Create

Create a Knowledge Base

post/v2/gen-ai/knowledge_bases

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

Body ParametersExpand Collapse

database_id: optional 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: optional array of object { aws_data_source, bucket_name, bucket_region, 5 more }

The data sources to use for this knowledge base. See Organize Data Sources for more information on data sources best practices.

aws_data_source: optional AwsDataSource { bucket_name, item_path, key_id, 2 more }

AWS S3 Data Source

bucket_name: optional string

Spaces bucket name

item_path: optional string

key_id: optional string

The AWS Key ID

region: optional string

Region of bucket

secret_key: optional string

The AWS Secret Key

bucket_name: optional string

Deprecated, moved to data_source_details

bucket_region: optional string

Deprecated, moved to data_source_details

dropbox_data_source: optional object { folder, refresh_token }

Dropbox Data Source

folder: optional string

refresh_token: optional 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: optional APIFileUploadDataSource { original_file_name, size_in_bytes, stored_object_key }

File to upload as data source for knowledge base.

original_file_name: optional string

The original file name

size_in_bytes: optional string

The size of the file in bytes

formatuint64

stored_object_key: optional string

The object key the file was stored as

item_path: optional string

spaces_data_source: optional APISpacesDataSource { bucket_name, item_path, region }

Spaces Bucket Data Source

bucket_name: optional string

Spaces bucket name

item_path: optional string

region: optional string

Region of bucket

web_crawler_data_source: optional APIWebCrawlerDataSource { base_url, crawling_option, embed_media }

WebCrawlerDataSource

base_url: optional string

The base url to crawl.

crawling_option: optional "UNKNOWN" or "SCOPED" or "PATH" or 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.

Accepts one of the following:

"UNKNOWN"

"SCOPED"

"PATH"

"DOMAIN"

"SUBDOMAINS"

embed_media: optional boolean

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

embedding_model_uuid: optional string

Identifier for the embedding model.

name: optional string

Name of the knowledge base.

project_id: optional string

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

region: optional string

The datacenter region to deploy the knowledge base in.

tags: optional array of string

Tags to organize your knowledge base.

vpc_uuid: optional string

The VPC to deploy the knowledge base database in

ReturnsExpand Collapse

knowledge_base: optional APIKnowledgeBase { added_to_agent_at, created_at, database_id, 10 more }

Knowledgebase Description

added_to_agent_at: optional string

Time when the knowledge base was added to the agent

formatdate-time

created_at: optional string

Creation date / time

formatdate-time

database_id: optional string

embedding_model_uuid: optional string

is_public: optional boolean

Whether the knowledge base is public or not

last_indexing_job: optional APIIndexingJob { completed_datasources, created_at, data_source_uuids, 12 more }

IndexingJob description

completed_datasources: optional number

Number of datasources indexed completed

formatint64

created_at: optional string

Creation date / time

formatdate-time

data_source_uuids: optional array of string

finished_at: optional string

formatdate-time

knowledge_base_uuid: optional string

Knowledge base id

phase: optional "BATCH_JOB_PHASE_UNKNOWN" or "BATCH_JOB_PHASE_PENDING" or "BATCH_JOB_PHASE_RUNNING" or 4 more

Accepts one of the following:

"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: optional string

formatdate-time

status: optional "INDEX_JOB_STATUS_UNKNOWN" or "INDEX_JOB_STATUS_PARTIAL" or "INDEX_JOB_STATUS_IN_PROGRESS" or 4 more

Accepts one of the following:

"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: optional number

Number of tokens

formatint64

total_datasources: optional number

Number of datasources being indexed

formatint64

total_items_failed: optional string

Total Items Failed

formatuint64

total_items_indexed: optional string

Total Items Indexed

formatuint64

total_items_skipped: optional string

Total Items Skipped

formatuint64

updated_at: optional string

Last modified

formatdate-time

uuid: optional string

Unique id

name: optional string

Name of knowledge base

project_id: optional string

region: optional string

Region code

tags: optional array of string

Tags to organize related resources

updated_at: optional string

Last modified

formatdate-time

user_id: optional string

Id of user that created the knowledge base

formatint64

uuid: optional string

Unique id for knowledge base

Create a Knowledge Base

curl https://api.digitalocean.com/v2/gen-ai/knowledge_bases \
    -H 'Content-Type: application/json' \
    -H "Authorization: Bearer $DIGITALOCEAN_ACCESS_TOKEN"

{
  "knowledge_base": {
    "added_to_agent_at": "2023-01-01T00:00:00Z",
    "created_at": "2023-01-01T00:00:00Z",
    "database_id": "123e4567-e89b-12d3-a456-426614174000",
    "embedding_model_uuid": "123e4567-e89b-12d3-a456-426614174000",
    "is_public": true,
    "last_indexing_job": {
      "completed_datasources": 123,
      "created_at": "2023-01-01T00:00:00Z",
      "data_source_uuids": [
        "example string"
      ],
      "finished_at": "2023-01-01T00:00:00Z",
      "knowledge_base_uuid": "123e4567-e89b-12d3-a456-426614174000",
      "phase": "BATCH_JOB_PHASE_UNKNOWN",
      "started_at": "2023-01-01T00:00:00Z",
      "status": "INDEX_JOB_STATUS_UNKNOWN",
      "tokens": 123,
      "total_datasources": 123,
      "total_items_failed": "12345",
      "total_items_indexed": "12345",
      "total_items_skipped": "12345",
      "updated_at": "2023-01-01T00:00:00Z",
      "uuid": "123e4567-e89b-12d3-a456-426614174000"
    },
    "name": "example name",
    "project_id": "123e4567-e89b-12d3-a456-426614174000",
    "region": "example string",
    "tags": [
      "example string"
    ],
    "updated_at": "2023-01-01T00:00:00Z",
    "user_id": "user_id",
    "uuid": "123e4567-e89b-12d3-a456-426614174000"
  }
}

Returns Examples

{
  "knowledge_base": {
    "added_to_agent_at": "2023-01-01T00:00:00Z",
    "created_at": "2023-01-01T00:00:00Z",
    "database_id": "123e4567-e89b-12d3-a456-426614174000",
    "embedding_model_uuid": "123e4567-e89b-12d3-a456-426614174000",
    "is_public": true,
    "last_indexing_job": {
      "completed_datasources": 123,
      "created_at": "2023-01-01T00:00:00Z",
      "data_source_uuids": [
        "example string"
      ],
      "finished_at": "2023-01-01T00:00:00Z",
      "knowledge_base_uuid": "123e4567-e89b-12d3-a456-426614174000",
      "phase": "BATCH_JOB_PHASE_UNKNOWN",
      "started_at": "2023-01-01T00:00:00Z",
      "status": "INDEX_JOB_STATUS_UNKNOWN",
      "tokens": 123,
      "total_datasources": 123,
      "total_items_failed": "12345",
      "total_items_indexed": "12345",
      "total_items_skipped": "12345",
      "updated_at": "2023-01-01T00:00:00Z",
      "uuid": "123e4567-e89b-12d3-a456-426614174000"
    },
    "name": "example name",
    "project_id": "123e4567-e89b-12d3-a456-426614174000",
    "region": "example string",
    "tags": [
      "example string"
    ],
    "updated_at": "2023-01-01T00:00:00Z",
    "user_id": "user_id",
    "uuid": "123e4567-e89b-12d3-a456-426614174000"
  }
}