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
- Rationale for using graphs in LLM applications: distinguishing orchestration from simple chains.
- Understanding nodes, edges, and state within LangGraph.
- Hello LangGraph: creating your first executable graph.
State Management and Prompt Chaining
- Structuring prompts as graph nodes.
- Transferring state between nodes and managing outputs.
- Memory patterns: distinguishing between short-term and persisted context.
Branching, Control Flow, and Error Handling
- Conditional routing and multi-path workflow design.
- Implementing retries, timeouts, and fallback strategies.
- Ensuring idempotency and safe re-execution.
Tools and External Integrations
- Function and tool calling mechanisms within graph nodes.
- Invoking REST APIs and external services inside the graph.
- Managing structured outputs.
Retrieval-Augmented Workflows
- Basics of document ingestion and chunking.
- Embeddings and vector stores (e.g., ChromaDB).
- Generating grounded answers with citations.
Testing, Debugging, and Evaluation
- Unit-style testing for nodes and execution paths.
- Tracing and observability techniques.
- Quality assurance: assessing factuality, safety, and determinism.
Packaging and Deployment Fundamentals
- Environment configuration and dependency management.
- Hosting graphs via APIs.
- Workflow versioning and rolling updates.
Summary and Next Steps
Requirements
- Foundational knowledge of Python programming.
- 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 practitioners developing multi-step LLM applications.
- Data professionals exploring workflow automation using LLMs.
14 Hours
