Repository Index

State-of-the-Art Embeddings, Retrieval, and Reranking

Topic Modelling for Humans

• gensim
• topic-modeling
• information-retrieval
• machine-learning

A very simple framework for state-of-the-art Natural Language Processing (NLP)

• pytorch
• nlp
• named-entity-recognition
• sequence-labeling

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

• python
• search
• nlp
• semantic-search

Translated100+ Chinese Word Vectors

• chinese
• chinese-word-segmentation
• embeddings
• word-embeddings

Implementation and experiments of graph embedding algorithms.

• deepwalk
• node2vec
• line
• sdne

Representation learning on large graphs using stochastic graph convolutions.

Open-source inference server and production cluster for all the models your agent needs.

• embeddings
• vector-search
• data-pipeline
• deep-learning

Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.

• machine-learning
• convolutional-networks
• embedding-vectors
• embeddings

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

• embeddings
• openai
• rag
• retrieval

Fast State-of-the-Art Static Embeddings

• embeddings
• machine-learning
• model2vec
• nlp

Python library for Representation Learning on Knowledge Graphs https://docs.ampligraph.org

• machine-learning
• knowledge-graph
• relational-learning
• representation-learning

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

• embeddings
• information-retrieval
• language-model
• text-classification

Nomic Developer API SDK

• python
• clustering
• duplicate-detection
• embeddings

NeurIPS 2025 Spotlight; ICLR2024 Spotlight; CVPR 2024; EMNLP 2024

Tasks Assessing Protein Embeddings (TAPE), a set of five biologically relevant semi-supervised learning tasks spread across different domains of protein biology.

• deep-learning
• protein-sequences
• protein-structure
• semi-supervised-learning

A simple deep learning library for estimating a set of tags and extracting semantic feature vectors from given illustrations.

Learning Heterogeneous Tactile Representation for General Dexterous Manipulation

UCE is a zero-shot foundation model for single-cell gene expression data