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 versus linear chains: identifying the optimal use cases and reasons.
- Understanding agents, tools, and planner-executor loops.
- Getting started: constructing a minimal agentic graph workflow.
Managing State, Memory, and Context
- Defining graph state structures and node interfaces.
- Differentiating between short-term memory and long-term persisted memory.
- Optimizing context windows through summarization and rehydration techniques.
Branching Logic and Control Flow Mechanisms
- Implementing conditional routing and complex multi-path decision making.
- Configuring retries, timeouts, and circuit breaker patterns.
- Establishing fallbacks, handling dead-ends, and designing recovery nodes.
Tool Utilization and External System Integration
- Executing function and tool calls directly from nodes and agents.
- Interacting with REST APIs and databases within the graph structure.
- Parsing and validating structured outputs for accuracy.
Retrieval-Augmented Agent Workflows
- Strategies for document ingestion and effective chunking.
- Utilizing embeddings and vector stores such as ChromaDB.
- Generating grounded responses with citations and built-in safeguards.
Evaluation, Debugging, and System Observability
- Tracing execution paths and analyzing node interactions.
- Creating golden sets, conducting evaluations, and running regression tests.
- Monitoring quality, safety, cost, and latency metrics.
Packaging and Deployment Strategies
- Serving applications via FastAPI and managing dependencies.
- Versioning graph structures and implementing rollback strategies.
- Developing operational playbooks and incident response protocols.
Conclusion and Future Directions
Requirements
- A solid working proficiency in Python.
- Practical experience in developing LLM applications or managing prompt chains.
- Comfort with REST APIs and handling JSON data structures.
Target Audience
- AI Engineers
- Product Managers
- Developers specializing in interactive LLM-driven systems