동영상 챕터 추출

동영상의 챕터를 구조화된 JSON으로 추출

모델을 직접 쿼리하고 Cloud 콘솔에서 다른 매개변수 값을 사용하거나 Vertex AI API를 직접 호출하여 반환된 결과를 테스트할 수 있습니다.

자유 형식 프롬프트

동영상 콘텐츠를 챕터로 그룹화하고 각 챕터의 요약을 제공하여 동영상 콘텐츠를 구분합니다. 주요 이벤트와 하이라이트만 포착하세요. 확실하지 않은 정보가 있으면 정보를 제공하지 마세요. 'timecode', 'chapterSummary' 등의 키를 사용하여 JSON 형식으로 결과를 반환합니다.

응답


[
  {
    "timecode": "00:00-00:16",
    "chapterSummary": "The video opens with breathtaking aerial views of Rio de Janeiro, showcasing iconic landmarks such as Sugarloaf Mountain and the Christ the Redeemer statue. It then transitions to scenes of the vibrant beach culture and the bustling city life."
  },
  {
    "timecode": "00:16-00:36",
    "chapterSummary": "The video shifts its focus to the favelas, highlighting the stark contrast between the affluent areas of Rio and these underserved communities. It emphasizes the negative stereotypes associated with favelas, often portrayed through news reports as hubs of crime, poverty, and violence."
  },
  {
    "timecode": "00:36-00:57",
    "chapterSummary": "The video introduces Google's initiative to collaborate with favela residents in mapping their communities. It underscores the importance of providing favelas with a sense of identity and recognition by giving them addresses and making them visible on maps. The chapter emphasizes that favelas are not just places but communities with rich cultures and resilient people."
  }
]
모델: gemini-1.5-pro-preview-0409
강도: 1
최대 출력 토큰: 8192
최상위 K: 40
최상위 P: 0.95