POST /v2/gen-ai/knowledge_bases/{knowledge_base_uuid}/data_sources

To add a data source to a knowledge base, send a POST request to /v2/gen-ai/knowledge_bases/{knowledge_base_uuid}/data_sources.

Servers

https://api.digitalocean.com

Path parameters

Name	Type	Required	Description
`knowledge_base_uuid`	String	Yes	Knowledge base id

Request headers

Name	Type	Required	Description
`Content-Type`	String	Yes	The media type of the request body. Default value: "application/json"

Request body fields

Name	Type	Required	Description
`chunking_algorithm`	String	No	The chunking algorithm to use for processing data sources. Note: This feature requires enabling the knowledgebase enhancements feature preview flag. Valid values: `"CHUNKING_ALGORITHM_SEMANTIC"` `"CHUNKING_ALGORITHM_UNKNOWN"` `"CHUNKING_ALGORITHM_HIERARCHICAL"` `"CHUNKING_ALGORITHM_FIXED_LENGTH"` `"CHUNKING_ALGORITHM_SECTION_BASED"` Default value: "CHUNKING_ALGORITHM_SECTION_BASED"
`aws_data_source`	Object	No	AWS S3 Data Source
`aws_data_source.region`	String	No	Region of bucket
`aws_data_source.bucket_name`	String	No	Spaces bucket name
`aws_data_source.secret_key`	String	No	The AWS Secret Key
`aws_data_source.item_path`	String	No
`aws_data_source.key_id`	String	No	The AWS Key ID
`knowledge_base_uuid`	String	No	Knowledge base id
`spaces_data_source`	Object	No	Spaces Bucket Data Source
`spaces_data_source.region`	String	No	Region of bucket
`spaces_data_source.bucket_name`	String	No	Spaces bucket name
`spaces_data_source.item_path`	String	No
`web_crawler_data_source`	Object	No	WebCrawlerDataSource
`web_crawler_data_source.embed_media`	Boolean	No	Whether to ingest and index media (images, etc.) on web pages.
`web_crawler_data_source.exclude_tags[]`	Array	No	Declaring which tags to exclude in web pages while webcrawling
`web_crawler_data_source.crawling_option`	String	No	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. SITEMAP: Crawl URLs discovered in the sitemap. Valid values: `"SCOPED"` `"PATH"` `"UNKNOWN"` `"DOMAIN"` `"SITEMAP"` `"SUBDOMAINS"` Default value: "UNKNOWN"
`web_crawler_data_source.base_url`	String	No	The base url to crawl.
`chunking_options`	Object	No	Configuration options for the chunking algorithm. Note: This feature requires enabling the knowledgebase enhancements feature preview flag.
`chunking_options.child_chunk_size`	Integer	No	Hierarchical options
`chunking_options.parent_chunk_size`	Integer	No	Hierarchical options
`chunking_options.max_chunk_size`	Integer	No	Section_Based and Fixed_Length options
`chunking_options.semantic_threshold`	Number	No	Semantic options

How to start integrating

Add HTTP Task to your workflow definition.
Search for the API you want to integrate with and click on the name.
- This loads the API reference documentation and prepares the Http request settings.
Click Test request to test run your request to the API and see the API's response.