# Vector Search

Pensieve is a privacy-focused passive recording project that automatically records screen content, builds intelligent indexes, and provides a convenient web interface for retrieving historical data. Inspired by Rewind and Windows Recall, Pensieve differentiates itself by allowing users complete control over their data, avoiding transmission to untrusted data centers. Key advantages of Pensieve include easy installation, complete data control, support for full-text and vector searches, integration with Ollama, compatibility with any OpenAI API model, support for both Mac and Windows (with Linux support in development), and extensibility via plugins.

kelindar/search is a Go language library that provides functionality for embedded vector search and semantic embeddings, built on llama.cpp. This library is particularly suitable for small to medium-sized projects that require powerful semantic search capabilities while maintaining a simple and efficient implementation. It supports GGUF BERT models, allowing users to leverage advanced embedding techniques without delving into the complexities of traditional search systems. The library also offers GPU acceleration for fast computations on supported hardware. If your dataset contains fewer than 100,000 entries, this library can be easily integrated into your Go application to implement semantic search features.

The Concept Stock Finder is an online tool based on natural language processing and vector search technology that semantically matches users' input descriptions to quickly find related stocks of publicly listed companies in China's A-share market. The main advantage of this product lies in its innovative search method, which can handle various forms of input such as images, concepts, and keywords, providing users with a new stock searching experience. Background information indicates that its purpose is to help users quickly obtain relevant information during investment decisions, but please note that the search results are for reference only and do not constitute investment advice.

DiscovAI-search is an AI technology-based search engine designed for AI tools and customized data. It utilizes vector search technology to convert user queries into vectors for precise similarity matching. With Redis caching technology, it significantly improves response time for repeated queries. Additionally, it features a comprehensive database of AI products spanning various categories and industries. Powered by large language models (LLM), it provides detailed, context-aware answers based on search results. The user-friendly interface is designed for easy navigation, helping users efficiently discover AI products.

Korvus is a search SDK built on Postgres, unifying the entire RAG (Retrieval Augmented Generation) process into a single database query. It offers high-performance, customizable search capabilities while minimizing infrastructure concerns. Korvus leverages PostgresML's pgml and pgvector extensions, compressing the RAG workflow within Postgres itself. It supports multi-language SDKs, including Python, JavaScript, Rust, and C, allowing developers to seamlessly integrate into existing technology stacks.

SemaDB is a vector search tool powered by Firebase, enabling users to perform fast and efficient vector searches. It boasts high accuracy and wide applicability across diverse fields. Pricing for SemaDB is usage-based, for detailed information, please visit the official website.

A2O Corpus is a generative AI chatbot solution that leverages the powerful capabilities of large language models (LLMs) to integrate your content (documents, websites, etc.) with chatbots, enabling easy, conversational responses to user queries. It also offers robust vector search functionality, quickly locating key information within your enterprise data and formulating answers.

AlloyDB AI is a database service introduced by Google Cloud that assists developers in building generative AI applications on top of PostgreSQL. It offers a familiar PostgreSQL interface, supports vector and model management, and can deeply integrate Google Vertex AI for easy access to various generative AI models. AlloyDB AI features enterprise-grade scalability, availability, and security, enabling ultra-high-performance vector operations, making it an ideal choice for building generative AI applications on PostgreSQL.

Qdrant is an open-source vector search database and search engine, written in Rust. It offers rapid and scalable vector similarity search services, accompanied by convenient APIs. Qdrant can integrate with any system and serves as the foundation for advanced and high-performance vector similarity search technology in the next generation of AI applications. It is a cloud-native vector database, capable of horizontal scaling, resource-efficient, and fully developed using the Rust programming language. Qdrant can address various business scenarios such as recommendation systems, semantic search, similar product discovery, fraud detection systems, and talent matching.

Embedditor is an open-source embedding tool that helps you maximize your performance in vector search. It improves embedding metadata and embedding tokens through a user-friendly interface. Seamlessly apply advanced NLP cleaning techniques like TF-IDF, normalization, and enrich your embedding tokens, boosting efficiency and accuracy in LLM-related applications. It also allows for intelligent content splitting or merging, adding blank or hidden tokens based on its structure to enhance semantic consistency and optimize the relevance of retrieved content from vector databases. You have complete control over your data, allowing you to easily deploy Embedditor on your PC or in private enterprise cloud or on-premise environments. By applying Embedditor's advanced cleaning techniques, filter out irrelevant embedding tokens such as stop words, punctuation, and low-relevance frequent words, you can save up to 40% on embedding and vector storage costs while achieving better search results.