towhee
Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.
- 3.5k
- Python
- Apache-2.0
- 2 y ago
Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.
A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for various file types through textract.
High-performance vector similarity library in Rust with Python bindings: Spearman, Kendall, distance correlation, Jensen-Shannon, Hoeffding's D, and bootstrapped confidence intervals
Program that lets you ask questions about your documents and audio or video files.
Score documents using embedding-vectors dot-product or cosine-similarity with ES Lucene engine
Vector Storage is a vector database that enables semantic similarity searches on text documents in the browser's local storage. It uses OpenAI embeddings to convert documents into vectors and allows searching for similar documents based on cosine similarity.
⚡ GUI for editing LLM vector embeddings. No more blind chunking. Upload content in any file extension, join and split chunks, edit metadata and embedding tokens + remove stop-words and punctuation with one click, add images, and download in .veml to share it with your team.
A client side vector search library that can embed, store, search, and cache vectors. Works on the browser and node. It outperforms OpenAI's text-embedding-ada-002 and is way faster than Pinecone and other VectorDBs.
RAG with langchain using Amazon Bedrock and Amazon OpenSearch
Vector Index Benchmark for Embeddings (VIBE) is an extensible benchmark for approximate nearest neighbor search methods, or vector indexes, using modern embedding datasets.
Vectory provides a collection of tools to track and compare embedding versions.
Two approaches to generating optimized embeddings in the Retrieval-Augmented Generation (RAG) Pattern
Proxy server for triton gRPC server that inferences embedding model in Rust
Local Vector Database coded in c# supports Cosine Similarity, Jaccard Dissimilarity as well as Euclidean , Manhattan, ChebyShev and Canberra distances
IntelliSearch is an advanced retrieval-based question-answering and recommendation system that leverages embeddings and a large language model (LLM) to provide accurate and relevant information to users.
Face-Based Attention Circuits (FBAC): A Theoretical Framework for Context-Aware Embeddings
This project is a work-in-progress and serves as an experiment for context injection with GPT and code embeddings. The goal is to use GPT to develop the remaining features of the project.
This repo contains code files and articles to help you learn and build beginner to advanced Generative AI applications.