Documentation for all-minilm:22m

Generates text embeddings using the /api/v1/embeddings endpoint. This model converts input text into numerical vectors suitable for tasks like semantic search, clustering, and classification.

Refer to the full documentation for the /api/v1/embeddings endpoint for details on headers, parameters (truncate, keep_alive, etc.), error handling, and response format.

Sample Request (cURL)

# Replace <your-orchestrator-host> and <API_KEY> with your actual values
curl https://<your-orchestrator-host>/api/v1/embeddings \
  -H "Authorization: Bearer <API_KEY>" \
  -H "X-User-Id: your_user_id_123" \
  -H "Content-Type: application/json" \
  -d '{
        "model": "all-minilm:22m",
        "input": ["Your text sentence here.", "Another sentence to embed."],
        "truncate": true,
        "keep_alive": "5m"
      }'