Reverse Dependencies of sentence-transformers
The following projects have a declared dependency on sentence-transformers:
- elasticsearch-dsl — Python client for Elasticsearch
- emb3d — emb3d.co command line inteface to work with embeddings.
- embd — Unix embedding driver for software 2.0
- embed-clustering — Clustering using different non-parameteric models with the combination of word Embedding
- embed-text-reducer — A simple text simplification tool using advanced NLP techniques.
- embedchain — Simplest open source retrieval (RAG) framework
- embedders — High-level API for creating sentence and token embeddings
- embedding-lenses — no summary
- embeddingcache — Retrieve text embeddings, but cache them locally if we have already computed them.
- embeddings-explorer — A package for generating, exploring, and visualizing word embeddings graphs.
- embedin — A lightweight vector database
- embestore — no summary
- embetter — Just a bunch of useful embeddings to get started quickly.
- EnvBert — Predicts classes of environmental due diligence
- esco-playground — no summary
- essence-extractor — Unleash the power of content transformation with EssenceExtractor, a dynamic tool that turbocharges your workflow, turning YouTube videos into engaging, readable blog posts in a snap!
- eurelis-kb-framework — Framework to build and manage knowledge base. Based on Langchain under the hood.
- evadb — EvaDB AI-Relational Database System
- experimaestro-ir — Experimaestro common module for IR experiments
- explainitall — no summary
- exponential — A Python package with a built-in web application
- fabler — Multimodal AI Story Teller, built with Stable Diffusion, GPT, and neural text-to-speech.
- factscore — FactScore is an automatic evaluation metric for factual precision in long-form text generation. It uses large language models and retrieval to break down generations into atomic facts and then measure the correctness with respect to a knowledge source (like Wikipedia).
- FactualSceneGraph — A package for scene graph parsing and evaluation
- faiss-instant — This package contains toolkit for faiss-instant. It mainly helps to encode texts via Transformers and build Faiss indexes in an automatic way.
- faithfulness — A library to evaluate faithfulness (factual correctness or consistency) of abstractive summaries.
- fake-statement-detection — no summary
- falcon-evaluate — Falcon Evaluate is an open-source Python library designed to simplify the process of evaluating and validating open source LLM models such as llama2,mistral ,etc. This library aims to provide an easy-to-use toolkit for assessing the performance, bias, and general behavior of LLMs in various natural language understanding (NLU) tasks.
- farm-haystack — LLM framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data.
- fasdr — Simple dense retrieval using SciPy, spaCy, and Sentence-Transformers
- fast-sentence-transformers — This repository contains code to run faster sentence-transformers using tools like quantization, ONNX and pruning.
- fastlexrank — A streamlined and approximate implementation of the LexRank algorithm for rapid text summarization.
- fastnn — A python library and framework for fast neural network computations.
- fastrepl — Fast Run-Eval-Polish Loop for LLM App
- fatush — Simple utility tools for translating fastapi documentation
- fendi — An auto py builder for ChatBots on top of streamlit app's - LLaMa's powered APS
- few-shot-clustering — A library for efficient semi-supervised clustering with large language models.
- few-shot-learning — Easy few shot learning for NLP
- Few-Shot-Learning-NLP — This library provides tools and utilities for Few Shot Learning in Natural Language Processing (NLP).
- fibber — Fibber is a benchmarking suite for adversarial attacks on text classification.
- fiddler-auditor — Auditing large language models made easy.
- FLAML — A fast library for automated machine learning and tuning
- flatpack — Ready-to-assemble AI
- flexible-semantic-kernel — flexible-semantic-kernel
- flexnlp — no summary
- frenchnlp — State of the art toolchain for natural language processing in French
- frogbase — FrogBase simplifies the download-transcribe-embed-index workflow for multi-media content. It does so by linking content from various platforms with speech-to-text models, image & text encoders and embedding stores.
- frye — LLM toolkit
- future-shot — FutureShot: Few-Shot Learning for high-dimensional classification problems
- FuzzTypes — FuzzTypes is a Pydantic extension for annotating autocorrecting fields
- gate-drift — Data drift detection tool for machine learning pipelines.
- genai_stack — End-to-End Secure & Private Generative AI for All
- genegist — Create summararies of groups of genes.
- genienlp — no summary
- genius-chatbot — Use huggingface models to create an intelligent and scalable chatbot
- geniusrise-audio — audio bolts for geniusrise
- geniusrise-text — Text bolts for geniusrise
- geniusrise-vision — Huggingface bolts for geniusrise
- geoparser — A geoparsing library for English texts
- geoverifysm — Validate Euclidea Levels without GUI. Note this is not the most reliable way, and might contain errors for some level packs.
- gft-cpu — GFT (general fine-tuning) A Little Language for Deepnets: 1-line programs for fine-tuning, inference and more
- ghagent — A GitHub Explorer
- ghexplorer — A GitHub Explorer
- gigachain — Building applications with LLMs through composability
- gigachain-experimental — Building applications with LLMs through composability
- goodai-ltm — A text memory meant to be used with conversational language models.
- gpt-me — An experiment to replicate a fully self-sufficient, human-like chatbot that imitates you using various artificial intelligence models.
- gpt-readme-reader — A utility to extract setup commands from a GitHub repository
- gpt3discord — A Chat GPT Discord bot
- gptstonks-api — GPTStonks API allows interacting with financial data sources using natural language.
- gptstonks-wrappers — Useful wrappers around common AI tools: LangChain, LlamaIndex, etc.
- gptswarm — GPTSwarm: Language Agents as Optimizable Graphs
- grad-info-opt — Implementation of Gradient Information Optimization for efficient and scalable training data selection
- grag — A simple package for implementing RAG
- graphistry — A visual graph analytics library for extracting, transforming, displaying, and sharing big graphs with end-to-end GPU acceleration
- GRLMerger — GRL Merger is a package that integrates two GRL models written in TGRL syntax into one GRL model.
- gts-engine — git_engine development suite: a powerful NLU training system
- guardrail-ml — Monitor LLMs with custom metrics to scale with confidence
- h2ogpt — no summary
- hackathon-evaluation-rag — no summary
- hammadml — ML
- hammadml-gpu — Hammad Python ~ Machine Learning
- happy-learning — Toolbox for reinforced developing of machine learning models (as proof-of-concept)
- harmonydata — Harmony Tool for Retrospective Data Harmonisation
- hf-hub-ctranslate2 — Connecting Transfromers on HuggingfaceHub with Ctranslate2
- hf-model-s — model-s served from hf spaces
- hierarchy-transformers — Language models as hierarchy encoders.
- hive-cli — no summary
- homepage2vec — Language-Agnostic Website Embedding and Classification
- huixiangdou — Overcoming Group Chat Scenarios with LLM-based Technical Assistance
- hushh-vibe-catalog — no summary
- hybrid-search — Hybrid search with OpenSearch and Langchain
- hypertag — File organization made for humans
- incognitoGPT — no summary
- indexpaper — indexpaper - library to index papers with vector databases
- infinity_emb — Infinity is a high-throughput, low-latency REST API for serving vector embeddings, supporting a wide range of sentence-transformer models and frameworks.
- info-chunks-to-embeddings — no summary
- instruct-qa — Empirical evaluation of retrieval-augmented instruction-following models.
- instructor-embedders-haystack — Haystack 2.x component to embed strings and Documents using Instructor embedding model.
- instrukt — A versatile AI environment to build and control AI agents using a terminal-based interface.