Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for various file types through textract.

A Python vector database you just need - no more, no less.

A curated list of awesome works related to high dimensional structure/vector search & database

VQLite - Simple and Lightweight Vector Search Engine based on Google ScaNN

langchain-chat is an AI-driven Q&A system that leverages OpenAI's GPT-4 model and FAISS for efficient document indexing. It loads and splits documents from websites or PDFs, remembers conversations, and provides accurate, context-aware answers based on the indexed data. Easy to set up and extend.

The ChatGPT Long Term Memory package is a powerful tool designed to empower your projects with the ability to handle a large number of simultaneous users and external sources.

A pure Python-implemented, lightweight, server-optional, multi-end compatible, vector database deployable locally or remotely.

Cottontail DB is a column store vector database aimed at multimedia retrieval. It allows for classical boolean as well as vector-space retrieval (nearest neighbour search) used in similarity search using a unified data and query model.

Serverless, lightweight, and fast vector database on top of DynamoDB

Vector Embedding Server in under 100 lines of code

Shotit is a screenshot-to-video search engine tailored for TV & Film, blazing-fast and compute-efficient.

Sinapsis repo with templates for face detection, face recognition and face verification

langchain-chat is an AI-driven Q&A system that leverages OpenAI's GPT-4 model and FAISS for efficient document indexing. It loads and splits documents from websites or PDFs, remembers conversations, and provides accurate, context-aware answers based on the indexed data. Easy to set up and extend.

The ultimate brain of Shotit, in charge of task coordination.

Unsupervised Video Summarization via Successor Embeddings

Four core workers of shotit: watcher, hasher, loader and searcher.

Provide meta information and utility for shotit, for example, image proxy, cast and poster etc.

Media broker for serving video preview for shotit

The frontend of shotit, with full documentation.