视频理解

curl "https://api.omnirelay.ai/v1beta/models/gemini-3.1-pro-preview:generateContent" \
  -H "x-goog-api-key: $OMNIRELAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "role": "user",
      "parts": [
        {"fileData": {"mimeType": "video/mp4", "fileUri": "https://example.com/clip.mp4"}},
        {"text": "请结合视频画面和音频进行详细解析，用中文输出 JSON。包含 summary（整体摘要）、timeline（事件数组，每项包含 start_time、end_time、visual_description、audio_summary）、visible_text（可辨认的画面文字数组）。看不清或听不清的内容标记为无法确认，不要编造。"}
      ]
    }],
    "generationConfig": {"responseMimeType": "application/json", "maxOutputTokens": 8192}
  }'

from google import genai
from google.genai import types

client = genai.Client(
    api_key=OMNIRELAY_API_KEY,
    http_options=types.HttpOptions(base_url="https://api.omnirelay.ai"),
)
response = client.models.generate_content(
    model="gemini-3.1-pro-preview",
    contents=[
        types.Part.from_uri(file_uri="https://example.com/clip.mp4", mime_type="video/mp4"),
        "请结合视频画面和音频进行解析，输出包含 summary、timeline、visible_text 的 JSON。",
    ],
    config=types.GenerateContentConfig(response_mime_type="application/json", max_output_tokens=8192),
)
print(response.text)