Skip to main content
{
  "results": [
    {}
  ],
  "query": "<string>",
  "knowledgeBase": "<string>",
  "mode": "<string>",
  "took": 123,
  "text": "<string>",
  "score": 123,
  "metadata": {}
}
Perform semantic search over your knowledge bases to find the most relevant chunks for a given query.

​
Examples

import requests

url = "https://labs.chonkie.ai/api/v1/search"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}

data = {
    "query": "How do I configure authentication?",
    "knowledge": "product-documentation",
    "limit": 5,
    "mode": "balanced"
}

response = requests.post(url, headers=headers, json=data)
result = response.json()

print(f"Found {len(result['results'])} results in {result['took']}ms")
for i, item in enumerate(result['results']):
    print(f"Result {i+1} (score: {item['score']:.3f}): {item['text'][:100]}...")

​
Request

​
Parameters

​
query
string
required
The search query. Can be a question, statement, or keywords.
​
knowledge
string
required
The slug of the knowledge base to search in.
​
limit
integer
default:"10"
Maximum number of results to return (1-100).
​
mode
string
default:"balanced"
Search mode:
  • “fast”: fastest, good quality
  • “balanced”: balances speed and quality
  • “deep”: slow with best quality.
We recommend using balanced for most operations

​
Response

​
Returns

​
results
array
Array of search result objects, ranked by relevance.
​
query
string
The original search query.
​
knowledgeBase
string
The knowledge base slug searched.
​
mode
string
The search mode used.
​
took
integer
Search time in milliseconds.
Each result object contains:
​
text
string
The chunk text content.
​
score
float
Relevance score (0-1, higher is more relevant).
​
metadata
object
Additional metadata about the chunk.