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 case for graphs in LLM apps: Orchestration versus linear chains
- Understanding nodes, edges, and state within LangGraph
- Getting started: Executing your first functional graph
State Control and Prompt Sequencing
- Structuring prompts as distinct graph nodes
- Managing data flow between nodes and processing outputs
- Memory architectures: Comparing short-term vs. persistent context
Logic Branching, Flow Control, and Resilience
- Implementing conditional routing and multi-path operations
- Managing retries, timeouts, and fallback mechanisms
- Ensuring idempotency for safe re-execution
Tool Integration and External Connections
- Executing functions and tools from within graph nodes
- Interacting with REST APIs and external services inside the graph
- Processing and utilising structured data outputs
Retrieval-Augmented Generation (RAG) Workflows
- Basics of document ingestion and chunking strategies
- Utilising embeddings and vector databases (e.g., ChromaDB)
- Generating grounded responses with source citations
Quality Assurance: Testing, Debugging, and Evaluation
- Writing unit-style tests for individual nodes and execution paths
- Implementing tracing and observability features
- Performing quality assessments for factuality, safety, and determinism
Deployment and Packaging Basics
- Configuring environments and managing dependencies
- Exposing graph workflows via API endpoints
- Managing workflow versions and implementing rolling updates
Conclusion and Future Directions
Requirements
- Foundational knowledge of Python programming
- Practical experience with REST APIs or command-line interface tools
- Basic understanding of LLM principles and prompt engineering techniques
Target Audience
- Software developers and engineers exploring graph-based LLM orchestration for the first time
- Prompt engineers and emerging AI professionals building complex, multi-step LLM applications
- Data practitioners investigating workflow automation opportunities with large language models