Skip to content

Is multimodal video possible with Gemini 1.5 flash? #43

Description

@tsaneyoshi

if so, Can you please provide me some sample code for the multimodal video?

This is my working code, Multimodal image.

`function AiFunction($text, $instructions, $image_urls = []) {
global $GOOGLE_AI_CLIENT;
logInfo("Input text: " . $text);
logInfo("Image URLs: " . json_encode($image_urls));

$messages = [
new TextPart($instructions . "" . $text . "")
];
foreach ($image_urls as $image_url) {
if (filter_var($image_url, FILTER_VALIDATE_URL)) {
$image_data = file_get_contents($image_url);
if ($image_data !== false && strlen($image_data) > 0) {
$messages[] = new ImagePart(
MimeType::IMAGE_JPEG,
base64_encode($image_data)
);
} else {
logInfo("Failed to fetch image data from URL: " . $image_url);
}
} else {
logInfo("Invalid image URL: " . $image_url);
}
}
try {
$response = $GOOGLE_AI_CLIENT->geminiProFlash1_5()->generateContent(...$messages);
return $response->text();
} catch (Exception $e) {
logError($e->getMessage());
throw new Exception("Error processing the request.");
}
}`

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions