Skip to main content
POST
/
library
/
{library_id}
/
query
Create a query
curl --request POST \
  --url https://api.libraria.ai/library/{library_id}/query \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "query": "<string>",
  "conversationId": {},
  "streaming": {}
}
'
{
  "reply": "The capital of France is Paris.",
  "conversationId": "optional-unique-id",
  "metadata": {
      "documents": [
          {
  			"id": "some-document-id",
  			"title": "The france capital",
  			"similarity": 0.966698234468654,
  			"extraFields": {
  				"learnMoreLink": {
  					"url": "https://france-capital",
  					"text": "The France Capital"
  				}
  			}
  		},
      ],
      "images": [],
      "helpArticles": [
          {
              "url": "https://france-capital",
              "text": "The France Capital"
  		}
      ]
  }
}

Documentation Index

Fetch the complete documentation index at: https://docs.libraria.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Parameters

​
library_id
string
required
The ID of the library you are going to ask a question

​
Body

​
query
string
required
The question you will make to the library.
​
conversationId
string | null
Optional. Use this for a continuation of the conversation. You will receive a conversation id on the first query you send.
​
streaming
boolean | null
Optional. Whether or not you want to receive a streamed response. Default value is False.

​
Response

The response will vary according to the value of the streaming attribute.

​
Non-streamed response

When streaming is equal to false the response will be a JSON object containing the following fields
​
reply
string
required
The response from the library for the query provided in the request body
​
conversationId
string
required
Optional. Use this in follow-up requests for a continuation of the conversation. You will receive a conversation id on the first query you send.
​
metadata
json
required
A map containing data used to generate the query response. It provides additional sources of information to the reply.

​
Streamed response

When streaming is equal to true the response is sent as a series of chunk where each of them will be a JSON object.
​
type
string
required
Specifies the type of the chunk that is being sentPossible values are: initializing, token, response, done
​
value
string | null
It only appears when type == token.It represents the token that is currently being sent as part of a partial response. If you concatenate all tokens you will have the complete response.
​
data
json | null
It only appears when type == response.A json object containing the final response and metadata for the gptQuery.
{
  "reply": "The capital of France is Paris.",
  "conversationId": "optional-unique-id",
  "metadata": {
      "documents": [
          {
  			"id": "some-document-id",
  			"title": "The france capital",
  			"similarity": 0.966698234468654,
  			"extraFields": {
  				"learnMoreLink": {
  					"url": "https://france-capital",
  					"text": "The France Capital"
  				}
  			}
  		},
      ],
      "images": [],
      "helpArticles": [
          {
              "url": "https://france-capital",
              "text": "The France Capital"
  		}
      ]
  }
}