# Databricks Tools

The Databricks Tools allow DinoAI to explore your Databricks workspace — listing catalogs, schemas, tables, and columns — so it can help you write accurate SQL, build dbt models, and navigate your Unity Catalog, all without leaving Paradime.

{% hint style="info" icon="plug-circle-plus" %}
**Requires a Databricks connection.** These tools are only available when your workspace is connected to Databricks. See your workspace settings to [configure a Databricks credential](https://docs.paradime.io/app-help/documentation/settings/connections/development-environment/databricks).
{% endhint %}

#### Capabilities

The Databricks Tools give DinoAI the following abilities:

* List all catalogs (databases) available in your Databricks account
* List all schemas within a given catalog
* List all tables within a given catalog and schema
* Inspect column names, data types, and comments for any table using `DESCRIBE TABLE`

#### Using the Databricks Tools

1. Open DinoAI in the right panel of the Code IDE
2. Describe what you want to explore (e.g., a catalog name, a schema, or the columns of a specific table)
3. Add your prompt describing what you want DinoAI to do with that information
4. Grant permission when DinoAI asks to access your Databricks workspace
5. Review the results and implement DinoAI's suggested actions

#### Example Use Cases

**Generating a dbt Source File**

**Prompt**

```
List the columns in the `main.raw.orders` table and generate a dbt sources.yml file for it.
```

**Result:** DinoAI runs `DESCRIBE TABLE main.raw.orders`, fetches all column names, data types, and comments, and produces a ready-to-use `sources.yml` file with the correct structure and column definitions pre-filled.

**Navigating an Unfamiliar Catalog**

**Prompt**

```
What schemas are in the `main` catalog, and what tables are in the `raw` schema?
```

**Result:** DinoAI first lists schemas in the catalog, then lists tables in the specified schema, giving you a full picture of what's available before writing queries or building models.

**Understanding a Table's Structure**

**Prompt**

```
What columns does the `events` table in `main.tracking` have?
```

**Result:** DinoAI returns all column names, data types, and any available comments from `DESCRIBE TABLE`, so you can immediately understand the schema and start writing accurate SQL.

#### Working with Other Tools

The Databricks Tools work well alongside DinoAI's other capabilities:

* Combine with the **dbt Tools** to inspect Databricks source tables and immediately scaffold dbt models or source definitions
* Combine with the **Catalog Search Tool** to cross-reference Databricks table structure with existing dbt model documentation
* Combine with the **Column Level Lineage Tool** to trace how a specific column flows from a raw Databricks table through your dbt transformations

#### Best Practices

* **Use the three-part identifier** — Databricks tables are referenced as `catalog.schema.table`; providing all three parts helps DinoAI navigate directly to the right resource
* **List catalogs first** — If you're unsure of exact names, ask DinoAI to list catalogs, then schemas, then tables before drilling into columns
* **Identifiers are normalised to lowercase** — DinoAI automatically lowercases identifiers when querying Databricks; this matches Databricks' case-insensitive behaviour for unquoted names
* **Check permissions** — DinoAI surfaces a `[ERROR]` if it cannot access a resource; confirm your Databricks credential has the necessary Unity Catalog privileges