A production-grade, local-first RAG & LLMOps pipeline for enterprise-grade AI. Features automated document ingestion (Airflow), vector storage (Qdrant), and hallucination guardrails (RAGAS). Demonstrates end-to-end observability and model lifecycle management.
machine-learning airflow ai grafana prometheus rag mlflow fastapi qdrant llmops mlobservability llama3 ai-infrastructure
-
Updated
Apr 7, 2026 - Python