Embeddings multilingual-e5-large para un RAG en español

multilingual-e5-large para un RAG en español: 1024 dimensiones, 512 tokens, prefijos query:/passage: obligatorios, distancia coseno. Licencia MIT.

Notes

Los prefijos «query: » y «passage: » son obligatorios: sin ellos, la búsqueda empeora mucho.
512 tokens como máximo por texto: divide los documentos en fragmentos de unas 350 palabras.
Normaliza los vectores y usa la distancia coseno.
Modelo publicado por Microsoft (intfloat) con licencia MIT.

Estimated cost

Input tokens per call : ≈ 249

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 September 29, 2026. Estimate: 1 token ≈ 3.6 characters.

Identifier

contextetech--multilingual-e5-large-rag-espanol

Type

Embeddings

File

multilingual-e5-large-rag-espanol.embedding.json

Format

JSON (application/json)

Size

685 bytes

Encoding

UTF-8

Estimated tokens

≈ 190

Language

Spanish

License

MIT

Commercial use

Allowed

Personal data

None

Version

1.0

Published on

October 3, 2026 at 5:20 AM

Updated on

October 3, 2026 at 5:20 AM

Storage

in database

Uses

0

Likes

0

multilingual-e5-large-rag-espanol.embedding.json

{
  "format": "contextetech/embedding/v1",
  "id": "contextetech/multilingual-e5-large-rag-espanol",
  "description": "multilingual-e5-large para un RAG en español: 1024 dimensiones, 512 tokens, prefijos query:/passage: obligatorios, distancia coseno. Licencia MIT.",
  "tags": [
    "rag",
    "multilingue",
    "busqueda-semantica"
  ],
  "license": "MIT",
  "language": "es",
  "model": "intfloat/multilingual-e5-large",
  "dimensions": 1024,
  "maxTokens": 512,
  "distance": "cosine",
  "languages": [
    "es",
    "en",
    "fr",
    "de",
    "it",
    "pt"
  ],
  "prefixes": {
    "query": "query: ",
    "passage": "passage: "
  },
  "chunkSize": 350,
  "benchmarks": []
}

Embed (Python)

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("intfloat/multilingual-e5-large")
q = model.encode(["query: your input here"], normalize_embeddings=True)
docs = model.encode(["passage: …"], normalize_embeddings=True)
print(q.shape)  # (1, 1024)
print(q @ docs.T)  # similarité