Skip to main content

A module to generate captions for images using Google AI's Vertex AI Platform.

Project description

ImageTextCaptions

A Python module to generate captions for images using Google AI's Vertex AI Platform.

Overview

The ImageTextCaptions class provides an intuitive interface for generating textual captions for images. By simply passing a base64 encoded image, users can get insightful and accurate captions for their visual content.

Features

  • Easy integration with Google AI's Vertex AI Platform.
  • Support for custom Google Cloud Project IDs.
  • Flexibility to use either a Google Cloud credentials file or rely on gcloud auth.
  • Option to set a custom base URL for the API endpoint.

Installation

Ensure you have the required libraries:

pip install requests google-auth

Usage

Convert Image to Base64:

import base64

def convert_image_to_base64(image_path):
    with open(image_path, "rb") as image_file:
        return base64.b64encode(image_file.read()).decode('utf-8')

Generate Captions:

from imagetext_captions import ImageTextCaptions

# Convert your image to base64
b64_image = convert_image_to_base64("path_to_your_image.jpg")

# Instantiate with your Google Cloud Project ID
captions = ImageTextCaptions("YOUR_PROJECT_ID")

# Define the number of responses you want and the language code
response_count = 1
language_code = "en"

# Generate captions
response = captions.caption(b64_image, response_count, language_code)

# Print the captions from the response
for caption in response["predictions"]:
    print(caption)

Using a Google Cloud Credentials File:

captions = ImageTextCaptions("YOUR_PROJECT_ID", credentials_path="path_to_your_google_cloud_credentials.json")

Specifying a Custom Base URL:

custom_url = "https://your_custom_base_url/v1/projects/{project_id}/locations/some_location/publishers/google/models/imagetext:predict"
captions = ImageTextCaptions("YOUR_PROJECT_ID", base_url=custom_url)

Contributions

Contributions are welcome! If you find any issues or have suggestions for improvements, please submit a pull request or open an issue.

License

This project is licensed under the MIT License.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ImageTextCaptions-0.1.0.tar.gz (2.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

ImageTextCaptions-0.1.0-py3-none-any.whl (3.5 kB view details)

Uploaded Python 3

File details

Details for the file ImageTextCaptions-0.1.0.tar.gz.

File metadata

  • Download URL: ImageTextCaptions-0.1.0.tar.gz
  • Upload date:
  • Size: 2.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.11.4

File hashes

Hashes for ImageTextCaptions-0.1.0.tar.gz
Algorithm Hash digest
SHA256 a4fda8e0f1b219eb338260e814655a10c695a1ac565061980400d4179b5da998
MD5 acbd13f8a705eaa40349375cd93e09b3
BLAKE2b-256 0a6479f19dd7b565e064637708cd3a985ef0a30094204ee458a5fb3f6b999147

See more details on using hashes here.

File details

Details for the file ImageTextCaptions-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for ImageTextCaptions-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 b436af4909f106cb5b7612d3b674761a314b96c3b68ac14cbb25f296ea3c1348
MD5 c23dfc170ccffc63bb5a7efbb1ced6a0
BLAKE2b-256 7c203099a3c513d5cc2a96813c6456f466d499f9239ae963a738a01757e1d437

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page