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
- The rationale for using graphs in LLM applications: orchestration versus simple chains.
- Understanding nodes, edges, and state within LangGraph.
- Hello LangGraph: creating the first runnable graph.
State Management and Prompt Chaining
- Designing prompts as graph nodes.
- Transmitting 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 workflows.
- Strategies for retries, timeouts, and fallbacks.
- Ensuring idempotency and enabling safe re-runs.
Tools and External Integrations
- Function and tool calling from graph nodes.
- Invoking REST APIs and services within the graph.
- Working with structured outputs.
Retrieval-Augmented Workflows
- Basics of document ingestion and chunking.
- Embeddings and vector stores (e.g., ChromaDB).
- Grounded answering techniques with citations.
Testing, Debugging, and Evaluation
- Unit-style tests for nodes and paths.
- Tracing and observability features.
- Quality checks focusing on factuality, safety, and determinism.
Packaging and Deployment Fundamentals
- Environment setup and dependency management.
- Serving graphs behind APIs.
- Versioning workflows and implementing rolling updates.
Summary and Next Steps
Requirements
- A foundational understanding of Python programming.
- Experience with REST APIs or CLI tools.
- Familiarity with LLM concepts and the fundamentals of prompt engineering.
Audience
- Developers and software engineers new to graph-based LLM orchestration.
- Prompt engineers and AI beginners working on multi-step LLM applications.
- Data practitioners investigating workflow automation with LLMs.
14 Hours
