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
LangGraph and Agent Patterns: A Practical Introduction
- Comparing graphs with linear chains: use cases and benefits.
- Understanding agents, tools, and planner-executor cycles.
- Creating a basic agentic graph workflow.
State Management, Memory, and Context Transfer
- Structuring graph state and defining node interfaces.
- Differentiating between short-term and persistent memory.
- Managing context windows through summarization and data rehydration.
Branching Logic and Execution Control
- Implementing conditional routing and multi-path decision making.
- Incorporating retries, timeout management, and circuit breakers.
- Handling fallbacks, dead-ends, and recovery nodes.
Tool Utilization and External Integration
- Executing function and tool calls from graph nodes and agents.
- Accessing REST APIs and databases directly within the graph structure.
- Parsing and validating structured output data.
Retrieval-Augmented Agent Processes
- Techniques for document ingestion and chunking.
- Utilizing embeddings and vector stores, specifically with ChromaDB.
- Generating grounded responses with citations and safety measures.
Evaluation, Debugging, and System Observability
- Tracing execution paths and analyzing node interactions.
- Using golden sets, evaluation metrics, and regression testing.
- Monitoring quality, safety, cost, and latency.
Packaging and Deployment
- Implementing FastAPI serving and managing dependencies.
- Versioning graph structures and developing rollback strategies.
- Establishing operational playbooks and incident response protocols.
Conclusion and Future Directions
Requirements
- Solid proficiency in Python.
- Hands-on experience with building LLM applications or managing prompt chains.
- Working understanding of REST APIs and JSON data formats.
Target Audience
- AI Engineers.
- Product Managers.
- Developers focused on creating interactive, LLM-driven systems.