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-Theoretic Concepts
- The rationale for using graphs in LLM applications: orchestration versus simple sequential chains
- Understanding nodes, edges, and state within LangGraph
- Getting started with LangGraph: creating the first executable graph
State Management and Prompt Sequencing
- Architecting prompts as discrete graph nodes
- Transferring state between nodes and managing output data
- Memory architectures: distinguishing between short-term and persisted context
Conditional Branching, Control Flow, and Exception Handling
- Implementing conditional routing and multi-path process flows
- Managing retries, timeouts, and fallback mechanisms
- Ensuring idempotency and safe re-execution of tasks
Tool Usage and External System Integration
- Invoking functions and tools from within graph nodes
- Integrating REST APIs and external services into the graph structure
- Processing and utilizing structured data outputs
Retrieval-Augmented Generation (RAG) Workflows
- Basics of document ingestion and text chunking
- Utilizing embeddings and vector databases (e.g., ChromaDB)
- Generating grounded responses with source citations
Quality Assurance: Testing, Debugging, and Assessment
- Developing unit-style tests for individual nodes and workflow paths
- Implementing tracing and observability tools
- Performing quality checks for factual accuracy, safety, and determinism
Deployment Essentials: Packaging and Distribution
- Configuring development environments and managing dependencies
- Exposing graph workflows via API endpoints
- Managing workflow versioning and implementing rolling updates
Conclusions and Future Directions
Requirements
- Fundamental proficiency in Python programming
- Practical experience with REST APIs or command-line interface (CLI) tools
- Basic knowledge of LLM concepts and core prompt engineering principles
Target Audience
- Developers and software engineers exploring graph-based LLM orchestration
- Prompt engineers and AI specialists developing complex, multi-step LLM applications
- Data professionals investigating workflow automation using LLMs