Gemini 嵌入(Embeddings)

使用指定引擎/模型创建嵌入

Authorization

bearerAuth

AuthorizationBearer <token>

使用 Authorization Bearer API Key 进行鉴权。

In: header

Path Parameters

model*string

模型/引擎 ID

Request Body

application/json

TypeScript Definitions

Use the request body type in TypeScript.

model*string

模型 ID。

input*|array<string>

要嵌入的文本

encoding_format?string

encoding_format 字段。

Default"float"

Value in"float" | "base64"

dimensions?integer

输出向量维度

Response Body

`application/json`

curl -X POST "https://example.com/v1/engines//embeddings" \  -H "Content-Type: application/json" \  -d '{    "model": "text-embedding-ada-002",    "input": "string"  }'

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [
        0
      ]
    }
  ],
  "model": "string",
  "usage": {
    "prompt_tokens": 0,
    "completion_tokens": 0,
    "total_tokens": 0,
    "input_tokens": 0,
    "output_tokens": 0
  }
}