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 Primer
- Graphs vs. linear chains: understanding when and why to use each.
- Exploring agents, tools, and planner-executor loop architectures.
- Hello workflow: building a minimal agentic graph.
State, Memory, and Context Passing
- Defining graph states and designing node interfaces.
- Distinguishing between short-term memory and persisted storage.
- Managing context windows, including summarization and rehydration techniques.
Branching Logic and Control Flow
- Implementing conditional routing and multi-path decision-making.
- Configuring retries, timeouts, and circuit breaker patterns.
- Handling fallbacks, dead-ends, and designing recovery nodes.
Tool Use and External Integrations
- Executing function/tool calls from graph nodes and agents.
- Connecting the graph to REST APIs and database resources.
- Parsing and validating structured outputs.
Retrieval-Augmented Agent Workflows
- Strategies for document ingestion and text chunking.
- Utilizing embeddings and vector stores, specifically with ChromaDB.
- Generating grounded responses with proper citations and safety safeguards.
Evaluation, Debugging, and Observability
- Tracing execution paths and inspecting node interactions.
- Using golden sets, evaluations, and regression testing for quality assurance.
- Monitoring quality, safety, cost efficiency, and latency metrics.
Packaging and Delivery
- Serving applications via FastAPI and managing dependencies.
- Versioning graphs and establishing rollback strategies.
- Developing operational playbooks and incident response protocols.
Summary and Next Steps
Requirements
- Proficiency in Python programming.
- Hands-on experience developing LLM applications or prompt chains.
- Comfortable working with REST APIs and JSON data structures.
Target Audience
- AI Engineers
- Product Managers
- Developers focused on building interactive, LLM-driven systems.