Google/text-embedding-004/Released May 2024

Text Embedding 004

Text embeddings for search, RAG

Embeddings

About Text Embedding 004

Text Embedding 004 is an embeddings model that generates vector representations of text to capture semantic meaning and context. It excels in tasks such as semantic search, text classification, and clustering, making it a versatile tool for understanding text relationships.

Some noteworthy use cases of Text Embedding 004 include:

  • Semantic search for relevant content
  • Text classification to categorize documents
  • Clustering similar texts together
MetricValue
Context Length2,048 tokens
Embedding Dimensions768
MultilingualYes

Note: While Text Embedding 004 supports multiple languages, there have been reports of identical vector outputs for certain languages, which may affect its performance in those cases.

Ready to build with Text Embedding 004?

Try Text Embedding 004 in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.

Sign in to grab your API key and start making requests.
bash
curl -sSf -X POST https://hub.oxen.ai/api/ai/chat/completions \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer $OXEN_API_KEY" \
    -d '{
  "model": "text-embedding-004",
  "messages": [
    {
      "role": "user",
      "content": "Try sending a message."
    }
  ]
}'