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 Concepts
- The rationale for using graphs in LLM apps: orchestration versus simple chains.
- Understanding nodes, edges, and state within LangGraph.
- Hello LangGraph: Building the first executable graph.
State Management and Prompt Chaining
- Designing prompts as individual graph nodes.
- Managing state transfer between nodes and processing outputs.
- Memory patterns: distinguishing between short-term and persisted context.
Branching, Control Flow, and Error Handling
- Implementing conditional routing and multi-path workflows.
- Managing retries, timeouts, and fallback strategies.
- Ensuring idempotency and safe re-execution of processes.
Tools and External Integrations
- Executing function and tool calls from graph nodes.
- Interacting with REST APIs and external services within the graph structure.
- Handling structured data outputs effectively.
Retrieval-Augmented Workflows
- Basics of document ingestion and chunking.
- Utilizing embeddings and vector stores, such as ChromaDB.
- Generating grounded answers with appropriate citations.
Testing, Debugging, and Evaluation
- Implementing unit-style tests for individual nodes and execution paths.
- Establishing tracing and observability mechanisms.
- Conducting quality checks for factuality, safety, and determinism.
Packaging and Deployment Fundamentals
- Setting up environments and managing dependencies.
- Serving graph applications behind APIs.
- Versioning workflows and executing rolling updates.
Summary and Next Steps
Requirements
- A solid understanding of basic Python programming principles.
- Practical experience with REST APIs or Command-Line Interface (CLI) tools.
- Familiarity with LLM concepts and the fundamentals of prompt engineering.
Target Audience
- Developers and software engineers new to graph-based LLM orchestration.
- Prompt engineers and AI enthusiasts building multi-stage LLM applications.
- Data practitioners exploring workflow automation using LLMs.