Skip to main content
POST
/
datastores
/
query
/
{id}
This endpoint gets the most similar document fragments for a given query.
curl --request POST \
  --url https://api.chaindesk.ai/datastores/query/{id} \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "query": "<string>",
  "topK": 123,
  "filters": {
    "custom_ids": [
      "<string>"
    ],
    "datasource_ids": [
      "<string>"
    ]
  }
}
'
[
  {
    "text": "<string>",
    "score": 123,
    "source": "<string>",
    "datasource_id": "<string>",
    "datasource_name": "<string>"
  }
]

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

​
id
string
required

ID of the datastore

Body

application/json
​
query
string
required

Query to ask your agent.

​
topK
number

The maximum number of results to retrieve.

​
filters
object

Response

Success

​
text
string

Text of the document fragment.

​
score
number

Similarity score of the document fragment.

​
source
string

Source url of the document fragment.

​
datasource_id
string

ID of the datasource the document fragment belongs to.

​
datasource_name
string

Name of the datasource the document fragment belongs to.