Embeddings Python Packages

fastembed

Fast, Accurate, Lightweight Python library to make State of the Art Embedding

pytorch-metric-learning

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

model2vec

Fast State-of-the-Art Static Embeddings

daft

High-performance data engine for AI and multimodal workloads. Process images, audio, video, and structured data at any scale

tensorflow-hub

A library for transfer learning by reusing parts of TensorFlow models.

mteb

MTEB: State-of-the-art evaluation of embeddings across languages and modalities

flagembedding

Retrieval and Retrieval-augmented LLMs

vicinity

Lightweight Nearest Neighbors with Flexible Backends

adaptive-classifier

A flexible, adaptive classification system for dynamic text classification

lightly

A python library for self-supervised learning on images.

lightly-utils

A python library for self-supervised learning on images.

semble

Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read

esperanto

A unified interface for various AI model providers

vecs

Postgres/pgvector Python Client

navec

Compact high quality word embeddings for Russian language

natasha

Solves basic Russian NLP tasks, API for lower level Natasha projects

qianfan

Provide best practices for LMOps, as well as elegant and convenient access to the features of the Qianfan MaaS Platform. (提供大模型工具链最佳实践，以及优雅且便捷地访问千帆大模型平台）

instructorembedding

[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings

turbovec

A vector index built on TurboQuant, written in Rust with Python bindings

node2vec

Implementation of the node2vec algorithm.

polyfuzz

Fuzzy string matching, grouping, and evaluation.

nomic

Nomic Developer API SDK

slopo

Embedding-based discovery of duplicated logic for projects too large or messy to maintain reliably

abstractcore

Code once, run everywhere across Ollama, LM Studio, MLX, HuggingFace, vLLM, OpenAI, Anthropic, and more with consistent APIs for tools, structured output, streaming, media, prompt caching, and secure OpenAI-compatible gateway deployment.