Advanced RAG with hybrid search, query classification, answer fusion, and self-correction
-
Updated
Jan 20, 2026 - Python
Advanced RAG with hybrid search, query classification, answer fusion, and self-correction
Production-ready RAG financial system with query classification, A/B testing, Streamlit dashboard, and comprehensive evaluation framework.
Query classification (complexity, keywords, SQL type) + schema ranking for RAG systems. Uses DistilBERT for query analysis and Sentence-BERT for table/column relevance. Filters 500 tables in 7ms.
Add a description, image, and links to the query-classification topic page so that developers can more easily learn about it.
To associate your repository with the query-classification topic, visit your repo's landing page and select "manage topics."