> For the complete documentation index, see [llms.txt](https://pixyleai.gitbook.io/pixyle.ai-documentation/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://pixyleai.gitbook.io/pixyle.ai-documentation/welcome-to-pixyle.ai/glossary.md).

# Glossary

The Glossary contains definitions of key terms, concepts, and labels used throughout the AI solution. It’s designed to help you feel confident and comfortable with the terminology behind Pixyle.ai’s processes and data attributes.

**Fashion item:**\
A fashion item is any article or accessory of clothing, footwear, or other wearable items. Understanding what counts as a fashion item helps ensure accurate tagging and categorization.

**Primary Product:**\
The primary product is the main fashion item recognized by Pixyle.ai models. It is the product being sold in the image(s) and the one for which data should be generated. Correctly identifying the primary product is key for precise data enrichment.

**Primary Image:**\
The primary image is the product photo detected as the best visual representation of the primary product. This ensures your AI-generated tags reflect the most relevant image.

**Collection:**\
A collection is a data structure used to group multiple products together. It is also known as a dataset. Grouping products this way helps streamline bulk processing and management.

**Collection processing:**\
Involves bulk processing of a collection of products. The system accepts a file containing multiple products, processing each one sequentially upon upload. Results for each product are available as soon as its processing is completed.

**Real-time processing:**\
Real-time processing is the analysis of one image or product at a time, with results immediately available for further processing. This allows you to see instant feedback and act on it without delay.

**Taxonomy:**\
A taxonomy is a hierarchical classification system made up of a structured set of tags. It is used to classify images based on visual characteristics, content, or attributes. Taxonomy is relevant only for Automatic Tagging and defines the structure in which generated data will be returned, giving you clarity and consistency.

**Tag:**\
A tag is a label or keyword assigned to images or items to categorize, classify, or organize data. A tag can represent either a category or an attribute, making it easier to navigate and analyze your catalog.

**Confidence Score:**\
A confidence score is a numerical value indicating the model’s level of certainty in a prediction. Higher scores mean the AI is more confident, helping you trust and prioritize results effectively.

**Verification Process:**\
The verification process represents the Human-in-the-loop (HITL) concept. It is a workflow in which a human reviews AI-generated data and approves or corrects it. Once a product’s verification process is complete, its data is reviewed and ready for further use. Whenever possible, a quick human review ensures the highest accuracy, giving you peace of mind before implementation.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://pixyleai.gitbook.io/pixyle.ai-documentation/welcome-to-pixyle.ai/glossary.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.