There are 5 repositories under retrieval topic.
⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡
Study guides for MIT's 15.003 Data Science Tools
MTEB: Massive Text Embedding Benchmark
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.
Epsilla is a high performance Vector Database Management System. Try out hosted Epsilla at https://cloud.epsilla.com/
Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch
SGPT: GPT Sentence Embeddings for Semantic Search
The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
A realtime and indexing and structured extraction engine for Unstructured Data to build Generative AI Applications
My personal note about local and global descriptor
Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate nearest neighbors, in Pytorch
Grounded search engine (i.e. with source reference) based on LLM / ChatGPT / OpenAI API. It supports web search, file content search etc.
Use ArXiv ChatGuru to talk to research papers. This app uses LangChain, OpenAI, Streamlit, and Redis as a vector database/semantic cache.
Generative Representational Instruction Tuning
The official implementation of ICLR 2020, "Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering".
An easy to use Neural Search Engine. Index latent vectors along with JSON metadata and do efficient k-NN search.
A compute framework for turning multimodal data structures into vector embeddings, to improve quality and control when working with LLMs. Generate custom multimodal embeddings with ease and weigh the vector parts separately at query time, removing the need for custom re-ranking models. Deploy straight from notebook to production.
Deep Recommenders
Neural Search
Library for generating vector embeddings, reranking in Rust
Multi-modal Molecule Structure-text Model for Text-based Editing and Retrieval, Nat Mach Intell 2023 (https://www.nature.com/articles/s42256-023-00759-6)
libfmp - Python package for teaching and learning Fundamentals of Music Processing (FMP)
Story-Based Retrieval with Contextual Embeddings. Largest freely available movie video dataset. [ACCV'20]
Open-source RAG evaluation through users' feedback
Using efficientnet to provide embeddings for retrieval
Audio Synchronization and Analysis Tool