faiss + Embeddings powered KPI classification system
-
Updated
Dec 5, 2025 - Jupyter Notebook
faiss + Embeddings powered KPI classification system
SQLite for Vectors - A fast, lightweight vector database built with C++ and HNSW (Hierarchical Navigable Small World) algorithm for approximate nearest neighbor search.
Real-time blockchain fraud detection using autonomous multi-agent AI swarms. Detect fraud in <2s with 150x faster vector search (HNSW), 84.8% accuracy, and 73% cost reduction. Features ERC-1155 trust scores, MCP integration, and reflexion learning.
A production-ready local RAG system. Features LaTeX/Table preservation, two-stage retrieval (Vector Search + Reranking), and grounded generation with Ollama.
Add a description, image, and links to the hnsw-index topic page so that developers can more easily learn about it.
To associate your repository with the hnsw-index topic, visit your repo's landing page and select "manage topics."