Embeddings
neuml/txtai🔥 active
▲ +272 ★ this week
💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
🔍 Search & Retrieval🤖 Language Models🧠 Natural Language Processing
PythonApache-2.0updated Nov 11, 2026
🔥 Trending this week in Embeddings
Embeddings
srbhr/Resume-Matcher🔥 active
▲ +122 ★ this week
The #1 AI Harness for Building Resumes, PDFs, Cover Letters & more, locally with 100+ LLMs support.
🔍 Search & Retrieval🧠 Natural Language Processing
PythonApache-2.0updated Nov 11, 2026
Embeddings
MaartenGr/BERTopic🔥 active
▲ +26 ★ this week
Leveraging BERT and c-TF-IDF to create easily interpretable topics.
🫧 Topic Modeling🧠 Natural Language Processing
PythonMITupdated Nov 5, 2026
Embeddings
FlagOpen/FlagEmbedding
▲ +20 ★ this week
Retrieval and Retrieval-augmented LLMs
🔍 Search & Retrieval
PythonMITupdated Oct 27, 2026
Embeddings
embeddings-benchmark/mteb🔥 active
▲ +12 ★ this week
MTEB: State-of-the-art evaluation of embeddings across languages and modalities
🔍 Search & Retrieval🗂️ Text Classification
PythonApache-2.0updated Nov 12, 2026
Embeddings
MinishLab/model2vec🔥 active
▲ +8 ★ this week
Fast State-of-the-Art Static Embeddings
🧠 Natural Language Processing
PythonMITupdated Nov 11, 2026
Top 30 text embedding models and libraries by stars
Embeddings🥇#1
srbhr/Resume-Matcher🔥 active
▲ +122 ★ this week
The #1 AI Harness for Building Resumes, PDFs, Cover Letters & more, locally with 100+ LLMs support.
🔍 Search & Retrieval🧠 Natural Language Processing
PythonApache-2.0updated Nov 11, 2026
Embeddings🥈#2
piskvorky/gensim
▲ +4 ★ this week
Topic Modelling for Humans
🧠 Natural Language Processing🫧 Topic Modeling🔍 Search & Retrieval
PythonLGPL-2.1updated Nov 1, 2025
Embeddings🥉#3
ddbourgin/numpy-ml
▲ +2 ★ this week
Machine learning, in numpy
🫧 Topic Modeling
PythonGPL-3.0updated Oct 29, 2023
Embeddings#4
flairNLP/flair
▲ +3 ★ this week
A very simple framework for state-of-the-art Natural Language Processing (NLP)
🧠 Natural Language Processing🏷️ Named Entity Recognition
PythonOtherupdated Oct 19, 2026
Embeddings#5
neuml/txtai🔥 active
▲ +272 ★ this week
💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
🔍 Search & Retrieval🤖 Language Models🧠 Natural Language Processing
PythonApache-2.0updated Nov 11, 2026
Embeddings#6
FlagOpen/FlagEmbedding
▲ +20 ★ this week
Retrieval and Retrieval-augmented LLMs
🔍 Search & Retrieval
PythonMITupdated Oct 27, 2026
Embeddings#7
Embedding/Chinese-Word-Vectors
▲ +1 ★ this week
100+ Chinese Word Vectors 上百种预训练中文词向量
PythonApache-2.0updated Oct 30, 2023
Embeddings#8
brightmart/nlp_chinese_corpus
▲ +2 ★ this week
大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP
🧠 Natural Language Processing🗂️ Text Classification❓ Question Answering🤖 Language Models
OtherMITupdated Feb 6, 2026
Embeddings#9
MaartenGr/BERTopic🔥 active
▲ +26 ★ this week
Leveraging BERT and c-TF-IDF to create easily interpretable topics.
🫧 Topic Modeling🧠 Natural Language Processing
PythonMITupdated Nov 5, 2026
Embeddings#10
OpenBMB/UltraRAG🔥 active
A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
🔍 Search & Retrieval
PythonApache-2.0updated Nov 12, 2026
Embeddings#11
vi3k6i5/flashtext
Extract Keywords from sentence or Replace keywords in sentences.
⛏️ Information Extraction🧠 Natural Language Processing
PythonMITupdated Apr 13, 2025
Embeddings#12
shibing624/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。
🔍 Search & Retrieval🧠 Natural Language Processing
PythonApache-2.0updated Feb 14, 2026
Embeddings#13
bentrevett/pytorch-sentiment-analysis
Tutorials on getting started with PyTorch and TorchText for sentiment analysis.
🧠 Natural Language Processing💖 Sentiment Analysis
Jupyter NotebookMITupdated Mar 27, 2024
Embeddings#14
PaddlePaddle/PaddleRec
▲ +1 ★ this week
Recommendation Algorithm大规模推荐算法库，包含推荐系统经典及最新算法LR、Wide&Deep、DSSM、TDM、MIND、Word2Vec、Bert4Rec、DeepWalk、SSR、AITM，DSIN，SIGN，IPREC、GRU4Rec、Youtube_dnn、NCF、GNN、FM、FFM、DeepFM、DCN、DIN、DIEN、DLRM、MMOE、PLE、ESMM、ESCMM, MAML、xDeepFM、DeepFEFM、NFM、AFM、RALM、DMR、GateNet、NAML、DIFM、Deep Crossing、PNN、BST、AutoInt、FGCNN、FLEN、Fibinet、ListWise、DeepRec、ENSFM，TiSAS，AutoFIS等，包含经典推荐系统数据集criteo 、movielens等
PythonApache-2.0updated Apr 2, 2025
Embeddings#15
princeton-nlp/SimCSE
[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
🧠 Natural Language Processing
PythonMITupdated Oct 27, 2026
Embeddings#16
alibaba/Alink
Alink is the Machine Learning algorithm platform based on Flink, developed by the PAI team of Alibaba computing platform.
JavaApache-2.0updated Jun 7, 2024
Embeddings#17
embeddings-benchmark/mteb🔥 active
▲ +12 ★ this week
MTEB: State-of-the-art evaluation of embeddings across languages and modalities
🔍 Search & Retrieval🗂️ Text Classification
PythonApache-2.0updated Nov 12, 2026
Embeddings#18
ddangelov/Top2Vec
▲ +1 ★ this week
Top2Vec learns jointly embedded topic, document and word vectors.
🫧 Topic Modeling🔍 Search & Retrieval🧠 Natural Language Processing
PythonBSD-3-Clauseupdated Nov 14, 2024
Embeddings#19
michaelfeil/infinity🔥 active
Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali
C++MITupdated Nov 11, 2026
Embeddings#20
jbesomi/texthero
Text preprocessing, representation and visualization from zero to hero.
✂️ Tokenization & Preprocessing🧠 Natural Language Processing💎 Text Mining
PythonMITupdated Aug 29, 2023
Embeddings#21
huggingface/setfit🔥 active
▲ +4 ★ this week
Efficient few-shot learning with Sentence Transformers
🧠 Natural Language Processing
Jupyter NotebookApache-2.0updated Nov 10, 2026
Embeddings#22
Embeddings#23
JasonKessler/scattertext
▲ +2 ★ this week
Beautiful visualizations of how language differs among document types.
🧠 Natural Language Processing🫧 Topic Modeling💎 Text Mining
PythonApache-2.0updated Jul 4, 2026
Embeddings#24
beir-cellar/beir
▲ +5 ★ this week
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.
🔍 Search & Retrieval🧠 Natural Language Processing
PythonApache-2.0updated Oct 16, 2025
Embeddings#25
MinishLab/model2vec🔥 active
▲ +8 ★ this week
Fast State-of-the-Art Static Embeddings
🧠 Natural Language Processing
PythonMITupdated Nov 11, 2026
Embeddings#26
Embeddings#27
golbin/TensorFlow-Tutorials
텐서플로우를 기초부터 응용까지 단계별로 연습할 수 있는 소스 코드를 제공합니다
Pythonno licenseupdated Jan 4, 2023
Embeddings#28
explosion/sense2vec
🦆 Contextually-keyed word vectors
🧠 Natural Language Processing
PythonMITupdated Mar 27, 2026
Embeddings#29
plasticityai/magnitude
A fast, efficient universal vector embedding utility package.
🧠 Natural Language Processing
PythonMITupdated Aug 3, 2023
Embeddings#30
omarsar/nlp_overview
Overview of Modern Deep Learning Techniques Applied to Natural Language Processing
🧠 Natural Language Processing
CSSMITupdated Mar 25, 2020
📄 New research on Embeddings
📄 arXiv:2611.14514 · cs.AI45h ago
Contrastive Discovery: Open-Ended Scientific Discovery over Competing Explanations
Ziang Liu, James J. Kim, Yijia Dai +1
💬 Accepted at NeurIPS 2026. 55 pages. Project page: https://codiscovery.ai/contrastive-discovery/
LLM agents are increasingly used for open-ended, data-driven scientific discovery, yet most of them evaluate hypotheses pointwise, testing an empirical claim $h$ only against its complement $\neg h$. When evidence rejects $h$, the agent learns that one explanation is unlikely but not which alternative the evidence supports. To recover that alternative, we introduce Contrastive Discovery, which replaces the single hypothesis with a contrast set, a scientific question paired with mutually exclusive and collectively exhaustive competing explanations. Each experiment is scored by how its evidence redistributes belief across the set, and the question is resolved when belief concentrates on one explanation. Because contrast sets change only the unit an agent proposes and scores, an existing agent can use them to re-evaluate evidence it has already collected or to guide its search. Across six domains, $89\%$ of the pointwise candidates with the largest belief shifts are rejections. On the same evidence, contrast sets resolve $73\%$ of these candidates to a specific alternative. When contrast sets guide search, the agent resolves $67\%$ more questions than pointwise surprisal under the same experiment budget. In a blinded study, $38$ human experts chose the same explanation on $78\%$ of resolved questions and on $82\%$ of questions where the pointwise agent rejected its hypothesis and stopped. Together, these results support explicit competing explanations as a way for discovery agents to resolve more scientific questions from the same evidence and validation budget.▼ more
🧬 Embeddings🤖 Language Models
📄 arXiv:2611.14236 · cs.CL2d ago
StaRSE: Compact Russian Sentence Embeddings with a Sign-Coded Static Encoder
Boris Malashenko, Ivan Jarsky, Egor Soldatov +6
💬 Accepted to ReNeuIR @ SIGIR 2026. 16 pages
Transformer sentence encoders provide strong retrieval quality, but their inference cost becomes a bottleneck when embeddings must be produced on CPUs or refreshed frequently. We introduce StaRSE, a compact Russian static sentence encoder that removes Transformer inference at deployment time: token directions are stored as sign bits, token norms are stored separately, and sentences are encoded by mean pooling over norm-scaled sign directions. StaRSE is initialized from ruBERT-base, fine-tuned on Russian adjacent-sentence and task-shaped pairs, and post-trained with a contrastive stage that directly optimizes the sign-projected token table. On RuMTEB, StaRSE reaches a task mean of $51.16$, $7.98$ points above the strongest included static baseline. The packaged model occupies $11.3$ MiB and has a mean CPU latency of $0.08$ ms per sentence, compared with an estimated $55.7$ MiB 16-bit parameter footprint and $1.43$ ms mean CPU latency for the closest-quality contextual encoder. Ablations examine adjacent-sentence supervision, token norms, and direct sign-projected post-training.▼ more
🧬 Embeddings🔍 Search & Retrieval🤖 Language Models
📄 arXiv:2611.14004 · cs.IR2d ago
LUMIR: Decoupled Multimodal Representation Learning from Heterogeneous Data for Next-POI Recommendation
Zehui Wang, Wolfram Höpken, Dietmar Jannach
💬 16 pages. Accepted at the DaQuaMRec Workshop, co-located with ACM RecSys 2026
As multimodal tourism-related information collected from heterogeneous data sources has become increasingly available, learning effective representations has attracted attention for improving recommendation performance. Existing approaches often tightly couple multimodal fusion with the architecture and optimization objective of a specific downstream model, which limits the generality and reusability of the learned representations. To address these limitations, we propose LUMIR, a decoupled multimodal representation learning framework based on contrastive learning. Multimodal information collected from heterogeneous data sources is first semantically unified into a shared textual representation space using large language models (LLMs). An interaction-aware fusion mechanism is then designed to model cross-modal interactions, while sequential signals are incorporated as a structural constraint to guide representation learning. To evaluate the learned representations, experiments are conducted on a multimodal point-of-interest (POI) dataset under the next-POI recommendation setting across multiple sequential recommendation backbones. The results show that LUMIR consistently outperforms existing multimodal fusion baselines in both accuracy-oriented and beyond-accuracy metrics, demonstrating that decoupling representation learning from downstream optimization provides an effective paradigm for learning reusable multimodal representations. The code is publicly available at https://github.com/wzehui/LUMIR.▼ more
🧬 Embeddings🔍 Search & Retrieval🤖 Language Models
📄 arXiv:2611.13997 · cs.CV2d ago
Specify Privacy Yourself: Assessing Inference-Time Personalized Privacy Preservation Ability of Large Vision-Language Models
Xingqi Wang, Xiaoyuan Yi, Xing Xie +1
💬 Accepted by ACM Multimedia 2025 (Brave New Ideas track)
Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities but raise significant privacy concerns due to their abilities to infer sensitive personal information from images with high precision. While current LVLMs are relatively well aligned to protect universal privacy, e.g., credit card data, we argue that privacy is inherently personalized and context-dependent. This work pivots towards a novel task: can LVLMs achieve Inference-Time Personalized Privacy Protection (ITP$^3$), allowing users to dynamically specify privacy boundaries through language specifications? To this end, we present SPY-Bench, the first systematic assessment of ITP$^3$ ability, which comprises (1) 32,700 unique samples with image-question pairs and personalized privacy instructions across 67 categories and 24 real-world scenarios, and (2) novel metrics grounded in user specifications and context awareness. Benchmarking the ITP$^3$ ability of 21 SOTA LVLMs, we reveal that: (i) most models, even the top-performing o4-mini, perform poorly, with only $\sim$24% compliance accuracy; (ii) they show quite limited contextual privacy understanding capability. Therefore, we implemented initial ITP$^3$ alignment methods, including a novel Noise Contrastive Alignment variant which achieves 96.88% accuracy while maintaining reasonable general performance. These results mark an initial step towards the ethical deployment of more controllable LVLMs. Code and data are available at https://github.com/achernarwang/specify-privacy-yourself▼ more
🧬 Embeddings🤖 Language Models