# TextFromImage
Get descriptions of images using OpenAI's GPT models, Azure OpenAI, and Anthropic Claude in an easy way.
## Installation
You can install the textfromimage package via PyPI using pip:
```bash
pip install textfromimage
```
## Usage
The textfromimage package is now class-based, allowing you to initialize the TextFromImage class with your desired configurations and use its methods to obtain image descriptions.
**Using OpenAI**
```bash
import textfromimage
# Option 1: Initialize OpenAI client with API key
textfromimage.openai.init(api_key="your-openai-api-key")
# Option 2: Set your OpenAI API key as an environment variable
# import os
# os.environ['OPENAI_API_KEY'] = 'your-openai-api-key'
# Get a description of the image using OpenAI
image_url = 'https://example.com/image.jpg'
openai_description = textfromimage.openai.get_description(
image_url=image_url"
)
print("OpenAI Description:", openai_description)
```
**Using Anthropic Claude**
```bash
import textfromimage
# Option 1: Initialize Anthropic Claude client with API key
textfromimage.claude.init(api_key="your-anthropic-api-key")
# Option 2: Set your Anthropic API key as an environment variable
# import os
# os.environ['ANTHROPIC_API_KEY'] = 'your-anthropic-api-key'
# Get a description of the image using Anthropic Claude
image_url = 'https://example.com/image.jpg'
claude_description = textfromimage.claude.get_description(
image_url=image_url"
)
print("Claude Description:", claude_description)
```
**Using Azure OpenAI**
```bash
import textfromimage
# Option 1: Initialize Azure OpenAI client with necessary parameters
textfromimage.azure_openai.init(
api_key="your-azure-openai-api-key",
api_base="https://your-azure-endpoint.openai.azure.com/",
deployment_name="your-deployment-name"
)
# Option 2: Set your Azure OpenAI credentials as environment variables
# import os
# os.environ['AZURE_OPENAI_API_KEY'] = 'your-azure-openai-api-key'
# os.environ['AZURE_OPENAI_ENDPOINT'] = 'https://your-azure-endpoint.openai.azure.com/'
# os.environ['AZURE_OPENAI_DEPLOYMENT'] = 'your-deployment-name'
# Get a description of the image using Azure OpenAI
image_url = 'https://example.com/image.jpg'
azure_description = textfromimage.azure_openai.get_description(
image_url=image_url"
)
print("Azure OpenAI Description:", azure_description)
```
**Specifying a Different Model**
You can specify a different OpenAI model if needed. By default, the model is set to "gpt-4o".
```bash
import textfromimage
# Option 1: Initialize OpenAI client with API key
textfromimage.openai.init(api_key="your-openai-api-key")
# Option 2: Set your OpenAI API key as an environment variable
# import os
# os.environ['OPENAI_API_KEY'] = 'your-openai-api-key'
# Get a description of the image using OpenAI
image_url = 'https://example.com/image.jpg'
openai_description = textfromimage.openai.get_description(
image_url=image_url,
model='gpt-4o-mini'"
)
print("OpenAI Description:", openai_description)
```
## Parameters
- image_url (str): The URL of the image.
- prompt (str, optional): The prompt for the description (default: "What's in this image?").
- model (str, optional): The OpenAI model to use (default: "gpt-4o").
- api_key (str, optional): Your OpenAI API key.
## Contributing
Contributions are welcome! Please follow these steps:
1. Fork the repository.
2. Create a new branch (git checkout -b feature/YourFeature).
3. Commit your changes (git commit -m 'Add some feature').
4. Push to the branch (git push origin feature/YourFeature).
5. Open a pull request.
Raw data
{
"_id": null,
"home_page": "https://github.com/OrenGrinker/textfromimage",
"name": "textfromimage",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.9",
"maintainer_email": null,
"keywords": "openai gpt-4 claude azure-openai computer-vision image-to-text ai machine-learning",
"author": "Oren Grinker",
"author_email": "orengr4@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/d8/6f/691ca522825e36a28f0ca18db17d668d02f8ae8c3a32c8d6cefeb2db46c0/textfromimage-0.3.1.tar.gz",
"platform": null,
"description": "# TextFromImage\n\nGet descriptions of images using OpenAI's GPT models, Azure OpenAI, and Anthropic Claude in an easy way.\n\n## Installation\nYou can install the textfromimage package via PyPI using pip:\n```bash\npip install textfromimage\n```\n\n## Usage\nThe textfromimage package is now class-based, allowing you to initialize the TextFromImage class with your desired configurations and use its methods to obtain image descriptions.\n\n**Using OpenAI**\n```bash\nimport textfromimage\n\n# Option 1: Initialize OpenAI client with API key\ntextfromimage.openai.init(api_key=\"your-openai-api-key\")\n\n# Option 2: Set your OpenAI API key as an environment variable\n# import os\n# os.environ['OPENAI_API_KEY'] = 'your-openai-api-key'\n\n# Get a description of the image using OpenAI\nimage_url = 'https://example.com/image.jpg'\nopenai_description = textfromimage.openai.get_description(\n image_url=image_url\"\n)\nprint(\"OpenAI Description:\", openai_description)\n```\n\n**Using Anthropic Claude**\n```bash\nimport textfromimage\n\n# Option 1: Initialize Anthropic Claude client with API key\ntextfromimage.claude.init(api_key=\"your-anthropic-api-key\")\n\n# Option 2: Set your Anthropic API key as an environment variable\n# import os\n# os.environ['ANTHROPIC_API_KEY'] = 'your-anthropic-api-key'\n\n# Get a description of the image using Anthropic Claude\nimage_url = 'https://example.com/image.jpg'\nclaude_description = textfromimage.claude.get_description(\n image_url=image_url\"\n)\nprint(\"Claude Description:\", claude_description)\n```\n\n**Using Azure OpenAI**\n```bash\nimport textfromimage\n\n# Option 1: Initialize Azure OpenAI client with necessary parameters\ntextfromimage.azure_openai.init(\n api_key=\"your-azure-openai-api-key\",\n api_base=\"https://your-azure-endpoint.openai.azure.com/\",\n deployment_name=\"your-deployment-name\"\n)\n\n# Option 2: Set your Azure OpenAI credentials as environment variables\n# import os\n# os.environ['AZURE_OPENAI_API_KEY'] = 'your-azure-openai-api-key'\n# os.environ['AZURE_OPENAI_ENDPOINT'] = 'https://your-azure-endpoint.openai.azure.com/'\n# os.environ['AZURE_OPENAI_DEPLOYMENT'] = 'your-deployment-name'\n\n# Get a description of the image using Azure OpenAI\nimage_url = 'https://example.com/image.jpg'\nazure_description = textfromimage.azure_openai.get_description(\n image_url=image_url\"\n)\nprint(\"Azure OpenAI Description:\", azure_description)\n```\n\n**Specifying a Different Model**\n\nYou can specify a different OpenAI model if needed. By default, the model is set to \"gpt-4o\".\n```bash\nimport textfromimage\n\n# Option 1: Initialize OpenAI client with API key\ntextfromimage.openai.init(api_key=\"your-openai-api-key\")\n\n# Option 2: Set your OpenAI API key as an environment variable\n# import os\n# os.environ['OPENAI_API_KEY'] = 'your-openai-api-key'\n\n# Get a description of the image using OpenAI\nimage_url = 'https://example.com/image.jpg'\nopenai_description = textfromimage.openai.get_description(\n image_url=image_url,\n model='gpt-4o-mini'\"\n)\nprint(\"OpenAI Description:\", openai_description)\n```\n\n## Parameters\n\n- image_url (str): The URL of the image.\n- prompt (str, optional): The prompt for the description (default: \"What's in this image?\").\n- model (str, optional): The OpenAI model to use (default: \"gpt-4o\").\n- api_key (str, optional): Your OpenAI API key.\n\n\n## Contributing\nContributions are welcome! Please follow these steps:\n\n1. Fork the repository.\n2. Create a new branch (git checkout -b feature/YourFeature).\n3. Commit your changes (git commit -m 'Add some feature').\n4. Push to the branch (git push origin feature/YourFeature).\n5. Open a pull request.\n",
"bugtrack_url": null,
"license": null,
"summary": "Get descriptions of images from OpenAI, Azure OpenAI, and Anthropic Claude models in an easy way.",
"version": "0.3.1",
"project_urls": {
"Homepage": "https://github.com/OrenGrinker/textfromimage"
},
"split_keywords": [
"openai",
"gpt-4",
"claude",
"azure-openai",
"computer-vision",
"image-to-text",
"ai",
"machine-learning"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "6dede768fe638dd410e4e6ac553f4a62323770117ed96ef82fe453976bcfe6ad",
"md5": "051988669285d83db7b59b0f26194d59",
"sha256": "700f5b11c1fc260849747b3eb4db99e18d557f78189b9d86f78716068e733c46"
},
"downloads": -1,
"filename": "textfromimage-0.3.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "051988669285d83db7b59b0f26194d59",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.9",
"size": 6569,
"upload_time": "2024-11-21T14:20:15",
"upload_time_iso_8601": "2024-11-21T14:20:15.233212Z",
"url": "https://files.pythonhosted.org/packages/6d/ed/e768fe638dd410e4e6ac553f4a62323770117ed96ef82fe453976bcfe6ad/textfromimage-0.3.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "d86f691ca522825e36a28f0ca18db17d668d02f8ae8c3a32c8d6cefeb2db46c0",
"md5": "26a99ced97a85cd5f9b4d7fbf8b0c406",
"sha256": "cc9eba3593cda4bbc50c6f8eda96edacde492791fa6da777b004cea91ccbdbf3"
},
"downloads": -1,
"filename": "textfromimage-0.3.1.tar.gz",
"has_sig": false,
"md5_digest": "26a99ced97a85cd5f9b4d7fbf8b0c406",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.9",
"size": 6125,
"upload_time": "2024-11-21T14:20:16",
"upload_time_iso_8601": "2024-11-21T14:20:16.424579Z",
"url": "https://files.pythonhosted.org/packages/d8/6f/691ca522825e36a28f0ca18db17d668d02f8ae8c3a32c8d6cefeb2db46c0/textfromimage-0.3.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-11-21 14:20:16",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "OrenGrinker",
"github_project": "textfromimage",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [],
"lcname": "textfromimage"
}
JSON
