Skip to main content
Core.Today
|
E5FastHigh

Multilingual E5 Large

Multilingual text embeddings (74M+ runs) โ€” 1024-dimension vectors across 100 languages including Korean. Pairs perfectly with Core.Today customer databases' vector search (knn_vector).

2 credits
per run (batch multiple texts in one call)
1024-dim embeddings, 100 languages incl. Korean
Batch embedding of multiple texts per call
Normalized embeddings option (cosine-ready)
Pairs with customer DB vector search

Run it right now

Test this model instantly in the Console Playground โ€” no code required

Sign in to try

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

Quick Start

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "beautyyuyanli/multilingual-e5-large",
  "input": {
    "texts": "[\"์ฝ”์–ด๋‹ทํˆฌ๋ฐ์ด๋Š” AI API ๊ฒŒ์ดํŠธ์›จ์ด์ž…๋‹ˆ๋‹ค.\", \"ํฌ๋ ˆ๋”ง ๊ธฐ๋ฐ˜ ๊ณผ๊ธˆ์„ ์ง€์›ํ•ฉ๋‹ˆ๋‹ค.\"]",
    "normalize_embeddings": true
  }
}'

Parameters

ParameterTypeRequiredDefaultDescription
textsstringNo["In the water, fish are swimming.", "Fish swim in the water.", "A book lies open on the table."]Texts to embed as a JSON list of strings, e.g. ["hello", "world"]
batch_sizeintegerNo32Batch size for processing
normalize_embeddingsbooleanNotrueNormalize embeddings (recommended for cosine similarity)

Common Parameters

Common parameters used when calling POST /v1/predictions.

ParameterTypeRequiredDefaultDescription
modelstringYes-Model identifier
inputobjectYes-Object containing the model-specific parameters from the table above
output_folderstringNo-Folder path for output files (max 256 chars, '..' not allowed)
webhook_urlstringNo-Webhook URL to call on completion
is_publicbooleanNofalseIf true, output files are also available via permanent public URLs

Examples

Embed Korean Documents

Embed multiple Korean texts in one call

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "beautyyuyanli/multilingual-e5-large",
  "input": {
    "texts": "[\"์ฝ”์–ด๋‹ทํˆฌ๋ฐ์ด๋Š” AI API ๊ฒŒ์ดํŠธ์›จ์ด์ž…๋‹ˆ๋‹ค.\", \"ํฌ๋ ˆ๋”ง ๊ธฐ๋ฐ˜ ๊ณผ๊ธˆ์„ ์ง€์›ํ•ฉ๋‹ˆ๋‹ค.\"]",
    "normalize_embeddings": true
  }
}'

Tips & Best Practices

1Batch many texts per call โ€” one run embeds the whole list for 3 credits
2Store vectors in a Core.Today database with a knn_vector field (dimension: 1024) for search
3Keep normalize_embeddings: true so cosine similarity works out of the box
4E5 convention: prefix queries with 'query: ' and passages with 'passage: ' for best retrieval

Use Cases

Semantic search over documents
RAG pipelines with Core.Today databases
Multilingual deduplication
Recommendation similarity
Clustering and topic discovery