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>'
[
  {
    "document_id": "doc-uuid-1",
    "document_name": "product-guide.pdf",
    "content_snippet": "To get started with the API, first generate an API key from the Settings page...",
    "relevance_score": 0.94,
    "metadata": {}
  }
]
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
default:5
Number of results to return (default: 5, maximum: 50)

​
Response

Returns a flat array of search results, each containing:
​
content
string
The extracted text content from the matching document
​
score
number
Relevance score (float, higher indicates better match)

​
Example Request

curl --request GET \
  --url 'https://api.xpander.ai/v1/knowledge/<kb-id>/search?search_query=pricing+plans&top_k=5' \
  --header 'x-api-key: <your-api-key>'

​
Example Response

[
  {
    "content": "The extracted text content from the matching document...",
    "score": 81.41
  }
]

​
Notes

  • Search only returns results from documents with status: "completed"
  • Pending or failed documents are excluded from search results
  • Empty results indicate no matching content in the knowledge base
  • Returns 404 if the knowledge base is not found

Authorizations

​
x-api-key
string
header
required

API Key for authentication

Path Parameters

​
kb_id
string
required

Query Parameters

​
search_query
string
required

Query to search in the VDB

​
use_bubble
boolean | null
default:false

Should use bubble search to return the result capped

​
bubble_size
integer | null
default:1000

Bubble size (padding + result + margin)

​
top_k
integer | null
default:10

Top K Results

Response

Successful Response

​
content
string
required

The content of the document

​
score
number
required

The search result score