Search Packages

flagembedding

Retrieval and Retrieval-augmented LLMs

bertopic

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

txtai

💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

sent2vec

How to encode sentences in a high-dimensional vector space, a.k.a., sentence embedding.

text2vec

text2vec, text to vector. 文本向量表征工具，把文本转化为向量矩阵，实现了Word2Vec、RankBM25、Sentence-BERT、CoSENT等文本表征、文本相似度计算模型，开箱即用。

encoderfile

Python bindings for encoderfile.

inltk

Natural Language Toolkit for Indian Languages (iNLTK)

vectordb

The Python VectorDB. Build your vector database from working as a library to scaling as a database in the cloud

xmnlp

xmnlp：提供中文分词, 词性标注, 命名体识别，情感分析，文本纠错，文本转拼音，文本摘要，偏旁部首，句子表征及文本相似度计算等功能

similar-sentences

Similar sentence Prediction with more accurate results with your dataset on top of pertained model. #BERT

jee-data-base

Tool to access and manage 14k+ jee main pyqs with semantic clustering

lm-cocktail

Retrieval and Retrieval-augmented LLMs

afterthoughts

Sentence-aware embeddings using late chunking with transformers.

pysentence-similarity

PySentence-Similarity is a tool designed to identify and find similarities between sentences and a base sentence, expressed as a percentage 📊.

simcse

[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821

easybert

A Dead Simple BERT API for Python and Java (https://github.com/google-research/bert)

deepse

**DeepSE**: **Sentence Embeddings** based on Deep Nerual Networks, designed for **PRODUCTION** enviroment!

c-mteb

Retrieval and Retrieval-augmented LLMs

simplests

Unsupervised models for Semantic Textual Similarity

smiles-featurizers

Extract Molecular SMILES embeddings from language models pre-trained with various objectives architectures.

sentence-similarity

Package to calculate the similarity score between two sentences

opposite-score

A lightweight toolkit for measuring how “opposite” two texts are when they share the same context.

wisse-sentence

A sentence embedding method based on weighted series

commitmind

CommitMind: Semantic search for Git commit history powered by TurboQuant vector compression (ICLR 2026). Search commits by meaning, not just keywords.