## Create

`knowledge_bases.create(KnowledgeBaseCreateParams**kwargs)  -> KnowledgeBaseCreateResponse`

**post** `/v2/gen-ai/knowledge_bases`

To create a knowledge base, send a POST request to `/v2/gen-ai/knowledge_bases`.

### Parameters

- **database\_id:** `str`

  Identifier of the DigitalOcean OpenSearch database this knowledge base will use, optional.
  If not provided, we create a new database for the knowledge base in
  the same region as the knowledge base.

- **datasources:** `Iterable[Datasource]`

  The data sources to use for this knowledge base. See [Organize Data Sources](https://docs.digitalocean.com/products/genai-platform/concepts/best-practices/#spaces-buckets) for more information on data sources best practices.

  - **aws\_data\_source:** `AwsDataSourceParam`

    AWS S3 Data Source

  - **bucket\_name:** `str`

    Deprecated, moved to data_source_details

  - **bucket\_region:** `str`

    Deprecated, moved to data_source_details

  - **file\_upload\_data\_source:** `APIFileUploadDataSourceParam`

    File to upload as data source for knowledge base.

  - **item\_path:** `str`

  - **spaces\_data\_source:** `APISpacesDataSourceParam`

    Spaces Bucket Data Source

  - **web\_crawler\_data\_source:** `APIWebCrawlerDataSourceParam`

    WebCrawlerDataSource

- **embedding\_model\_uuid:** `str`

  Identifier for the [embedding model](https://docs.digitalocean.com/products/genai-platform/details/models/#embedding-models).

- **name:** `str`

  Name of the knowledge base.

- **project\_id:** `str`

  Identifier of the DigitalOcean project this knowledge base will belong to.

- **region:** `str`

  The datacenter region to deploy the knowledge base in.

- **tags:** `List[str]`

  Tags to organize your knowledge base.

- **vpc\_uuid:** `str`

  The VPC to deploy the knowledge base database in

### Returns

- `class KnowledgeBaseCreateResponse`

  Information about a newly created knowledge base

  - **knowledge\_base:** `Optional[APIKnowledgeBase]`

    Knowledgebase Description

### Example

```python
from do_gradientai import GradientAI

client = GradientAI()
knowledge_base = client.knowledge_bases.create()
print(knowledge_base.knowledge_base)
```