mxbai-embed

A local text embedding model turns queries and documents into vectors for semantic search, with Apache 2.0 weights and adjustable embedding dimensions.

mxbai-embed is Mixedbread's text embedding model family for developers building semantic search and retrieval systems. The downloadable mxbai-embed-large-v1 model converts queries and documents into vectors that applications can compare by meaning.

Semantic retrieval: Compare a query with document passages to find relevant text, including matches that use different wording.
Smaller embeddings: Reduce embedding dimensions with Matryoshka Representation Learning and compress vectors with binary quantization to lower storage and memory use; both approaches can work together.
Python and JavaScript support: Run the model with SentenceTransformers, Transformers or Transformers.js, or serve it through Infinity in Docker.

The mxbai-embed-large-v1 weights use the Apache 2.0 license. Local inference runs on your own hardware and doesn't require Mixedbread's hosted service. The model produces embeddings; your application still needs a way to store and search them.

Mixedbread also offers a separate managed search platform that processes and indexes uploaded files. Its Wholembed V3 model depends on the Silo storage engine and isn't available as a standalone download.

Embedding and Reranker Models Hugging Face integration

Nobody has claimed mxbai-embed yet

Work on mxbai-embed? Claim this page with an email at mixedbread.com. mxbai-embed gets the verified checkmark, and you can upgrade the listing.

Want more people to find it? Promote it

Something wrong or outdated on this page?

Logotyper

Got an idea for an AI tool? I'm Eugene, the designer and developer behind Localhosted. I'll help you build it, from the first sketch to launch.

Start your project

Videos about mxbai-embed

View all mxbai-embed videos

SillyTavern vector memory setup with Ollama

AstrBot setup with CasaOS, Ollama and QQ

Similar to mxbai-embed

View all tools

Ollama

261 videos

An MIT-licensed local LLM runner and API for macOS, Windows, Linux and Docker, with optional cloud inference and coding agent integrations.

186.9KUpdated 21 hours agoMIT

macOS · Windows · Linux · Docker#GGUF#llama.cpp backend#Multimodal input

Ollama runs open models for people who want local AI applications, model chat or a backend for coding assistants. It provides a command-line interface and an API, with a choice between inference on your hardware and its cloud service.

Inference Servers and ClustersLocal Model Runners

ColBERT

An open-source neural search library for your own text collections, with BERT-based retrieval, CPU search and GPU indexing under the MIT license.

4KUpdated 1 year agoMIT

#Batch processing#Distributed execution#Hugging Face integration

ColBERT is a self-hosted neural search library for developers building document search or retrieval for AI applications. It finds relevant passages in your own text collections and stores their search representations on disk. The Python project is open source under the MIT license.

Embedding and Reranker ModelsRAG and Vector Search

ColPali

A local AI document retrieval library searches page images without separate OCR and includes training code; its engine package is deprecated.

2.9KUpdated 3 months agoMIT

macOS#Batch processing#Hugging Face integration#LoRA

ColPali is a document retrieval library for developers and researchers building search or retrieval-augmented generation systems. It matches text queries to page images, using visual content alongside text. The colpali-engine package is deprecated, and maintainers recommend Sentence Transformers for new projects and production use.

Embedding and Reranker ModelsInference Libraries and BindingsRAG and Vector Search

DINOv3

1 video

Local vision foundation models extract image features through PyTorch, with ViT and ConvNeXt backbones and Hugging Face Transformers support.

11.7KUpdated 4 months ago

#Hugging Face integration

DINOv3 is Meta AI's family of vision foundation models for researchers and developers building image analysis systems on their own hardware. Its pretrained models extract features for individual image regions that can support multiple vision tasks without fine-tuning the backbone.

Computer Vision ModelsEmbedding and Reranker Models

E5 Embeddings

1 video

A text embedding model family for local search and retrieval, with English, multilingual and instruction-based checkpoints on Hugging Face.

22.2KUpdated 2 months agoMIT

#Hugging Face integration#Multilingual

E5 Embeddings is a family of text embedding models for developers building search and retrieval systems. It represents text as numerical vectors so applications can match queries with relevant passages on their own hardware.

Embedding and Reranker Models

EmbeddingGemma

4 videos

An open-source embedding model supports text, code and media search locally and offline on consumer CPUs or GPUs under Apache 2.0.

5.8KUpdated 1 month agoApache-2.0

#Hugging Face integration#Multilingual#Quantization

EmbeddingGemma is a local AI embedding model for developers adding search and retrieval to applications. It represents text, images, audio and video in a shared space so apps can find related content across media types.

Embedding and Reranker Models