> ## Documentation Index > Fetch the complete documentation index at: https://mixroute.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Gemini 文字向量（embedContent） > 使用 Gemini 原生介面將文字轉換為向量嵌入 ## 簡介 使用 Gemini 原生介面將文字轉換為向量嵌入。模型由 URL 路徑 指定（如 `gemini-embedding-001`），適用於需要 Google 嵌入模型或與 Gemini API 對齊的場景。 與 [文字向量化（Embedding）](/docs/zh-Hant/api-reference/endpoint/embeddings) 的 OpenAI 格式互為補充：本文件為 Gemini 原生路徑；同一能力也可透過 `POST /v1/embeddings` 呼叫。 ## 認證 Bearer Token，如 `Bearer sk-xxxxxxxxxx` ## 路徑參數 **model** `string` *required* 嵌入模型名稱，如 `gemini-embedding-001`。 ## 請求參數 **content** `object` *required* 待嵌入內容。須包含 `parts` 陣列，每項為 `{ "text": "文字內容" }`。 **outputDimensionality** `integer` 輸出向量維度（僅部分模型支援，如 `gemini-embedding-001`、`text-embedding-004`）。 **taskType** `string` 任務類型，如 `RETRIEVAL_DOCUMENT`、`RETRIEVAL_QUERY`（選填）。 ## 程式碼範例 **cURL** ```bash theme={null} curl -X POST "https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent" \ -H "Content-Type: application/json" \ -H "Authorization: Bearer sk-xxxxxxxxxx" \ -d '{ "content": { "parts": [ { "text": "要嵌入的文字內容" } ] } }' ``` **cURL（帶維度）** ```bash theme={null} curl -X POST "https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent" \ -H "Content-Type: application/json" \ -H "Authorization: Bearer sk-xxxxxxxxxx" \ -d '{ "content": { "parts": [ { "text": "要嵌入的文字內容" } ] }, "outputDimensionality": 768 }' ``` **Python** ```python theme={null} import requests url = "https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent" headers = { "Content-Type": "application/json", "Authorization": "Bearer sk-xxxxxxxxxx" } payload = { "content": { "parts": [ { "text": "要嵌入的文字內容" } ] } } response = requests.post(url, json=payload, headers=headers) data = response.json() embedding = data["embedding"]["values"] print(f"向量維度：{len(embedding)}") ``` ## 回應範例 ```json theme={null} { "embedding": { "values": [0.0023064255, -0.009327292, 0.015797347, ...] }, "metadata": { "usage": { "prompt_tokens": 6, "total_tokens": 6 } } } ``` ## 批次介面（batchEmbedContents） 批次嵌入請使用：`POST /v1/models/{model}:batchEmbedContents`，請求體為 `requests` 陣列，每項結構同單條（含 `content.parts`），且 **不要** 在每項中帶 `model` 欄位。 ```bash theme={null} curl -X POST "https://api.mixroute.ai/v1/models/gemini-embedding-001:batchEmbedContents" \ -H "Content-Type: application/json" \ -H "Authorization: Bearer sk-xxxxxxxxxx" \ -d '{ "requests": [ { "content": { "parts": [{ "text": "第一段文字" }] } }, { "content": { "parts": [{ "text": "第二段文字" }] } } ] }' ``` ## 支援的模型 | 模型 | 說明 | | - | - | | gemini-embedding-001 | 通用嵌入模型，支援 `outputDimensionality` | | text-embedding-004 | 高精度嵌入模型 | ## 注意事項 * `content.parts` 必填，至少一個 `text` 非空 * 模型由 URL 路徑指定，請求體不要包含 `model` 欄位 * 用量資訊在回應的 `metadata.usage` 中（`prompt_tokens`、`total_tokens`） > [!TIP] > > 如果您的應用程式已使用 OpenAI SDK，建議使用 `/v1/embeddings` 相容介面以減少程式碼修改。 ```bash cURL theme={null} curl --request POST \ --url https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent \ --header 'Authorization: Bearer sk-xxxxxxxxxx' \ --header 'Content-Type: application/json' \ --data '{ "content": { "parts": [{"text": "這是一段測試文字"}] } }' ``` ```python Python theme={null} import requests url = "https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent" headers = { "Authorization": "Bearer sk-xxxxxxxxxx", "Content-Type": "application/json" } payload = { "content": { "parts": [{"text": "這是一段測試文字"}] } } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript JavaScript theme={null} const response = await fetch('https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent', { method: 'POST', headers: { 'Authorization': 'Bearer sk-xxxxxxxxxx', 'Content-Type': 'application/json' }, body: JSON.stringify({ content: { parts: [{ text: '這是一段測試文字' }] } }) }); const data = await response.json(); console.log(data); ``` ```php PHP theme={null} post('https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent', [ 'headers' => [ 'Authorization' => 'Bearer sk-xxxxxxxxxx', 'Content-Type' => 'application/json', ], 'json' => [ 'content' => [ 'parts' => [['text' => '這是一段測試文字']] ] ] ]); echo $response->getBody(); ``` ```go Go theme={null} package main import ( "bytes" "encoding/json" "net/http" ) func main() { payload := map[string]interface{}{ "content": map[string]interface{}{ "parts": []map[string]string{ {"text": "這是一段測試文字"}, }, }, } body, _ := json.Marshal(payload) req, _ := http.NewRequest("POST", "https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent", bytes.NewBuffer(body)) req.Header.Set("Authorization", "Bearer sk-xxxxxxxxxx") req.Header.Set("Content-Type", "application/json") http.DefaultClient.Do(req) } ``` ```java Java theme={null} import java.net.http.*; import java.net.URI; HttpClient client = HttpClient.newHttpClient(); String json = """ { "content": { "parts": [{"text": "這是一段測試文字"}] } } """; HttpRequest request = HttpRequest.newBuilder() .uri(URI.create("https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent")) .header("Authorization", "Bearer sk-xxxxxxxxxx") .header("Content-Type", "application/json") .POST(HttpRequest.BodyPublishers.ofString(json)) .build(); HttpResponse response = client.send(request, HttpResponse.BodyHandlers.ofString()); System.out.println(response.body()); ``` ```ruby Ruby theme={null} require 'net/http' require 'json' uri = URI('https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent') http = Net::HTTP.new(uri.host, uri.port) http.use_ssl = true request = Net::HTTP::Post.new(uri) request['Authorization'] = 'Bearer sk-xxxxxxxxxx' request['Content-Type'] = 'application/json' request.body = { content: { parts: [{ text: '這是一段測試文字' }] } }.to_json response = http.request(request) puts response.body ``` ```json Response theme={null} { "embedding": { "values": [0.0023064255, -0.009327292, 0.015797347] }, "metadata": { "usage": { "prompt_tokens": 6, "total_tokens": 6 } } } ``` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.