Process External Links for Knowledge Base

Used to accept URLs or links to external content, which will then be crawled, processed, and indexed into the knowledge base. This allows the AI to draw information from web pages or online resources.

API Endpoint

Property	Value
Request Method	POST
Request URL	https://api.seliseblocks.com/kb/link

Request

Request Example

curl -X POST 'https://api.seliseblocks.com/kb/link' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -d '{
    "project_key": "YOUR_PROJECT_KEY",
    "agent_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
    "link": "https://example.com/documentation/getting-started",
    "allow_recursive": true
  }'

Request Headers

Field	Type	Required	Description
accept	string	Yes	Accepted response format. Use application/json
Content-Type	application/json	Yes	Data type, must be application/json.

Request Body

Request Body Schema

{
  "project_key": "string",
  "agent_id": "string",
  "link": "string",
  "allow_recursive": false
}

Request Body Parameters

Field	Type	Required	Description
project_key	string	Yes	The project key for your project.
agent_id	string	Yes	UUID of the AI agent to associate the content with.
link	string	Yes	Valid URL of the external content to crawl and process.
allow_recursive	boolean	No	Whether to recursively crawl linked pages from the provided URL. Default: false.

note

Recursive Crawling

• When allow_recursive is set to true, the system will follow links on the provided page and crawl related content within the same domain.
• Be cautious with recursive crawling on large websites, as it may take considerable time and resources to process.

tip

External links are useful for:

• Ingesting product documentation from your website
• Adding knowledge from blog posts or articles
• Incorporating information from public knowledge bases
• Keeping your agent updated with the latest web content

Response

Success Response (200 OK)

Returns an object containing the processing status.

{
  "is_success": true,
  "detail": "Link content crawled and added to knowledge base successfully",
  "error": {}
}

Response Fields

Field	Type	Description
is_success	boolean	Indicates whether the link processing was successful.
detail	string	Success or failure message with additional context.
error	object	Error details if the operation failed (empty if successful).

warning

The crawling and processing of external links may take time depending on:

• The size and complexity of the content
• Whether recursive crawling is enabled
• The responsiveness of the external website
• The number of pages to be processed

Error Response (422 Unprocessable Entity)

Returns validation error details when the request body is invalid.

{
  "detail": [
    {
      "loc": [
        "body",
        "link"
      ],
      "msg": "invalid or missing URL scheme",
      "type": "value_error.url.scheme"
    }
  ]
}

Error Response Fields

Field	Type	Description
detail	array	Array of validation error objects.
loc	array	Location of the error in the request (e.g., body field).
msg	string	Human-readable error message.
type	string	Error type identifier.

Error Codes

Status Code	Description	Response Type
200	Successful Response	Success
400	Bad Request - Invalid URL or crawling error	Bad Request
422	Validation Error - Invalid request parameters	Unprocessable Entity
504	Gateway Timeout - External site not responding	Gateway Timeout