> For the complete documentation index, see [llms.txt](https://userflux.gitbook.io/userflux-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://userflux.gitbook.io/userflux-docs/feature-guides/data-management/product-catalog.md).
# Product Catalog
The Product Catalogue is where you define the structure of your product data and inspect the items you have synced. By creating a **schema**—a blueprint for your product data—you enable the system to understand, organise, and utilise your product information for advanced features like personalised recommendations, semantic search, and targeted content.
This guide will walk you through creating and managing your product schemas, and how to inspect your synced product data.
***
### Navigating to the Product Catalogue
All schema and product management is done from a central location.
1. From the main dashboard, locate the **Data Management** section.
2. Click on **Product Catalog**.
### Understanding the Interface
The Product Catalogue has two primary views, which you can switch between using the toggle buttons at the top of the page:
* **Schema View:** This is the default view. It is where you create, view, and manage the structure (the schema) of different product types.
* **Inspect View:** This view allows you to browse, search, and inspect the individual product items that have been synced to your catalogue.
### Working with Schemas
A schema defines all the properties associated with a type of product. For example, a `movie` schema might have properties like `title`, `director`, and `genre`, while a `dog` schema could have `breed`, `name`, and `adoption_status`.
#### Creating a New Schema
This process sets up the blueprint for a new type of product in your catalogue.
1. Ensure you are in the **Schema** view.
2. Click the **New Schema** button in the top-right corner.
3. The **Manage Schema** modal will open, where you will configure the schema's details.
**Configuring Schema Details**
These top-level settings define the schema's identity and its behaviour for vector-based features.
* **Name:** A user-friendly name for your schema (e.g., "Dogs", "Blog Posts").
* **ID:** The unique identifier for this schema, used in API calls. This should be a machine-readable version of the name (e.g., "dogs", "blog-posts").
* **Vector Embedding Model:** The AI model used to generate numerical representations (embeddings) for this schema's properties. This is crucial for semantic search and recommendations.
* **Vector Embedding Strategy:** The method used to combine multiple vector embeddings into a single representation for the product.
**Adding Standard Properties**
Standard properties are the core attributes that map directly to the data in your product objects.
1. In the **Manage Schema** modal, ensure the **Properties** tab is selected.
2. Click the **+** icon to add a new property row.
3. Configure the following for each property:
* **Path:** The JSON path that points to the property's value in your product data (e.g., `title`, `details.description`).
* **Type:** The data type of the property (e.g., `String`, `Boolean`, `Number`).
* **Filterable:** Enable this toggle to use this property for filtering products.
* **Full Text Search:** Enable this toggle to include this property in full-text search queries.
* **Vector Embed:** Enable this toggle to generate vector embeddings for this property. When enabled, you must provide a **Vector Weight** (a number, typically 1-10) to define the property's importance in similarity calculations.
> **Warning: Reserved Property Path** Do not use `id` as a property **Path**. This path is reserved for the product's unique identifier. Using it for a custom property will cause data syncs to fail.
**Adding Enriched Properties**
Enriched properties are generated by an AI model based on a prompt and your other product data, allowing you to create new, structured attributes automatically.
1. In the **Manage Schema** modal, select the **Enriched Properties** tab.
2. Click the **+** icon to add a new enriched property.
3. Configure the following:
* **Name:** The name for the new property that will be created (e.g., `size_category`).
* **Type:** The data type for the generated property (`String`, `String Array`, `Boolean`).
* **Prompt:** A detailed instruction for the AI model, telling it how to generate the value for this field based on the product's other data.
* **Valid Options (Optional):** Define a list of allowed values for the generated property. This constrains the AI's output to a predefined set. Click **New option** to add a value.
4. Once all properties are configured, click **Save Changes**. Your new schema is now ready.
#### Managing Existing Schemas
You can easily modify, duplicate, or delete schemas you no longer need.
1. From the **Schema** view, select the schema you wish to manage from the list on the left.
2. The schema's details and properties will be displayed.
3. At the bottom of the details pane, you will find the management buttons:
* **Edit:** Opens the **Manage Schema** modal to modify the selected schema.
* **Duplicate:** Creates a copy of the selected schema with "(Copy)" appended to its name.
* **Delete:** Permanently removes the selected schema. This action cannot be undone.
***
### Inspecting Product Data
After you have synced products to your catalogue via the API, you can use the Inspect view to verify and browse them.
1. Navigate to the **Product Catalog**.
2. Click the **Inspect** toggle button at the top of the page.
3. You will see a list of all product items across all your schemas.
4. You can use the following tools to find specific products:
* **Schema Filter:** Use the dropdown menu (defaulting to "All Products") to show only items belonging to a specific schema.
* **Search Bar:** Perform a full-text search across the properties you configured for searching.
5. Click on any product in the list to open a detailed side panel. This panel displays all the properties and their corresponding values for the selected item, allowing you to validate that your data was synced correctly.
***
---
# 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://userflux.gitbook.io/userflux-docs/feature-guides/data-management/product-catalog.md?ask=&goal=
```
`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.