There are 2 repositories under embedding-similarity topic.
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 curated list of awesome works related to high dimensional structure/vector search & database
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.
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.
Vector Embedding Server in under 100 lines of code
Serverless, lightweight, and fast vector database on top of DynamoDB
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.
The frontend of shotit, with full documentation.
Media broker for serving video preview for shotit
Provide meta information and utility for shotit, for example, image proxy, cast and poster etc.
Sort the search results of Shotit to increase the correctness of Top1 result by using Keras and Faiss.
Search for code by what it does in natural language, using machine learning embeddings.
"if-then-else" over topics made up of free-form sentences. Build conversations, not LLM chains!