branching, Control Flow, and Error Management
- Designing conditional routing and multi-path workflows
- Configuring retries, timeouts, and fallback mechanisms
- Ensuring idempotency and enabling safe re-execution
Tools and External Integrations
- Implementing function and tool calls from graph nodes
- Interacting with REST APIs and external services within the graph structure
- Processing structured output formats
Retrieval-Augmented Workflows
- Fundamentals of document ingestion and chunking
- Utilizing embeddings and vector stores, such as ChromaDB
- Generating grounded responses with proper citations
Testing, Debugging, and Evaluation
- Writing unit-style tests for specific nodes and execution paths
- Implementing tracing and observability features
- Conducting quality assessments focused on factuality, safety, and determinism
Deployment and Packaging Essentials
- Setting up environments and managing dependencies
- Exposing graph applications via API endpoints
- Handling workflow versioning and rolling updates
Conclusion and Future Directions
Requirements
- Foundational knowledge of Python programming
- Hands-on experience with REST APIs or command-line interface tools
- A working understanding 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 multi-step LLM applications
- Data practitioners looking to implement LLM-based workflow automation