Sign in Publish
contextetech/

BGE-M3 embeddings for RAG over long documents

v1
Contexte Tech

254 publication(s) · 321 uses

Source: huggingface.co/BAAI/bge-m3 ↗ Configuration English License: MIT updated 2 days ago
# BGE-M3 embeddings for RAG over long documents
code: 3g8wa | type: embedding | language: en | licence: MIT | version: v1
description: BGE-M3 for RAG over long documents: 1024 dimensions, up to 8,192 tokens, 100+ languages, no prefix needed. MIT license.
page: https://contextetech.com/en/embeddings/bge-m3-long-documents-3g8wa
mcp: connect https://contextetech.com/mcp then call load_resource with code "3g8wa" (or ask "load 3g8wa")
json: https://contextetech.com/api/resources/contextetech--bge-m3-long-documents
python: pip install contexte && contexte get 3g8wa
source: https://huggingface.co/BAAI/bge-m3
citation (required by the licence): contextetech. (2026). BGE-M3 embeddings for RAG over long documents (Version 1) [Embeddings]. Contexte Tech. https://contextetech.com/en/embeddings/bge-m3-long-documents-3g8wa. Data source: https://huggingface.co/BAAI/bge-m3

BGE-M3 for RAG over long documents: 1024 dimensions, up to 8,192 tokens, 100+ languages, no prefix needed. MIT license.

ModelBAAI/bge-m3
Dimensions1024
Max tokens8.2K
Distancecosine
Languagesen, es, fr, de, it, pt, zh, ja
Chunk size1000

Notes

No prefix needed for queries or passages.
Handles long inputs (8,192 tokens): chunks of about 1,000 words work well.
The model can also produce sparse vectors (keyword search) with the FlagEmbedding library.
Published by BAAI under the MIT license.

Community

No comments yet. Share your feedback, it will help the next person.