Multimodal Embedding Model

POST 
https://knox.chat/v1/multimodalembeddings

Returns Multimodal Embedding Response

The multimodal embedding endpoint returns vector representations of given multimodal input lists composed of text, images, or interleaving of both modalities.

Headers

Name	Type	Required	Description
Authorization	String	Yes	Bearer authentication in the form of Bearer <token>, where token is your authentication token.

图片URL

curl -X POST https://knox.chat/v1/multimodalembeddings \
  -H "Authorization: Bearer $KNOXCHAT_API_KEY" \
  -H "content-type: application/json" \
  -d ' 
  {
    "inputs": [
      {
        "content": [
          {
            "type": "text",
            "text": "This is a banana."
          },
          {
            "type": "image_url",
            "image_url": "https://knox.chat/logo.png"
          }
        ]
      }
    ],
    "model": "voyage-multimodal-3"
  }'

Base64 图片

curl -X POST https://knox.chat/v1/multimodalembeddings \
  -H "Authorization: Bearer $KNOXCHAT_API_KEY" \
  -H "content-type: application/json" \
  -d ' 
  {
    "inputs": [
      {
        "content": [
          {
            "type": "text",
            "text": "This is a banana."
          },
          {
            "type": "image_base64",
            "image_base64": "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAA..."
          }
        ]
      }
    ],
    "model": "voyage-multimodal-3"
  }'

Response

Success Response (200)

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [
        0.027587891,
        -0.021240234,
        0.018310547,
        "...",
        -0.021240234
      ],
      "index": 0
    }
  ],
  "model": "voyage-multimodal-3",
  "usage": {
    "text_tokens": 5,
    "image_pixels": 2000000,
    "total_tokens": 3576
  }
}

Response Errors

• 4xx series are client-side errors
• 5xx series are server-side errors