To help you get the most value from AI Configurations in the PIM, we strongly recommend following the guides below:
- AI Configuration Overview
- Creating & Managing AI Configuration
- Executing AI Configurations
- Useful AI Configurations Examples
- AI Prompt Analyzer & Rewriter
- AI Configuration Considerations & Limitations (You are here!)
- Understanding AI Behaviour & Realistic Use Cases
- AI Configuration Security & Data Privacy
Overview
Akeneo’s AI enrichment features are designed for performance, reliability, and scalability.
However, because AI generation involves analyzing structured product data, assets, and prompts simultaneously, a few technical and practical limits apply.
These limits help ensure a consistent experience for all customers while maintaining data integrity and predictable performance across large catalogs.
This page explains:
- The maximum supported configuration sizes
- File type and asset restrictions
- Attribute option limits
- General performance and reliability considerations
Configuration Limits
| Type | Limit | Description |
|---|---|---|
| AI Configurations per environment | 200 | You can create up to 200 AI Configurations in a single Akeneo environment. For higher requirements, contact your Customer Success Manager. |
| Family-level prompts | Supported but not centralized | Family-level prompts created before the introduction of AI Configurations remain functional, but they are not managed from the new page. |
| Active configurations | Unlimited | You can enable as many configurations as needed within the 200 limit, but each consumes processing resources when executed. |
Recommendation:
If you manage multiple teams or product lines, organize configurations by purpose (for example, “Enrichment,” “Translation,” “Audit”) rather than creating one configuration per attribute. This keeps the total number manageable.
Attribute Option Limits
AI Configurations can generate values for select-type attributes, such as Simple Select or Multi Select.
However, these attributes have a maximum option limit.
| Attribute Type | Limit | Description |
|---|---|---|
| Simple Select / Multi Select, Reference Entity Simple / Multi Link | 500 options | AI can only process up to 500 options per attribute. Any options beyond this number are ignored during generation. |
Best Practice:
If you have a very large list of select options, consider grouping or filtering them in advance to keep the set below 500.
Supported Asset Types
When assets (images or documents) are included in an AI Configuration, Akeneo automatically analyzes them to extract contextual data (for example, product color, certifications, or logos). To ensure smooth processing, only certain file types are supported.
| Asset Type | Supported Formats | Notes |
|---|---|---|
| Images | JPG, JPEG, PNG, WEBP, TIFF, single-frame GIF | Used for visual analysis such as identifying dominant color, shape, or logos. |
| Documents | Only the first 20 pages are analyzed. Used for extracting structured text or key sections from technical sheets or certificates. |
Unsupported files (e.g., videos, multi-frame GIFs, or PSDs) will be skipped automatically during processing.
You can still store them in the Asset Manager, but they won’t be used by AI.
Asset Quantity and Size Limits
Each product can include a limited number of assets for AI enrichment to maintain performance consistency.
| Asset Type | Maximum Count | Total Size Limit | Additional Notes |
|---|---|---|---|
| Images | 5 | 32 MB total | AI automatically resizes large images for optimal analysis. |
| Documents (PDF) | 2 | 20 MB total | Only the first 20 pages of each PDF are processed. |
If a product contains more than the maximum number of assets, only the first ones found in the selected asset collection will be used.
Asset Collection Requirements
Only assets stored in collections that include a “main media” attribute are supported for AI processing.
This ensures that each asset has a defined primary image or document for analysis.
If you attempt to include a collection without a main media reference, it will be skipped during execution.
Tip: To verify, open your Asset Manager and check that each relevant collection includes a defined main media field.
Processing Order for Assets
When multiple assets are available, the AI prioritizes them in the following order:
- Primary images from selected asset collections
- Secondary images (if available)
- PDF documents (up to 2, in order of upload date)
This order helps ensure the AI uses the most relevant visuals first (for example, product packshots or hero images) before supplemental documentation.
Fair Usage and Performance Management
Akeneo monitors AI feature usage to ensure equitable access and performance for all customers.
While there are currently no hard usage limits, usage is tracked internally to prevent abuse and manage costs efficiently.
Future releases will introduce customer-specific fair usage thresholds, such as a maximum number of AI calls or tokens per month, depending on your plan and contract.
If your team consistently runs large-scale automation, your Akeneo representative can help evaluate suitable scaling or quota options.
Recommendation:
- Run enrichment rules in batches rather than simultaneously.
- Schedule heavy automation during off-peak hours.
- Use Preview and manual runs to test configurations before scaling.
Data Privacy and Security
All data is processed through OpenAI’s Enterprise API:
- Your data is not used to train AI models
- No data is stored after processing
- All data is transmitted securely over encrypted channels
Key Considerations for Reliable Performance
| Category | Recommendation |
|---|---|
| Prompt Size | Keep prompts concise and structured. Long or repetitive text can degrade quality |
| Attribute Selection | Limit source attributes to those directly relevant to the task. |
| Rule Frequency | Avoid excessive rule triggers (for example, 10-20 AI configurations running within 1 rule). |
| Asset Size | Compress or optimize images and PDFs before upload. |
| Parallel Rules | Run complex AI rules sequentially when possible to improve reliability. |
By following these guidelines, you can maintain high-quality, predictable AI performance across large catalogs.
Troubleshooting Common Limit Issues
| Problem | Likely Cause | Suggested Fix |
|---|---|---|
| Missing output for a product | Too many assets or unsupported file type | Reduce the number of images or use supported formats. |
| AI Configuration not listed in Rules Engine | Configuration disabled or missing code | Check that it is enabled and saved correctly. |
| Incomplete AI output | Prompt may exceed token limit or attribute context too large | Simplify the prompt or reduce the number of context attributes. |
| Inconsistent enrichment times | Large data scope or high concurrency | Schedule smaller, staggered rule executions. |
Summary
Akeneo’s AI engine is optimized for both flexibility and safety. Understanding the limits ensures you can:
- Design efficient configurations
- Avoid data overload
- Maintain high enrichment performance
- Scale confidently across your entire catalog
For detailed recommendations on AI output behavior and realistic expectations, continue to the next page:
Understanding AI Behavior and Realistic Use Cases