Reverse Dependencies of sentence-transformers
The following projects have a declared dependency on sentence-transformers:
- pyccr — Contextualized Construct Representations (CCR).
- pyconverse — Coversational Transcript Analysis using various NLP techniques
- pydata-wrangler — Wrangle messy data into pandas DataFrames, with a special focus on text data and natural language processing
- pyjedai — An open-source library that builds powerful end-to-end Entity Resolution workflows.
- pykoi — pykoi: Active learning in one unified interface
- pyllmsearch — LLM Powered Advanced RAG Application
- pynbx — Next generation of knolwedge management
- pyspark-ai — English SDK for Apache Spark
- pyterrier-sentence-transformers — Create an pyterrier index using any sentence-transformers model
- python-boilerplate123123 — Python boilerplate
- python-vectorspace — Directory file watcher for automatically creating and querying vector embeddings.
- pyvindex — simple python api to create vector indexes
- qary — A chatbot that assists rather than manipulates.
- qualiti — Qualiti.ai Python Tools
- query-package-documentation — A package to explore documentations
- quintus — Document Embedding and Inference
- r2r — SciPhi R2R
- racp — A tool for building academic paper retriever.
- radio-mlbee — mlbee via gradio
- raga-llm-eval — Package for LLM Evaluation
- raga-llm-hub — Package for LLM Evaluation
- ragas — no summary
- RAGatouille — Library to facilitate the use of state-of-the-art retrieval models in common RAG contexts.
- ragcar — RAGCAR: Retrieval-Augmented Generative Companion for Advanced Research
- RAGchain — Build advanced RAG workflows with LLM, compatible with Langchain
- ragen — Retrieval Augmented Generation.
- ragfmk — Lightweight RAG Framework: Simple and Scalable Framework with Efficient Embeddings. Leverage: FAISS, ChromaDB, and Ollama.
- ragmap — RAGmap is a simple RAG visualization package for exploring document chunks and queries in embedding space
- ragxplorer — A open-source tool to to visualise your RAG documents 🔮.
- ralf-jhuapl — A lightweight library to support the development of applications using LLMs.
- rankexpansion — no summary
- readability-transformers — Package for integrating transformer modules for readability-related NLP tasks.
- recommender-agent — En el presente proyecto muestro la construcción de una sistema de recomendación, el sistema permite recomendar recursos a través del uso de mecanismos de Procesamiento de lenguaje natura como agentes langchain, IA generatica y embeddings.
- recs-searcher — Search engine and registry error corrector
- redisvl — Python client library and CLI for using Redis as a vector database
- referral-augment — Official implementation of "Referral Augmentation for Zero-Shot Information Retrieval"
- reflective-listening — Reflective listening statements via paraphrase generation
- refuel-autolabel — Label, clean and enrich text datasets with LLMs
- relatio — A Python package to extract narrative statements from text
- RelevanceAI-dev — no summary
- Remote-Sensing-Analysis — Library that conducts analysis on Satellite Imagery
- research-framework — framework base para investigación
- responsibleai-text — SDK API to assess text Machine Learning models.
- retake — Open Source Infrastructure for Vector Data Streams
- retriever-search — Local retriever search for your use
- reverse-engineering-assistant — An AI assistant for reverse engineering tasks
- rising-plugin — It is a plugin for Rising GPT
- RiskBERT — Generalized semantic regression with a BERT base.
- RLMS-PK — Multimodal Summarization using RLMS approach
- rtk-mult-clf — no summary
- russian-paraphrasers — Russian Paraphrasers (based on ru-gpt, mt5)
- safe-store — A library for safe document storage and vectorization.
- sam-ml-py — a library for ML programing created by Samuel Brinkmann
- samosila-core — no summary
- sbnltk — Bangla NLP toolkit
- schema-matching — Using XGboost and Sentence-Transformers to perform schema matching task on tables.
- sciterra — Scientific literature data exploration analysis
- scrapegoat — Scrape data in one-shot
- scripture — A simplistic rule-based AI that is easy to train and use
- searchbible — Search Bible AI - Integrate Unique Bible App resources with AI tools
- searchbibleai — Search Bible AI - Integrate Unique Bible App resources with AI tools
- searchdatamodels — no summary
- selector-standardizers — Electoral Data Standardization classes for the Selector project
- semantic-ai — Sematic AI RAG System
- semantic-code-search — Search your codebase with natural language.
- semantic-kernel — Semantic Kernel Python SDK
- semantic-navigator — An active learning approach to query and search through large archival datasets.
- semantic-search — Make semantic search easier
- semantic-search-faiss — Semantic search to query covid related papers
- semantic-similarity-cli — file: README.md
- semantic-split — A better way to split (chunk/group) your text before inserting them into an LLM/Vector DB.
- semanticlayertools — Create social, material or semantic layers using different methods to work with the Socio-epistemic networks framework.
- semanticmatcher — Semantic search of text and semanic matching of tables using FAISS
- SemRun — PigeonAI client and SDK
- semsis — A libary for semantic similarity search
- sentecon — Interpretable deep embeddings using lexicons
- sentence-similarity — Package to calculate the similarity score of two sentences
- SentenceGraph — Easily create semantic graphs from text using SentenceTransformers
- senti-key-summ — Multilingual Summarization
- seotools — A collection of tools for use with writing SEO-related programs in Python.
- setfit — Efficient few-shot learning with Sentence Transformers
- similarity-check — package for measuring the similarity of two texts
- similarity-ranker — no summary
- siminotes — A CLI tool for discovering similar notes within your note collection.
- simplests — Unsupervised models for Semantic Textual Similarity
- SimpleTopicModel — An NLP Package for generating Topic Models
- sliceguard — A library for detecting critical data slices in structured and unstructured data based on features, metadata and model predictions.
- smart-data-science — Personal side project to streamline the most common tasks of data science solutions in an efficient manner. This project is based on my experience as a lead data scientist in the industry and financial services sectors, where I have gained expertise in delivering effective data-driven insights and solutions
- smiles-featurizers — A python library for extracting molecular SMILES embeddings from language models pre-trained with various objectives and/or architectures.
- snowflake-ml-python — The machine learning client library that is used for interacting with Snowflake to build machine learning solutions.
- softpandas — An easy to use semantic (soft) querying on pandas dataframes.
- sommify — A package for recipe parsing
- spadepp — no summary
- spanking — 🍑👋
- srctag — Tag source files with real-world stories.
- steadynlp — A collection of simple NLP focused functions to support your main projects
- strategais — A Python library for deploying large language models (LLMs) in local environments.
- stripnet — STriP Net: Semantic Similarity of Scientific Papers (S3P) Network
- sts-select — Feature selection tools based on semantic textual similarity (STS) scores.
- studcamp-yandex-hse — Text-tagging project within Yandex x HSE StudCamp event