A reliability layer for LLM API calls: retries with backoff, rate limiting, Pydantic-validated outputs, and correlation-ID logging — tested against mocked responses. Provider-agnostic (OpenAI, Anthropic, Groq). The shared backbone every downstream project in this portfolio imports.
python api build pytest openai asyncio twine structlog pydantic groq httpx pytest-asyncio tenacity llm anthropic aiolimiter pythondotenv
-
Updated
Sep 23, 2026 - Python