Reverse Dependencies of sentence-transformers
The following projects have a declared dependency on sentence-transformers:
- studcamp-yandex-hse — Text-tagging project within Yandex x HSE StudCamp event
- superagi — Private AutoGPT Robot - Your private task assistant with GPT!
- SuperDuperDB — 🔮 Super-power your database with AI 🔮
- superlinked — The Superlinked vector computing library
- supertriplets — Torch Multimodal Supervised Triplet Learning Toolbox
- superu — A package that helps optimize your chatbot response
- surprise-similarity — Context-aware similarity score for embedding vectors
- suzuka — ML
- synonym-finder — This package consists of synonym finder class
- tacrpy — Analytická knihovna pro potřeby TA ČR
- talk-codebase — talk-codebase is a powerful tool for querying and analyzing codebases.
- taranis-story-clustering — Story Clustering Bot for Taranis-NG
- targeted-sum — A package for targeted summarization
- testllm — Deep eval provides evaluation platform to accelerate development of LLMs and Agents
- testpackage12121 — This library is to search the best parameters across different steps of the RAG process.
- text-explainability — Generic explainability architecture for text machine learning models
- text-tagging-model — Here we collected some online and offline models for text tagging.
- text2mapviewer — A python package to map your own csv files data using Atlas from NOMIC
- text2music — A package for text-to-music generation
- textattack — A library for generating text adversarial examples
- textdiversity — A family of textual diversity metrics
- textmatchertoolkit — In summary, this package provides a set of utility functions and matching algorithms that can be used to preprocess, analyze, and match text data in various applications such as natural language processing, information retrieval, and text similarity analysis.
- textoir — TEXTOIR is the first high-quality Text Open Intent Recognition platform.
- textweaver — A FastAPI-based web server for working with LLMs, embedding models, and Pinecone Vector DB.
- thesaurus-lib — Implemented thesaurus library using SOM
- thext — THExt - Transformer-based Highlights Extraction
- tinyhnsw — no summary
- tknlp — no summary
- tokenwise — Tokenizer evaluation library
- toolva — SosiAl Media Bigdata Analysis service by pcn
- top2vec — Top2Vec learns jointly embedded topic, document and word vectors.
- topic-benchmark — Benchmarking topic models for a paper
- topicgpt — A package for integrating LLMs like GPT-3.5 and GPT-4 into topic modelling
- torchness — PyTorch tools
- TPE-Bot — A TPEdu All-in-one Chatbot Package
- TR-BIAS — Python package to idenitfy bias from a corpus
- transformertopic — Topic modeling using sentence_transformer
- transfusion — Transformers 🤝 diffusion
- translation-quality-estimator — To estimate the quality of translation
- TrendFlow — A tool for literature research and analysis
- triple-encoders — Distributed Sentence Transformer Representations with Triple Encoders
- turftopic — Topic modeling with contextual representations from sentence transformers.
- tweets-to-topic-network — start from a set of tweets and create a multilayer network where each layer is a topic
- twembeddings — event detection in tweets
- txtai — All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows
- uniteai — AI, Inside your Editor.
- unitxt — Load any mixture of text to text data in one line of code
- unstructured — A library that prepares raw documents for downstream ML tasks.
- useb — Heterogenous, Task- and Domain-Specific Benchmark for Unsupervised Sentence Embeddings used in the TSDAE paper.
- vdf-io — This library uses a universal format for vector datasets to easily export and import data from all vector databases.
- vec2text — convert embedding vectors back to text
- vecspace — VecSpace.
- vector-pipelines — Create scalable vector search powered pipelines with ease
- vectordb2 — A lightweight Python package for storing and retrieving text using chunking, embedding, and vector search
- vectorhub — One liner to encode data into vectors with state-of-the-art models using tensorflow, pytorch and other open source libraries. Word2Vec, Image2Vec, BERT, etc
- vectorhub-nightly — One liner to encode data into vectors with state-of-the-art models using tensorflow, pytorch and other open source libraries. Word2Vec, Image2Vec, BERT, etc
- vectorlite — Lightweight vector database.
- VectorMD — no summary
- vembed — Package providing methods to create Vector Embeddings from Strings, calculate similarities between lists of Strings, and Generate Visualizations such as Heatmaps from simple Lists.
- vesslflow — VESSLFlow
- vital-ai-vitalsigns — VitalSigns knowledge graph bindings
- vokab — vokab: named entity linking through hybrid (lexical and semantic) search engine.
- vsql — no summary
- wafl-llm — A hybrid chatbot - LLM side.
- weak-annotators — Weak annotators for information extraction (NER)
- whatlies — Tools to help uncover `whatlies` in word embeddings.
- whisperplus — WhisperPlus: A Python library for WhisperPlus API.
- whyis-milvus — no summary
- wikirec — Recommendation engine framework based on Wikipedia data
- wisdomweaver — Wisdom indexer and generator
- wizz — A terminal-based LLM chat client with knowledge retrieval.
- wm-topicgpt — This is a package to generate topics for the text corpus.
- wordpress-recommender — An application to recommend articles from a Wordpress blog based on user's query using semantic search
- wordview — Wordview is a Python package for Exploratory Data Analysis of text and provides many statistics about your data in the form of plots, tables, and descriptions allowing you to have both a high-level and detailed overview of your data.
- ws-benchmark — a weak supervision learning benchmark
- xinference — Model Serving Made Easy
- xlingual-papers-recommender — Component of Papers recommender system in cross-lingual and multidisciplinary scope
- xmen — An extensible toolkit for Cross-lingual (x) Medical Entity Normalization.
- yonlu — A deep learning based natural language understanding module
- yosemite — yosemite
- youtube-qa — Question answering over YouTube videos with embeddings and LLMs.
- zerohero — Easy Embedding-Based Zero-Shot Classfication
- zhkeybert — Based on KeyBERT performs Chinese documents keyword extraction with state-of-the-art transformer models.