## Create

`client.knowledgeBases.create(KnowledgeBaseCreateParamsbody?, RequestOptionsoptions?): KnowledgeBaseCreateResponse`

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

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

### Parameters

- `body: KnowledgeBaseCreateParams`

  - `database_id?: string`

    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?: Array<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?: AwsDataSource`

      AWS S3 Data Source

      - `bucket_name?: string`

        Spaces bucket name

      - `item_path?: string`

      - `key_id?: string`

        The AWS Key ID

      - `region?: string`

        Region of bucket

      - `secret_key?: string`

        The AWS Secret Key

    - `bucket_name?: string`

      Deprecated, moved to data_source_details

    - `bucket_region?: string`

      Deprecated, moved to data_source_details

    - `dropbox_data_source?: DropboxDataSource`

      Dropbox Data Source

      - `folder?: string`

      - `refresh_token?: string`

        Refresh token. you can obrain a refresh token by following the oauth2 flow. see /v2/gen-ai/oauth2/dropbox/tokens for reference.

    - `file_upload_data_source?: APIFileUploadDataSource`

      File to upload as data source for knowledge base.

      - `original_file_name?: string`

        The original file name

      - `size_in_bytes?: string`

        The size of the file in bytes

      - `stored_object_key?: string`

        The object key the file was stored as

    - `item_path?: string`

    - `spaces_data_source?: APISpacesDataSource`

      Spaces Bucket Data Source

      - `bucket_name?: string`

        Spaces bucket name

      - `item_path?: string`

      - `region?: string`

        Region of bucket

    - `web_crawler_data_source?: APIWebCrawlerDataSource`

      WebCrawlerDataSource

      - `base_url?: string`

        The base url to crawl.

      - `crawling_option?: "UNKNOWN" | "SCOPED" | "PATH" | 2 more`

        Options for specifying how URLs found on pages should be handled.

        - UNKNOWN: Default unknown value
        - SCOPED: Only include the base URL.
        - PATH: Crawl the base URL and linked pages within the URL path.
        - DOMAIN: Crawl the base URL and linked pages within the same domain.
        - SUBDOMAINS: Crawl the base URL and linked pages for any subdomain.

        - `"UNKNOWN"`

        - `"SCOPED"`

        - `"PATH"`

        - `"DOMAIN"`

        - `"SUBDOMAINS"`

      - `embed_media?: boolean`

        Whether to ingest and index media (images, etc.) on web pages.

  - `embedding_model_uuid?: string`

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

  - `name?: string`

    Name of the knowledge base.

  - `project_id?: string`

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

  - `region?: string`

    The datacenter region to deploy the knowledge base in.

  - `tags?: Array<string>`

    Tags to organize your knowledge base.

  - `vpc_uuid?: string`

    The VPC to deploy the knowledge base database in

### Returns

- `KnowledgeBaseCreateResponse`

  Information about a newly created knowledge base

  - `knowledge_base?: APIKnowledgeBase`

    Knowledgebase Description

    - `added_to_agent_at?: string`

      Time when the knowledge base was added to the agent

    - `created_at?: string`

      Creation date / time

    - `database_id?: string`

    - `embedding_model_uuid?: string`

    - `is_public?: boolean`

      Whether the knowledge base is public or not

    - `last_indexing_job?: APIIndexingJob`

      IndexingJob description

      - `completed_datasources?: number`

        Number of datasources indexed completed

      - `created_at?: string`

        Creation date / time

      - `data_source_uuids?: Array<string>`

      - `finished_at?: string`

      - `knowledge_base_uuid?: string`

        Knowledge base id

      - `phase?: "BATCH_JOB_PHASE_UNKNOWN" | "BATCH_JOB_PHASE_PENDING" | "BATCH_JOB_PHASE_RUNNING" | 4 more`

        - `"BATCH_JOB_PHASE_UNKNOWN"`

        - `"BATCH_JOB_PHASE_PENDING"`

        - `"BATCH_JOB_PHASE_RUNNING"`

        - `"BATCH_JOB_PHASE_SUCCEEDED"`

        - `"BATCH_JOB_PHASE_FAILED"`

        - `"BATCH_JOB_PHASE_ERROR"`

        - `"BATCH_JOB_PHASE_CANCELLED"`

      - `started_at?: string`

      - `status?: "INDEX_JOB_STATUS_UNKNOWN" | "INDEX_JOB_STATUS_PARTIAL" | "INDEX_JOB_STATUS_IN_PROGRESS" | 4 more`

        - `"INDEX_JOB_STATUS_UNKNOWN"`

        - `"INDEX_JOB_STATUS_PARTIAL"`

        - `"INDEX_JOB_STATUS_IN_PROGRESS"`

        - `"INDEX_JOB_STATUS_COMPLETED"`

        - `"INDEX_JOB_STATUS_FAILED"`

        - `"INDEX_JOB_STATUS_NO_CHANGES"`

        - `"INDEX_JOB_STATUS_PENDING"`

      - `tokens?: number`

        Number of tokens

      - `total_datasources?: number`

        Number of datasources being indexed

      - `total_items_failed?: string`

        Total Items Failed

      - `total_items_indexed?: string`

        Total Items Indexed

      - `total_items_skipped?: string`

        Total Items Skipped

      - `updated_at?: string`

        Last modified

      - `uuid?: string`

        Unique id

    - `name?: string`

      Name of knowledge base

    - `project_id?: string`

    - `region?: string`

      Region code

    - `tags?: Array<string>`

      Tags to organize related resources

    - `updated_at?: string`

      Last modified

    - `user_id?: string`

      Id of user that created the knowledge base

    - `uuid?: string`

      Unique id for knowledge base

### Example

```typescript
import Gradient from '@digitalocean/gradient';

const client = new Gradient();

const knowledgeBase = await client.knowledgeBases.create();

console.log(knowledgeBase.knowledge_base);
```