This is an end-to-end framework for managing, evaluating, and tracing Retrieval-Augmented Generation (RAG) pipelines using modern LLMOps practices. The project integrates LLMs, Phoenix, and LangChain tracing to monitor model performance, collect evaluation metrics, and streamline debugging and optimization of LLM apps.
nlp docker dockerfile phoenix docker-compose tracing phoenix-framework observability rag llmops rag-evaluation model-tracing
-
Updated
Nov 6, 2025 - Python