> For the complete documentation index, see [llms.txt](https://v2.dataos.info/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://v2.dataos.info/consume/v1/evaluate/assets/semantics.md).

# Semantics

Semantic models are the business-facing layer on top of curated outputs. They expose dimensions and measures so you can query without learning every underlying table. In `Orders Analytics Platform`, models like `CUSTOMER_PROFILE`, `DAILY_SALES`, `PRODUCT_PROFILE`, `RFM`, `SALES_FUNNEL`, and `WEEKLY_SALES` expose customer, sales, and product attributes.

Open **Assets**, expand **Semantics**, and click a model. The detail view shows the name, a description, a summary row with **Kind** and **Schedule**, **View lineage**, and the **Columns**, **Dependencies**, **Relationships**, and (when a policy applies) **Policies** tabs. The **Columns** tab lists each field with its **Kind** (dimension or measure), **Tags**, and **Quality**.

![Semantic model detail showing columns with kind, tags, and quality](/files/o8MlGyvfBngElm6iOrUe)

## Dimensions and measures

Each column shows its kind: **dimensions** for filtering, grouping, and slicing; **measures** for aggregations. In `CUSTOMER_PROFILE`, fields like `customer_name`, `region_name`, `first_order_date`, and `total_orders` describe customer identity and purchase behavior. Use the list to confirm the model exposes the fields your analysis needs.

## Relationships

Open the **Relationships** tab to see which models you can combine in one query. Each row shows the related **Model**, the **Relationship** type (for example, one-to-many), the **Joins** key, and any tags. The **Dependencies** tab shows the outputs that feed the model and what is built on it, and **View lineage** traces a field back to outputs, inputs, or sources.

Next: [Metrics](/consume/v1/evaluate/assets/metrics.md).


---

# 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://v2.dataos.info/consume/v1/evaluate/assets/semantics.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.