Calling LLM APIs
Production patterns for calling LLM APIs - authentication, retry logic, rate limiting, error handling, async calls, and the Anthropic and OpenAI Python SDKs.
Production patterns for calling LLM APIs - authentication, retry logic, rate limiting, error handling, async calls, and the Anthropic and OpenAI Python SDKs.
Circuit breakers, retries, bulkheads, timeouts, service discovery, and observability - resilience patterns for Python microservices.