⚡ PDX: A Library for Fast Vector Search and Indexing on CPUs (x86, ARM) — for Python and C++. Index millions of vectors in seconds. Search them in milliseconds.
PaveDB is an inspectable retrieval database for AI applications: text-backed vector search with source provenance and query replay, embedded or over HTTP. Website: https://pavedb.org/
Flask-based web application designed for detecting objects in images and retrieving visually similar images from a dataset (2021)
Automated video advertisement content analysis system using Sentence Transformers and cosine similarity for yes/no question evaluation. Features text embedding with all-mpnet-base-v2, batch processing, vector indexing, and performance evaluation against human-coded ground truth data.
Local-RAG indexes selected project folders using a local embedding model storing chunked vectors in Weaviate. Enables coding agents to traverse a code graph and perform semantic queries against the codebase (supports Word, PDF and OCR)
Experimental framework for evaluating TiDB’s vector search capabilities with LangChain-based LLM retrieval workflows. Includes setup scripts, indexing pipelines, and retrieval benchmarks to test hybrid query performance and relevance scoring on TiDB’s vector database engine.
Milvus integration vector pipeline
Document intelligence & RAG engine. 7 API endpoints, FAISS vector indexing, semantic chunking, parallel LLM inference with VRAM monitoring. 24 docs/min throughput. Pub+sub NATS integration for bidirectional knowledge flow with Cerebro
Dependency-free Elixir client for PaveDB’s HTTP API, covering collections, text/file/vector ingestion, search, shared scope, query replay, documents, chunks, and health.
To associate your repository with the vector-indexing topic, visit your repo's landing page and select "manage topics."