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
Introduction to LangGraph and Graph Concepts
- Why graphs for LLM applications: orchestration versus simple chains
- Nodes, edges, and state in LangGraph
- Hello LangGraph: creating the first executable graph
State Management and Prompt Chaining
- Designing prompts as graph nodes for government use
- Passing state between nodes and managing outputs
- Memory patterns: short-term versus persisted context
Branching, Control Flow, and Error Handling
- Conditional routing and multi-path workflows for government applications
- Retries, timeouts, and fallback strategies in government processes
- Idempotency and safe re-runs for government operations
Tools and External Integrations
- Function/tool invocation from graph nodes
- Calling REST APIs and services within the graph for government systems
- Working with structured outputs in a government context
Retrieval-Augmented Workflows
- Document ingestion and chunking basics for government documents
- Embeddings and vector stores (e.g., ChromaDB) for government data
- Grounded answering with citations in government reports
Testing, Debugging, and Evaluation
- Unit-style tests for nodes and paths to ensure reliability for government
- Tracing and observability for enhanced transparency in government operations
- Quality checks: factuality, safety, and determinism in government applications
Packaging and Deployment Fundamentals
- Environment setup and dependency management for government systems
- Serving graphs behind APIs for government services
- Versioning workflows and rolling updates for continuous improvement in government operations
Summary and Next Steps
Requirements
- An understanding of fundamental Python programming
- Experience with REST APIs or command-line interface (CLI) tools
- Familiarity with large language model (LLM) concepts and prompt engineering basics
Audience for Government
- Developers and software engineers new to graph-based LLM orchestration in public sector applications
- Prompt engineers and AI professionals building multi-step LLM applications for government use
- Data practitioners exploring workflow automation with LLMs for government operations
14 Hours
