Skip to main content
POST
/
v1
/
knowledge
/
learn
curl -X POST https://api.bland.ai/v1/knowledge/learn \
  -H "authorization: YOUR_API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "type": "web",
    "name": "Documentation",
    "description": "Complete product documentation",
    "urls": [
      "https://docs.example.com/overview",
      "https://docs.example.com/api-reference",
      "https://docs.example.com/tutorials"
    ]
  }'

{
  "data": {
    "id": "kb_01H8X9QK5R2N7P3M6Z8W4Y1V7V",
    "name": "Documentation",
    "description": "Complete product documentation",
    "status": "PROCESSING",
    "type": "WEB_SCRAPE",
    "source_urls": "https://docs.example.com/overview,https://docs.example.com/api-reference,https://docs.example.com/tutorials",
    "base_url": "https://docs.example.com",
    "created_at": "2025-01-15T12:00:00Z",
    "updated_at": "2025-01-15T12:00:00Z"
  },
  "errors": null
}

Documentation Index

Fetch the complete documentation index at: https://blandai-feat-kb-attachment-matrix.mintlify.app/llms.txt

Use this file to discover all available pages before exploring further.

Create a knowledge base by scraping content from one or more web URLs. This is perfect for creating knowledge bases from documentation sites, blog posts, or other web-based content. This endpoint returns a data.id UUID. See Where can a knowledge base be attached? for the surfaces that consume the UUID (Web Agents, Personas, Pathway nodes, outbound calls).

​
Headers

​
authorization
string
required
Your API key for authentication.
​
content-type
string
required
Must be application/json for web scraping knowledge bases.

​
Body Parameters

​
type
string
default:"web"
required
Must be "web" for web scraping knowledge bases.
​
name
string
required
Name for the knowledge base.
​
description
string
Optional description of the knowledge base content.
​
urls
string[]
required
Array of URLs to scrape (maximum 100 URLs).

​
Response

​
data
object
The created knowledge base object.
​
data.id
string
Unique identifier for the knowledge base.
​
data.name
string
Name of the knowledge base.
​
data.description
string
Description of the knowledge base (if provided).
​
data.status
string
Current status: "PROCESSING", "COMPLETED", "FAILED", or "DELETED".
​
data.type
string
Will be "WEB_SCRAPE" for web scraping knowledge bases.
​
data.source_urls
string
Source URLs that were scraped (comma-separated).
​
data.base_url
string
Base URL derived from the provided URLs.
​
data.created_at
string
ISO timestamp of creation.
​
data.updated_at
string
ISO timestamp of last update.
​
data.error_message
string
Error message if status is "FAILED".
​
errors
null
Will be null on successful creation.
curl -X POST https://api.bland.ai/v1/knowledge/learn \
  -H "authorization: YOUR_API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "type": "web",
    "name": "Documentation",
    "description": "Complete product documentation",
    "urls": [
      "https://docs.example.com/overview",
      "https://docs.example.com/api-reference",
      "https://docs.example.com/tutorials"
    ]
  }'

{
  "data": {
    "id": "kb_01H8X9QK5R2N7P3M6Z8W4Y1V7V",
    "name": "Documentation",
    "description": "Complete product documentation",
    "status": "PROCESSING",
    "type": "WEB_SCRAPE",
    "source_urls": "https://docs.example.com/overview,https://docs.example.com/api-reference,https://docs.example.com/tutorials",
    "base_url": "https://docs.example.com",
    "created_at": "2025-01-15T12:00:00Z",
    "updated_at": "2025-01-15T12:00:00Z"
  },
  "errors": null
}
Docs for agents: llms.txt