Skip to main content
POST
/
kb
/
v1
/
knowledge-bases
/
{id}
/
query
Query Knowledge Base
curl --request POST \
  --url https://api-prod.interactly.ai/kb/v1/knowledge-bases/{id}/query \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-4o",
  "prompt": "<string>",
  "messages": [
    {
      "role": "user",
      "content": "What are the services offered?"
    }
  ],
  "temperature": 0.1,
  "seed": 42,
  "stream": false
}
'
{
  "response": "string"
}

Authorizations

​
Authorization
string
header
required

Retrieve your API Key from Dashboard API Keys Section.

Path Parameters

​
id
string
required

The ID of the knowledge base to train.

Body

application/json
​
model
enum<string>
default:gpt-4o

Optional parameter - The GPT model to use for generating responses

Available options:
gpt-4o,
gpt-4o-mini
​
prompt
string
deprecated

[DEPRECATED. USE "messages" instead] The query prompt to send to the knowledge base.

​
messages
object[]

A list of messages to query with. Note that "messages" and "prompt" cannot be used together. If both are found in the request, "messages" takes precedence and "prompt" is ignored.

​
temperature
number

Temperature controls the randomness in the output of the underlying language model; while lower values produce predictable and factual replies, higher values allow the model to be creative and reword the responses.

Required range: 0 <= x <= 2
Example:

0.1

​
seed
integer

Seed initializes the random number generator in the underlying language model, ensuring reproducible outputs for the same prompt and settings.

Example:

42

​
stream
boolean
default:false

Determines whether to stream the generated response back instead of returning it all at once. When stream = true, the response is a list of JSON objects of the form {"response": string} separated by newline characters

Response

Successful response

​
response
string

The response from the knowledge base.

Example:

"string"