Kurzusleírás

Advanced LangGraph Architecture

  • Graph topology patterns: nodes, edges, routers, subgraphs
  • State modeling: channels, message passing, persistence
  • DAG vs cyclic flows and hierarchical composition

Performance and Optimization

  • Parallelism and concurrency patterns in Python
  • Caching, batching, tool calling, and streaming
  • Cost controls and token budgeting strategies

Reliability Engineering

  • Retries, timeouts, backoff, and circuit breaking
  • Idempotency and deduplication of steps
  • Checkpointing and recovery using local or cloud stores

Complex Graphs Debugging

  • Step-through execution and dry runs
  • State inspection and event tracing
  • Reproducing production issues with seeds and fixtures

Observability and Monitoring

  • Structured logging and distributed tracing
  • Operational metrics: latency, reliability, token usage
  • Dashboards, alerts, and SLO tracking

Deployment and Operations

  • Packaging graphs as services and containers
  • Configuration management and secrets handling
  • CI/CD pipelines, rollouts, and canaries

Quality, Testing, and Safety

  • Unit, scenario, and automated eval harnesses
  • Guardrails, content filtering, and PII handling
  • Red teaming and chaos experiments for robustness

Summary and Next Steps

Követelmények

  • Python és aszinkron programozás ismerete
  • Tapasztalat LLM alkalmazás-fejlesztésben
  • Ismeret alapvető LangGraph vagy LangChain koncepciókról

A célközönség

  • AI platform mérnökök
  • DevOps AI-rendszerek számára
  • ML architektok, akik LangGraph rendszereket üzemeltetnek
 35 Órák

Résztvevők száma


Ár résztvevőnként

Közelgő kurzusok

Rokon kategóriák