GOD.EXEA god's-eye view of the AI universe
2026Drag to orbit · right-drag to pan · scroll to zoom
GOD.EXE is booting…

Model

BGE

BGE is an open-weight AI model, released in 2023, made for developers.

A family of open embedding and reranker models from BAAI for search and RAG.

Main jobs: Embeddings. It is open source and free to use. You can use it on your own server, offline on your own machine and through an API.

Visit github.com

Markdown version of https://godooo.ai/en/model/bge. Every page on this site has one: add .md to its address.

At a glance

Type
Model
Released
2023
Open source
Yes · MIT
GitHub stars
12,192
How you run it
Self-host · Runs offline · API
Made for
Developers
Website
github.com
Also known as
FlagEmbedding · BAAI General Embedding · bge-m3

What it can do

  • Embeddingsmain jobunconfirmed

    “BGE (BAAI General Embedding) focuses on retrieval-augmented LLMs, consisting of the following projects currently: - Inference : Embedder, Reranker”— github.com, 2026-09-24
  • Vector searchsupportedunconfirmed

    “It is the first embedding model which supports all three retrieval methods, achieving new SOTA on multi-lingual (MIRACL) and cross-lingual (MKQA) benchmarks.”— github.com, 2026-09-24

unconfirmedproposed by a machine, awaiting calibration

Alternatives

Connections

Applies
Embeddings

Questions

What is BGE?

BGE is an open-weight AI model, released in 2023, made for developers. A family of open embedding and reranker models from BAAI for search and RAG.

Is BGE free?

Yes. BGE is open source (MIT) and free to use.

Is BGE open source?

Yes, under the MIT license. The source code is at https://github.com/FlagOpen/FlagEmbedding.

Can BGE run locally?

Yes. BGE can run offline on your own machine. It can also be self-hosted on your own server.

What can BGE do?

Main jobs: Embeddings. It can also do: Vector search.

What are open-source alternatives to BGE?

Open-source ones: Sentence Transformers, BERT, CLIP, word2vec, ELMo, Weaviate, Mistral and LLM. Others: OpenAI Platform.

Sources