Videos verstehen

from google import genai
import base64

client = genai.Client()

myfile = client.files.upload(file="path/to/sample.mp4")

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input=[
        {"type": "video", "uri": myfile.uri, "mime_type": myfile.mime_type},
        {"type": "text", "text": "Summarize this video. Then create a quiz with an answer key based on the information in this video."}
    ]
)

print(interaction.steps[-1].content[0].text)

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

const ai = new GoogleGenAI({});

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

  const interaction = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: [
      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(interaction.steps.at(-1).content[0].text);
}

await main();

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" \
  -H "x-goog-api-key: $GEMINI_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}"

echo "Generating content from video..."
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -H 'Content-Type: application/json' \
    -d '{
      "model": "gemini-3-flash-preview",
      "input": [
        {"type": "video", "uri": "'${file_uri}'", "mime_type": "'${MIME_TYPE}'"},
        {"type": "text", "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 ".steps[].content[0].text" response.json

from google import genai

video_file_name = "/path/to/your/video.mp4"
video_bytes = open(video_file_name, 'rb').read()

client = genai.Client()
interaction = client.interactions.create(
    model='gemini-3-flash-preview',
    input=[
        {"type": "text", "text": "Please summarize the video in 3 sentences."},
        {
            "type": "video",
            "data": base64.b64encode(video_bytes).decode('utf-8'),
            "mime_type": "video/mp4"
        }
    ]
)
print(interaction.steps[-1].content[0].text)

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

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

const interaction = await ai.interactions.create({
  model: "gemini-3-flash-preview",
  input: [
    { type: "text", text: "Please summarize the video in 3 sentences." },
    {
      type: "video",
      data: base64VideoFile,
      mime_type: "video/mp4",
    }
  ],
});
console.log(interaction.steps.at(-1).content[0].text);

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

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

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -H 'Content-Type: application/json' \
    -d '{
      "model": "gemini-3-flash-preview",
      "input": [
        {"type": "text", "text": "Please summarize the video in 3 sentences."},
        {
          "type": "video",
          "data": "'$(base64 $B64FLAGS $VIDEO_PATH)'",
          "mime_type": "video/mp4"
        }
      ]
    }' 2> /dev/null

from google import genai

client = genai.Client()
interaction = client.interactions.create(
    model='gemini-3-flash-preview',
    input=[
        {"type": "text", "text": "Please summarize the video in 3 sentences."},
        {
            "type": "video",
            "uri": "https://www.youtube.com/watch?v=9hE5-98ZeCg"
        }
    ]
)
print(interaction.steps[-1].content[0].text)

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

const interaction = await ai.interactions.create({
  model: "gemini-3-flash-preview",
  input: [
    { type: "text", text: "Please summarize the video in 3 sentences." },
    {
      type: "video",
      uri: "https://www.youtube.com/watch?v=9hE5-98ZeCg",
    }
  ],
});
console.log(interaction.steps.at(-1).content[0].text);

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -H 'Content-Type: application/json' \
    -d '{
      "model": "gemini-3-flash-preview",
      "input": [
        {"type": "text", "text": "Please summarize the video in 3 sentences."},
        {
          "type": "video",
          "uri": "https://www.youtube.com/watch?v=9hE5-98ZeCg"
        }
      ]
    }' 2> /dev/null

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

const prompt = "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?"

prompt = "Describe the key events in this video, providing both audio and visual details. Include timestamps for salient moments."

const prompt = "Describe the key events in this video, providing both audio and visual details. Include timestamps for salient moments.";

PROMPT="Describe the key events in this video, providing both audio and visual details. Include timestamps for salient moments."