Reverse Dependencies of faiss-cpu
The following projects have a declared dependency on faiss-cpu:
- dfapp — A Python package with a built-in web application
- dir-assistant — Chat with your current directory's files using a local or API LLM.
- dire-jax — A JAX-based Dimension Reducer
- distilabel — Distilabel is an AI Feedback (AIF) framework for building datasets with and for LLMs.
- dleamse — dleamse's encoding and embedding methods, and dleamse's faiss index (IndexIDMap type) write.
- dls-rvc — no summary
- docmesh-agent — Agent helps you dig the paper connection!
- docusearch — Query documents quickly and efficiently
- doraemon-torch — Doraemon
- dr-doc-search — Search through a document using a chat interface
- dreamai-ray — DreamAI platform leveraging RAY.
- dreamsboard — no summary
- dspackage — DSpackage: A Data Science Toolkit
- dsrag — State-of-the-art RAG pipeline from D-Star AI
- easy-rag-llm — Easily implement RAG workflows with pre-built modules.
- easy-text-clustering — User-friendly, low-code text clustering
- easydata-python — A toolkit for processing data powered by PaddlePaddle, which include data augmentation, data cleaning and data annotation.
- easyfaiss — Package for building vector indexes
- easylaser — An easy to use interface to LASER
- easyrag-python — EasyRAG Python Package
- edubotics-core — Core modules for edubotics-based LLM AI chatbots
- efficient-ocr — Efficient OCR
- eknowledge — A Python package for executing graph generation from textual inputs.
- emb-opt — A lightweight framework to efficiently screen vector databases
- embantic — Embed pydantic models
- embeddings-evaluator — Tool for analyzing and comparing embedding models through pairwise cosine similarity distributions
- embedin — A lightweight vector database
- emergingtrajectories — Open source library for tracking and saving forecasts of political, economic, and social events.
- emlens — A lightweight toolbox for understanding embedding space
- engineX — no summary
- ensembleai — A Python package for AI-MultiModal MultiAgents methods and tools.
- 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!
- etoile-generate — no summary
- evadb — EvaDB AI-Relational Database System
- evoagent — An orchestration framework for evolving autonomous AI agents
- exponential — A Python package with a built-in web application
- extralit — Open-source tool for accurate & fast scientific literature data extraction with LLM and human-in-the-loop.
- face-recognition-pkg — A package for face recognition in images and videos
- fair-sense-ai — no summary
- faiss-imputer — Impute missing values using faiss
- faiss-minio-connection — Combining FAISS work with S3 cloud storage.
- faiss-searcher — 基于Pandas的Faiss检索小工具
- faiss-vector-aggregator — A package to aggregate embeddings in a Faiss vector store based on metadata columns.
- falcon-ms — Large-scale tandem mass spectrum clustering using fast nearest neighbor searching
- 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.
- fast-tts — no summary
- fastrag — An Efficient Retrieval Augmentation and Generation Framework for Intel Hardware.
- fastreid — SOTA Re-identification Methods and Toolbox
- faststream-gen — The faststream-gen library uses advanced AI to generate FastStream code from user descriptions, speeding up FastStream app development.
- fastwonn — Fast, GPU-friendly, differentiable computation of Intrinsic Dimension via Maximum Likelihood, the TwoNN algorithm, and everything in between!
- fatush — Simple utility tools for translating fastapi documentation
- fileseek — FileSeek – AI-Powered Local Document Archive&Search
- findprob — A CLI that lets you classify and search for problems by topic using an LLM
- fknni — Fast implementations of KNN imputation.
- flexrag — A RAG Framework for Information Retrieval and Generation.
- flow-benchmark-tools — A library containing LLM benchmarking tools
- fluxion-ai-python — A framework for orchestrating flow-based agentic workflows using LLMs.
- fmcore — A specialized toolkit for scaling experimental research with Foundation Models.
- forte.faiss — Provide Forte implementations of a fantastic collection of NLP tools.
- free-search — A simple vector database with CRUD and search functionality
- frye — LLM toolkit
- fumedev — AI pair programmer
- funcchain — 🔖 write prompts as python functions
- fvdb — Thin porcelain around the FAISS vector database.
- gaea-paddleclas — A treasure chest for visual recognition powered by PaddlePaddle.
- galadriel — no summary
- gega-promptflow-vectordb — Prompt flow tools for accessing popular vector databases
- genericsuite-ai — The GenericSuite AI for Python (backend version)
- genia — no summary
- genrag — It is a rag standalone package
- ggd-py-utils — A collection of utility functions for my projects.
- ghagent — A GitHub Explorer
- ghexplorer — A GitHub Explorer
- giskard — The testing framework dedicated to ML models, from tabular to LLMs
- git_autocommit_hook — Automatically generate commit messages from changes
- goldenretriever-core — Dense Retriever
- golem-garden — Welcome to the Garden - We're so glad you're here <3
- goodai-ltm — A text memory meant to be used with conversational language models.
- gps-babel-tower — Babel Tower NLP Library
- GPT4Readability — A tool to automatically generate a README.md and suggest code improvements for any code repository. It uses GPT-3, GPT-4, or an optional LocalAI model to generate the README.md and suggestions.
- graphfleet — A graph-based knowledge management and query system
- graphistry — A visual graph analytics library for extracting, transforming, displaying, and sharing big graphs with end-to-end GPU acceleration
- graphsense — GraphSense is a framework that can be used to easily train and use code suggestion models with minimal data preprocessing and resource consumption
- guardrails-ai — Adding guardrails to large language models.
- h2ogpt — no summary
- Harmonify — Harmonify: A project fork of RVC V2
- hashAI — A powerful SDK for building AI assistants with RAG capabilities.
- hawking — Hawking CLI
- hf-datasets — HuggingFace/NLP is an open library of NLP datasets.
- hi-sourcing — A similarity search utility for data sourcing
- hspylib-askai — HomeSetup - AskAI
- htmlrag — A smart toolkit for HTML cleaning and pruning for RAG systems.
- hybridagi — The Programmable Neuro-Symbolic Cypher-based AGI
- hypex — Fast and customizable framework for Causal Inference
- illufly — A simple Agent framework based on GPT with auto-evolution ability.
- image_vector_diego — no summary
- indexbinder — A library for storing and managing FAISS indexes on Google Cloud Storage. Fashionably serverless.
- inf-rvc-py — Python wrapper for fast inference with rvc
- infer-rvc-python — Python wrapper for fast inference with rvc
- inferrvc — High performance RVC inferencing, intended for multiple instances in memory at once. Also includes the latest pitch estimator RMVPE, Python 3.8-3.11 compatible, pip installable, memory + performance improvements in the pipeline and model usage.