Tokatlas

外觀

English
Gemini Messages

檔案分析 ​

使用 Gemini Interactions API 分析圖像、影片、音訊與文件。

Gemini Interactions API 透過 input 陣列中的內容區塊支援多模態輸入。請先透過 Files API 上傳檔案，再於請求中引用傳回的 uri。

端點與驗證方式同文字生成。

路由前提

本頁為 Interactions 協定範例。目前本地網關程式只註冊 Gemini generateContent 路由，沒有註冊 /v1beta/interactions；只有部署環境另外提供此路由時才能執行本頁範例。一般 Gemini 客戶端請見 Gemini CLI，圖像生成請見 Nano Banana。若收到 404，不要只替換 URL：兩種協定的請求與回包不同。

內容區塊類型 ​

類型說明
text隨媒體輸入附上的文字提示
image包含 uri 與 mime_type 的圖像（如 image/jpeg、image/png）
documentPDF 文件，使用 uri 與 mime_type: "application/pdf"
video包含 uri 與 mime_type 的影片（如 video/mp4）
audio包含 uri 與 mime_type 的音訊（如 audio/wav、audio/mp3）

取得可用的檔案 URI ​

先使用 Tokatlas 已確認支援的上傳流程取得 uri，再替換下方 YOUR_FILE_URI。本頁未定義上傳端點或上傳請求格式，請先向服務管理者確認；其他供應商或帳戶的 URI 不一定可讀取。若檔案需要處理，請等到可用後再送出互動請求。

圖像分析 ​

json
{
  "model": "gemini-3.7-flash",
  "input": [
    {"type": "text", "text": "Tell me about this instrument"},
    {
      "type": "image",
      "uri": "YOUR_FILE_URI",
      "mime_type": "image/jpeg"
    }
  ]
}

影片分析 ​

json
{
  "model": "gemini-3.7-flash",
  "input": [
    {"type": "text", "text": "Summarize what happens in this video."},
    {
      "type": "video",
      "uri": "YOUR_FILE_URI",
      "mime_type": "video/mp4"
    }
  ]
}

音訊分析 ​

json
{
  "model": "gemini-3.7-flash",
  "input": [
    {"type": "text", "text": "Transcribe and summarize this audio."},
    {
      "type": "audio",
      "uri": "YOUR_FILE_URI",
      "mime_type": "audio/wav"
    }
  ]
}

文件分析 ​

PDF 與其他文件請先透過 Files API 上傳，再引用其 URI：

json
{
  "model": "gemini-3.7-flash",
  "input": [
    {"type": "text", "text": "Summarize the key points in this document."},
    {
      "type": "document",
      "uri": "YOUR_FILE_URI",
      "mime_type": "application/pdf"
    }
  ]
}

請求範例 ​

執行方式見多語言範例說明。先設定 API_KEY，並替換模型、檔案網址及 ID 占位值；四種方式會顯示相同請求的原始回應。

bash
curl --fail-with-body --silent --show-error --max-time 180 \
  --request POST \
  --url "https://api.tokatlas.ai/v1beta/interactions" \
  --header "x-goog-api-key: $API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "gemini-3.7-flash",
  "input": [
    {
      "type": "text",
      "text": "Describe this image in detail."
    },
    {
      "type": "image",
      "uri": "YOUR_FILE_URI",
      "mime_type": "image/jpeg"
    }
  ]
}'
python
import os
import requests

headers = {
    'x-goog-api-key': os.environ["API_KEY"],
    'Content-Type': 'application/json',
}
payload = {'model': 'gemini-3.7-flash',
 'input': [{'type': 'text', 'text': 'Describe this image in detail.'},
           {'type': 'image', 'uri': 'YOUR_FILE_URI', 'mime_type': 'image/jpeg'}]}
response = requests.request(
    'POST', 'https://api.tokatlas.ai/v1beta/interactions', headers=headers,
    json=payload,
    timeout=180,
)
response.raise_for_status()
print(response.text)
js
if (!process.env.API_KEY) throw new Error("Set API_KEY first.");
const response = await fetch("https://api.tokatlas.ai/v1beta/interactions", {
  method: "POST",
  headers: {
    "x-goog-api-key": process.env.API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
  "model": "gemini-3.7-flash",
  "input": [
    {
      "type": "text",
      "text": "Describe this image in detail."
    },
    {
      "type": "image",
      "uri": "YOUR_FILE_URI",
      "mime_type": "image/jpeg"
    }
  ]
}),
  signal: AbortSignal.timeout(180_000),
});
if (!response.ok) {
  throw new Error(`HTTP ${response.status}: ${await response.text()}`);
}
console.log(await response.text());
java
import java.net.URI;
import java.net.http.*;
import java.time.Duration;

public class Example {
    public static void main(String[] args) throws Exception {
        String apiKey = System.getenv("API_KEY");
        if (apiKey == null || apiKey.isBlank()) {
            throw new IllegalArgumentException("Set API_KEY first.");
        }
        String payload = String.join("\n",
            "{",
            "  \"model\": \"gemini-3.7-flash\",",
            "  \"input\": [",
            "    {",
            "      \"type\": \"text\",",
            "      \"text\": \"Describe this image in detail.\"",
            "    },",
            "    {",
            "      \"type\": \"image\",",
            "      \"uri\": \"YOUR_FILE_URI\",",
            "      \"mime_type\": \"image/jpeg\"",
            "    }",
            "  ]",
            "}"
        );
        HttpClient client = HttpClient.newBuilder()
            .connectTimeout(Duration.ofSeconds(30)).build();
        HttpRequest request = HttpRequest.newBuilder()
            .uri(URI.create("https://api.tokatlas.ai/v1beta/interactions"))
            .timeout(Duration.ofSeconds(180))
            .header("x-goog-api-key", apiKey)
            .header("Content-Type", "application/json")
            .method("POST", HttpRequest.BodyPublishers.ofString(payload))
            .build();
        HttpResponse<String> response = client.send(
            request, HttpResponse.BodyHandlers.ofString());
        if (response.statusCode() < 200 || response.statusCode() >= 300) {
            throw new IllegalStateException("HTTP " + response.statusCode() + ": "
                + response.body());
        }
        System.out.println(response.body());
    }
}

回應範例 ​

json
{
  "id": "interaction_abc123",
  "model": "gemini-3.7-flash",
  "steps": [
    {
      "type": "model_output",
      "content": [
        {
          "type": "text",
          "text": "The image shows a vintage acoustic guitar with a sunburst finish, positioned against a dark background..."
        }
      ]
    }
  ],
  "status": "completed"
}

相關主題 ​