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
Overview of LangGraph and Graph Principles
- The rationale for using graphs in LLM applications: orchestration versus linear chains
- Core components: Nodes, edges, and state within LangGraph
- Getting started: Creating the first executable graph
State Management and Prompt Chaining
- Structuring prompts as graph nodes
- Transferring state between nodes and managing outputs
- Memory strategies: Distinguishing between short-term and persisted context
Branching, Control Flow, and Error Management
- Implementing conditional routing and multi-path workflows
- Managing retries, timeouts, and fallback mechanisms
- Ensuring idempotency for safe re-execution
Tool Utilization and External Integrations
- Executing function and tool calls from graph nodes
- Interacting with REST APIs and services within the graph structure
- Processing structured outputs
Retrieval-Augmented Workflows
- Basics of document ingestion and chunking
- Working with embeddings and vector stores (e.g., ChromaDB)
- Generating grounded answers with citations
Testing, Debugging, and Evaluation
- Writing unit-style tests for individual nodes and paths
- Implementing tracing and observability
- Quality assurance: Verifying factuality, safety, and determinism
Packaging and Deployment Basics
- Environment configuration and dependency management
- Serving graphs through API endpoints
- Workflow versioning and rolling updates
Conclusion and Future Directions
Requirements
- Proficiency in fundamental Python programming
- Hands-on experience with REST APIs or command-line interface (CLI) tools
- A solid grasp of LLM concepts and the fundamentals of prompt engineering
Target Audience
- Developers and software engineers seeking to explore graph-based LLM orchestration
- Prompt engineers and AI specialists developing multi-step LLM applications
- Data professionals investigating workflow automation using LLMs