254 publication(s) · 321 uses
# 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.
| Model | BAAI/bge-m3 |
|---|---|
| Dimensions | 1024 |
| Max tokens | 8.2K |
| Distance | cosine |
| Languages | en, es, fr, de, it, pt, zh, ja |
| Chunk size | 1000 |
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.
- Identifier
- contextetech--bge-m3-long-documents
- File
- bge-m3-long-documents.embedding.json
- Format
- JSON (application/json)
- Size
- 560 bytes
- Encoding
- UTF-8
- Estimated tokens
- ≈ 156
- Commercial use
- Allowed
- Personal data
- None
- Version
- 1.0
- Published on
- October 2, 2026 at 9:54 PM
- Updated on
- October 16, 2026 at 11:19 PM
- Storage
- in database
Statistics
Likes : 0 · Comments : 0
Click a counter to show or hide it, hover the chart for details. One view per visitor per day, bots excluded; counting started on 30 September 2026.
Estimated cost
- Input tokens per call
- ≈ 225
| Model | Per call | Per month |
|---|---|---|
| GPT-6 Luna · OpenAIbest price | €0.00002 | €0.02 |
| DeepSeek Flash · DeepSeek | €0.00006 | €0.06 |
| Mistral Large · Mistral AI | €0.00010 | €0.10 |
| DeepSeek V4 Pro · DeepSeek | €0.00026 | €0.26 |
| GPT-6 Sol · OpenAI | €0.00040 | €0.40 |
| Claude Sonnet 5.5 · Anthropic | €0.00040 | €0.40 |
| Claude Opus 5.5 · Anthropic | €0.00079 | €0.79 |
| Self-hosted open-source model (Ollama, vLLM) | €0 in API fees (server cost only) | |
Input cost only, excluding the model's answer. Providers' public standard prices (Mistral AI, DeepSeek, OpenAI, Anthropic) converted from USD to euros at the ECB rate of October 13, 2026. Estimate: 1 token ≈ 3.6 characters.
Common to all 3 regions
Sources under a compatible licence.
Sources: BAAI/bge-m3 model, MIT license (Hugging Face model card)
Commercial use allowed · credit the author · changes allowed.
Text or data only: no access to files, network or commands.
Hosted in France (Scaleway, Paris). No transfer outside the EU.
European Union · 5/5
No personal data.
No training data: no summary required.
United States · 5/5
No personal data.
No training data: no documentation to publish.
China · 5/5
No personal data.
No training data; AI-generated content published in China must be labelled (2025).
Indicative summary as of 30/09/2026, not a legal certification. Method and sources →
Content quality
The detailed criteria are for members.
Every criterion, the points removed and a tip to fix each one.
MCP contexte
https://contextetech.com/mcp
load 3g8wa
Add the URL as a connector in your AI apps' settings, then send the request above.
API
import json, urllib.request url = "https://contextetech.com/api/resources/contextetech--bge-m3-long-documents" fiche = json.load(urllib.request.urlopen(url)) print(fiche["title"] or fiche["name"])
bge-m3-long-documents.embedding.json
{
"format": "contextetech/embedding/v1",
"id": "contextetech/bge-m3-long-documents",
"description": "BGE-M3 for RAG over long documents: 1024 dimensions, up to 8,192 tokens, 100+ languages, no prefix needed. MIT license.",
"license": "MIT",
"language": "en",
"model": "BAAI/bge-m3",
"dimensions": 1024,
"maxTokens": 8192,
"distance": "cosine",
"languages": [
"en",
"es",
"fr",
"de",
"it",
"pt",
"zh",
"ja"
],
"prefixes": {
"query": "",
"passage": ""
},
"chunkSize": 1000,
"benchmarks": []
}Embed (Python)
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("BAAI/bge-m3")
q = model.encode(["your input here"], normalize_embeddings=True)
docs = model.encode(["…"], normalize_embeddings=True)
print(q.shape) # (1, 1024)
print(q @ docs.T) # similarité
Community
No comments yet. Share your feedback, it will help the next person.