Generating image descriptions using Claude

Use image description to generate alt text and visual summaries from images.

Common use cases include:

  • Accessibility workflows for screen readers
  • Digital asset cataloging
  • Document enrichment for scanned reports
  • E-learning content description
  • Archive and metadata generation

This guide uses Claude as the VLM provider through Nutrient Vision API.

Download sample

How Nutrient helps

Nutrient Python SDK handles provider configuration, request handling, and response parsing.

The SDK handles:

  • API authentication and endpoint configuration
  • Image encoding and multimodal request payloads
  • Model settings such as temperature and token limits
  • Vision API failures and rate-limit handling

Complete implementation

This example generates an image description using Claude:

from nutrient_sdk import Document, Vision
from nutrient_sdk import VlmProvider

Configuring the Claude provider

Open the image in a context manager(opens in a new tab) and configure Claude as the provider.

In this sample:

  • vision_settings.provider = VlmProvider.CLAUDE selects Claude.
  • claude_api_settings.api_key sets the Anthropic API key.
  • Input can be PNG, JPEG, GIF, BMP, or TIFF.
with Document.open("input_photo.png") as document:
    # Configure Claude as the VLM provider
    document.settings.vision_settings.provider = VlmProvider.CLAUDE


    # Set the Claude API key
    document.settings.claude_api_settings.api_key = "CLAUDE_API_KEY"

Creating a vision instance and generating the description

Create a vision instance and call describe() to generate text.

In this sample:

  • Vision.set(document) binds processing to the opened image.
  • vision.describe() returns a description string.
  • The SDK handles encoding, request construction, and response parsing.
    vision = Vision.set(document)
    description = vision.describe()

Outputting the description

Print the description for review, or store it in your application.

Common destinations include:

  • Database fields
  • JSON output files
  • HTML alt attributes
    print("Image description:")
    print(description)

Understanding the output

describe() returns natural language text for accessibility and content understanding.

Claude descriptions are typically:

  • Concise — Focused on key subjects and details, often one to three sentences
  • Accessible — Suitable for users who rely on screen readers
  • Accurate — Based on visible content only
  • Contextual — Include relevant relationships and scene context

Use this output for accessibility metadata, image search, and document workflows.

Claude API settings

The Claude provider uses these claude_api_settings properties:

  • api_endpoint — The Claude API endpoint (default: https://api.anthropic.com/v1/).
  • api_key — Your Anthropic API key for authentication.
  • model — The model identifier to use (default: claude-sonnet-4-5).
  • temperature — Controls response creativity (0.0 = deterministic, 1.0 = creative).
  • max_tokens — Maximum tokens in the response (default: 16384).

Error handling

The SDK raises NutrientException when vision operations fail.

Common failure scenarios include:

  • The input image can’t be read due to path, permission, or format issues
  • The Claude API key is missing or invalid
  • The Claude API is unavailable
  • Rate limits are exceeded
  • Network requests fail before reaching the API
  • Image data is too large or corrupted

In production code:

  • Catch NutrientException.
  • Return a clear error message.
  • Log failure details for debugging.
  • Add retry logic for transient API failures.

Conclusion

Use this workflow to generate image descriptions with Claude:

  1. Open the image file using a context manager(opens in a new tab) for automatic resource cleanup.
  2. The SDK supports multiple image formats, including PNG, JPEG, GIF, BMP, and TIFF.
  3. Access the vision settings with document.settings.vision_settings.provider to configure the VLM provider.
  4. Set the provider to Claude with the property assignment VlmProvider.CLAUDE instead of alternatives like OpenAI or local models.
  5. Access Claude-specific settings with document.settings.claude_api_settings for API configuration.
  6. Set the Anthropic API key with property assignment using credentials obtained from the Anthropic Console.
  7. Claude API settings control endpoint URLs, model selection (default: claude-sonnet-4-5), temperature, and max tokens.
  8. Create a vision instance with Vision.set() bound to the document with configured provider settings.
  9. Generate the description with vision.describe(), which sends the image to Claude’s vision endpoint and returns natural language text.
  10. The SDK encodes image data, constructs multimodal API requests, and parses responses automatically.
  11. Generated descriptions are concise (1–3 sentences), accessible (WCAG-compliant alt text), accurate (observable details only), and contextual.
  12. Print or save the description for use in accessibility systems, content management, or cataloging workflows.
  13. Handle NutrientException for vision processing failures, including authentication errors, API failures, and rate limits.
  14. The context manager ensures proper resource cleanup when processing completes or exceptions occur.

For related image workflows, refer to the Python SDK guides.

Download this ready-to-use sample package to explore Claude-based image description.