视频理解

VIDEO_PATH="path/to/sample.mp4"
MIME_TYPE=$(file -b --mime-type "${VIDEO_PATH}")
NUM_BYTES=$(wc -c < "${VIDEO_PATH}")
DISPLAY_NAME=VIDEO

tmp_header_file=upload-header.tmp

echo "Starting file upload..."
curl "https://generativelanguage.googleapis.com/upload/v1beta/files?key=${GOOGLE_API_KEY}" \
  -D ${tmp_header_file} \
  -H "X-Goog-Upload-Protocol: resumable" \
  -H "X-Goog-Upload-Command: start" \
  -H "X-Goog-Upload-Header-Content-Length: ${NUM_BYTES}" \
  -H "X-Goog-Upload-Header-Content-Type: ${MIME_TYPE}" \
  -H "Content-Type: application/json" \
  -d "{'file': {'display_name': '${DISPLAY_NAME}'}}" 2> /dev/null

upload_url=$(grep -i "x-goog-upload-url: " "${tmp_header_file}" | cut -d" " -f2 | tr -d "\r")
rm "${tmp_header_file}"

echo "Uploading video data..."
curl "${upload_url}" \
  -H "Content-Length: ${NUM_BYTES}" \
  -H "X-Goog-Upload-Offset: 0" \
  -H "X-Goog-Upload-Command: upload, finalize" \
  --data-binary "@${VIDEO_PATH}" 2> /dev/null > file_info.json

file_uri=$(jq -r ".file.uri" file_info.json)
echo file_uri=$file_uri

echo "File uploaded successfully. File URI: ${file_uri}"

# --- 3. Generate content using the uploaded video file ---
echo "Generating content from video..."
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=$GOOGLE_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [{
        "parts":[
          {"file_data":{"mime_type": "'"${MIME_TYPE}"'", "file_uri": "'"${file_uri}"'"}},
          {"text": "Summarize this video. Then create a quiz with an answer key based on the information in this video."}]
        }]
      }' 2> /dev/null > response.json

jq -r ".candidates[].content.parts[].text" response.json

VIDEO_PATH=/path/to/your/video.mp4

if [[ "$(base64 --version 2>&1)" = *"FreeBSD"* ]]; then
  B64FLAGS="--input"
else
  B64FLAGS="-w0"
fi

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=$GOOGLE_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [{
        "parts":[
            {
              "inline_data": {
                "mime_type":"video/mp4",
                "data": "'$(base64 $B64FLAGS $VIDEO_PATH)'"
              }
            },
            {"text": "Please summarize the video in 3 sentences."}
        ]
      }]
    }' 2> /dev/null

PROMPT="What are the examples given at 00:05 and 00:10 supposed to show us?"

PROMPT="Transcribe the audio from this video, giving timestamps for salient events in the video. Also provide visual descriptions."