> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tokenlab.sh/llms.txt
> Use this file to discover all available pages before exploring further.

# 建立 Embedding

> 建立表示輸入文字的 embedding 向量

## 請求主體

**同步請求逾時：** 這個非聊天端點會等待路由到的模型完成處理。大型輸入、長音訊或大量批次可能超過常見的 30s 用戶端預設逾時，因此請將 HTTP 用戶端逾時設定為至少 `120s`。

<ParamField body="model" type="string" required>
  要使用的 embedding 模型 ID（例如：`text-embedding-3-small`）。
</ParamField>

<ParamField body="input" type="string | array" required>
  要進行 embedding 的輸入文字。可以是字串或字串陣列。
</ParamField>

<ParamField body="encoding_format" type="string" default="float">
  embeddings 的格式：`float` 或 `base64`。
</ParamField>

<ParamField body="dimensions" type="integer">
  輸出的維度數量（依模型而定）。
</ParamField>

<ParamField body="user" type="string">
  代表終端使用者的唯一識別碼，用於濫用監控。
</ParamField>

## 可用模型

| 模型                       | 維度   | 說明   |
| ------------------------ | ---- | ---- |
| `text-embedding-3-large` | 3072 | 最佳品質 |
| `text-embedding-3-small` | 1536 | 平衡   |
| `text-embedding-ada-002` | 1536 | 舊版   |

## 回應

<ResponseField name="object" type="string">
  一律為 `list`。
</ResponseField>

<ResponseField name="data" type="array">
  embedding 物件的陣列。

  每個物件包含：

  * `object` (string)：`embedding`
  * `index` (integer)：輸入陣列中的索引
  * `embedding` (array)：embedding 向量
</ResponseField>

<ResponseField name="model" type="string">
  使用的模型。
</ResponseField>

<ResponseField name="usage" type="object">
  Token 使用量，包含 `prompt_tokens` 和 `total_tokens`。
</ResponseField>

<RequestExample>
  ```bash cURL theme={null}
  curl -X POST "https://api.tokenlab.sh/v1/embeddings" \
    -H "Authorization: Bearer sk-your-api-key" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "text-embedding-3-small",
      "input": "The quick brown fox jumps over the lazy dog"
    }'
  ```

  ```python Python theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key="sk-your-api-key",
      base_url="https://api.tokenlab.sh/v1"
  )

  response = client.embeddings.create(
      model="text-embedding-3-small",
      input="The quick brown fox jumps over the lazy dog"
  )

  embedding = response.data[0].embedding
  print(f"Embedding dimension: {len(embedding)}")
  print(f"First 5 values: {embedding[:5]}")
  ```

  ```javascript JavaScript theme={null}
  import OpenAI from 'openai';

  const client = new OpenAI({
    apiKey: 'sk-your-api-key',
    baseURL: 'https://api.tokenlab.sh/v1'
  });

  const response = await client.embeddings.create({
    model: 'text-embedding-3-small',
    input: 'The quick brown fox jumps over the lazy dog'
  });

  console.log(response.data[0].embedding.slice(0, 5));
  ```

  ```php PHP theme={null}
  <?php
  $ch = curl_init('https://api.tokenlab.sh/v1/embeddings');

  curl_setopt_array($ch, [
      CURLOPT_RETURNTRANSFER => true,
      CURLOPT_POST => true,
      CURLOPT_HTTPHEADER => [
          'Content-Type: application/json',
          'Authorization: Bearer sk-your-api-key'
      ],
      CURLOPT_POSTFIELDS => json_encode([
          'model' => 'text-embedding-3-small',
          'input' => 'The quick brown fox jumps over the lazy dog'
      ])
  ]);

  $response = curl_exec($ch);
  curl_close($ch);

  $data = json_decode($response, true);
  print_r(array_slice($data['data'][0]['embedding'], 0, 5));
  ```
</RequestExample>

<ResponseExample>
  ```json Response theme={null}
  {
    "object": "list",
    "data": [
      {
        "object": "embedding",
        "index": 0,
        "embedding": [0.0023, -0.0194, 0.0081, ...]
      }
    ],
    "model": "text-embedding-3-small",
    "usage": {
      "prompt_tokens": 9,
      "total_tokens": 9
    }
  }
  ```
</ResponseExample>

## 批次 Embeddings

```python theme={null}
# Embed multiple texts at once
response = client.embeddings.create(
    model="text-embedding-3-small",
    input=[
        "First document text",
        "Second document text",
        "Third document text"
    ]
)

for i, data in enumerate(response.data):
    print(f"Document {i}: {len(data.embedding)} dimensions")
```