
Agentic Enterprise RAG
Reference ArchitectureAgentic RAG reference system using LangGraph orchestration, Weaviate hybrid retrieval, local/cloud LLM modes and a FastAPI backend.
Selected repositories
RAG systems, ML prototypes and evaluation frameworks. Each project is classified by its actual scope.

Agentic RAG reference system using LangGraph orchestration, Weaviate hybrid retrieval, local/cloud LLM modes and a FastAPI backend.

Predictive-maintenance prototype on simulated sensor data, with failure classification, RUL regression, Prefect workflows, FastAPI endpoints and a Dash demo.

Synthetic policy-evaluation framework with a custom PPO-style trainer, distribution-shift evaluation, threshold-based checkpoint judging and reproducibility controls.

RAG portfolio system with FAISS/BM25 hybrid retrieval, persistent Q&A memory, generated summary notes and evaluation utilities.

Recommendation-system prototype with FastAPI services, Kafka/Spark pipeline code, MLflow integration, Redis caching and observability/deployment examples.

Prototype research workflow with specialist components for data preparation, EDA, baseline ML comparison, evaluation summaries and templated reports.