multilingual-e5-small

Name: multilingual-e5-small
Author: intfloat

by intfloat

Compact multilingual E5 text embedder with instruction prefixes

118Mparams

HuggingFace Run it on your own data, free

Identifiers

Model ID

intfloat/multilingual-e5-small

Feature URI

Overview

multilingual-e5-small is a small, fast text embedding model covering 100+ languages. Like the rest of the E5 family it uses instruction prefixes, 'query:' for searches and 'passage,' for indexed documents, which meaningfully improves retrieval quality for its size. It is a strong, cheap default for multilingual semantic search.

On Mixpeek, it is a text embedding extractor for documents, transcripts, and metadata, well suited to high-volume multilingual corpora where you want good recall at low latency and cost.

Architecture

12-layer multilingual encoder (initialized from multilingual MiniLM/E5 recipe), mean-pooled to a 384-dim embedding, trained with weakly-supervised contrastive pretraining plus supervised fine-tuning. Expects 'query:' / 'passage:' instruction prefixes.

Mixpeek SDK Integration

// No extractor parameter takes a Hugging Face model id (checked against
// GET /v1/discovery/extractors, which returns 13), so multilingual-e5-small runs
// on your side and the output is upserted through POST
// /v1/namespaces/{namespace_id}/documents/upsert. On Enterprise the other
// path is to upload the weights instead: POST /v1/namespaces/{id}/models
// accepts the huggingface format and a custom plugin loads them.
const res = await fetch(
  "https://api.mixpeek.com/v1/namespaces/ns_your_namespace/documents/upsert",
  {
    method: "POST",
    headers: {
      Authorization: "Bearer API_KEY",
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      collection_id: "col_your_collection",
      documents: [
        {
          document_id: "asset-00412",
          // The vector name has to match a vector index on the collection.
          vectors: { "text-embedding": yourVector },
          payload: { source_key: "archive/2026/asset-00412" },
        },
      ],
    }),
  },
);

// Managed alternative, if this exact model is not the requirement:
// text_extractor@v1 runs intfloat/multilingual-e5-large-instruct
// (1024-d) over a bucket, with no inference of your own.