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.
Course Outline
Overview of LangGraph and Graph Fundamentals
- Rationale for employing graph structures in large language model applications: orchestrating complex processes versus linear chains
- Core components: nodes, edges, and state management within LangGraph
- Initial implementation: creating the first executable graph
State Management and Sequential Prompting
- Structuring prompts as distinct graph nodes
- Transferring state between nodes and processing outputs
- Memory architectures: distinguishing short-term context from persistent storage
Control Flow, Branching Logic, and Error Resilience
- Conditional routing and execution of parallel or divergent workflows
- Strategies for retries, timeout handling, and operational fallbacks
- Ensuring idempotency and reliability during re-execution
Integration with External Tools and Services
- Utilizing function or tool calls within graph nodes
- Integrating REST APIs and external services into graph workflows
- Processing and managing structured data outputs
Retrieval-Augmented Generation Workflows
- Fundamentals of document ingestion and text chunking
- Implementation of embeddings and vector databases, such as ChromaDB
- Generating grounded responses with source citations
Testing, Debugging, and Quality Assurance
- Conducting unit-style testing for individual nodes and execution paths
- Monitoring system behavior through tracing and observability tools
- Evaluating output quality: verifying factuality, safety, and deterministic behavior
Deployment and Operational Readiness
- Configuring runtime environments and managing dependencies for government applications
- Deploying graph services via application programming interfaces (APIs)
- Managing workflow version control and executing rolling updates
Conclusion and Strategic Next Steps
Requirements
- Fundamental proficiency in Python programming languages
- Practical application of RESTful APIs or command-line interface utilities
- Conceptual knowledge of large language models and core principles of prompt engineering
Target Audience
- Software engineers and developers initiating work in graph-based orchestration of large language models
- Prompt specialists and artificial intelligence practitioners developing complex, multi-stage AI applications
- Data professionals investigating workflow automation capabilities utilizing large language models for government initiatives
14 Hours