動画理解

import {
  GoogleGenAI,
  createUserContent,
  createPartFromUri,
} from "@google/genai";

const ai = new GoogleGenAI({ apiKey: "GOOGLE_API_KEY" });

async function main() {
  const myfile = await ai.files.upload({
    file: "path/to/sample.mp4",
    config: { mimeType: "video/mp4" },
  });

  const response = await ai.models.generateContent({
    model: "gemini-2.0-flash",
    contents: createUserContent([
      createPartFromUri(myfile.uri, myfile.mimeType),
      "Summarize this video. Then create a quiz with an answer key based on the information in this video.",
    ]),
  });
  console.log(response.text);
}

await main();

file, err := client.UploadFileFromPath(ctx, "path/to/sample.mp4", nil)
if err != nil {
    log.Fatal(err)
}
defer client.DeleteFile(ctx, file.Name)

model := client.GenerativeModel("gemini-2.0-flash")
resp, err := model.GenerateContent(ctx,
    genai.FileData{URI: file.URI},
    genai.Text("Summarize this video. Then create a quiz with an answer key based on the information in this video."))
if err != nil {
    log.Fatal(err)
}

printResponse(resp)

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

import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";

const ai = new GoogleGenAI({ apiKey: "GOOGLE_API_KEY" });
const base64VideoFile = fs.readFileSync("path/to/small-sample.mp4", {
  encoding: "base64",
});

const contents = [
  {
    inlineData: {
      mimeType: "video/mp4",
      data: base64VideoFile,
    },
  },
  { text: "Please summarize the video in 3 sentences." }
];

const response = await ai.models.generateContent({
  model: "gemini-2.0-flash",
  contents: contents,
});
console.log(response.text);

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

import { GoogleGenerativeAI } from "@google/generative-ai";

const genAI = new GoogleGenerativeAI(process.env.GOOGLE_API_KEY);
const model = genAI.getGenerativeModel({ model: "gemini-1.5-pro" });
const result = await model.generateContent([
  "Please summarize the video in 3 sentences.",
  {
    fileData: {
      fileUri: "https://www.youtube.com/watch?v=9hE5-98ZeCg",
    },
  },
]);
console.log(result.response.text());

ctx := context.Background()
client, err := genai.NewClient(ctx, option.WithAPIKey(os.Getenv("GOOGLE_API_KEY")))
if err != nil {
  log.Fatal(err)
}
defer client.Close()

model := client.GenerativeModel("gemini-2.0-flash")
resp, err := model.GenerateContent(ctx,
  genai.FileData{URI: "https://www.youtube.com/watch?v=9hE5-98ZeCg"},
  genai.Text("Please summarize the video in 3 sentences."))
if err != nil {
  log.Fatal(err)
}

// Handle the response of generated text.
for _, c := range resp.Candidates {
  if c.Content != nil {
    fmt.Println(*c.Content)
  }
}

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":[
            {"text": "Please summarize the video in 3 sentences."},
            {
              "file_data": {
                "file_uri": "https://www.youtube.com/watch?v=9hE5-98ZeCg"
              }
            }
        ]
      }]
    }' 2> /dev/null

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

    prompt := []genai.Part{
        genai.FileData{URI: currentVideoFile.URI, MIMEType: currentVideoFile.MIMEType},
         // Adjusted timestamps for the NASA video
        genai.Text("What are the examples given at 00:05 and " +
            "00:10 supposed to show us?"),
    }

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

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

    prompt := []genai.Part{
        genai.FileData{URI: currentVideoFile.URI, MIMEType: currentVideoFile.MIMEType},
        genai.Text("Transcribe the audio from this video, giving timestamps for salient events in the video. Also " +
            "provide visual descriptions."),
    }

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