Skip to main content
GET
/
v1
/
knowledge
/
{kb_id}
/
search
Search In Knowledge Base
curl --request GET \
  --url https://api.xpander.ai/v1/knowledge/{kb_id}/search \
  --header 'x-api-key: <api-key>'
[
  {
    "content": "<string>",
    "score": 123
  }
]
Perform semantic search across documents in a knowledge base using vector similarity. Returns the most relevant document chunks based on your query.

​
Path Parameters

​
kb_id
string
required
Unique identifier of the knowledge base to search (UUID format)

​
Query Parameters

​
search_query
string
required
The search query text to find relevant documents
​
top_k
integer
Number of results to return (default: 5, max: 50)
​
use_bubble
boolean
Whether to use bubble search algorithm for improved relevance (default: false)

​
Response

Returns an array of search results, each containing:
​
content
string
The text content of the matching document chunk
​
score
number
Similarity score (0-1, higher is more relevant)
​
document_id
string
UUID of the source document
​
metadata
object
Additional metadata about the document chunk

​
Example Request

curl -H "x-api-key: YOUR_API_KEY" \
  "https://api.xpander.ai/v1/knowledge/{kb_id}/search?search_query=API%20authentication&top_k=10"

​
Example Response

[
  {
    "content": "API authentication is handled via x-api-key header...",
    "score": 0.92,
    "document_id": "doc-123",
    "metadata": {
      "source": "api-docs.pdf",
      "page": 5
    }
  },
  {
    "content": "To authenticate requests, include your API key...",
    "score": 0.87,
    "document_id": "doc-456",
    "metadata": {
      "source": "getting-started.md"
    }
  }
]

Authorizations

​
x-api-key
string
header
required

Path Parameters

​
kb_id
string
required

Query Parameters

​
search_query
string
required
​
use_bubble
boolean | null
default:false
​
bubble_size
integer | null
default:1000
​
top_k
integer | null
default:10

Response

​
content
string
required
​
score
number
required