Nibi talkres with ad hoc shema

This method is the same as the api/ask/v2//nibitalkres APi but instead of using a predefined data source you use an ad hoc data source. You need to send the data source configuration in the request.

URL : /api/ask/v2/schema_nibitalkres

Method : POST

Parameters

Name	Type	Description
`Question`	`string`	The question you want translated to SQL.
`maxResults`	`string` /int	The max number of results you want to get.
`schema`	`string`	Schema describing your data source (see *note below )
`filter`		Fitler - this is used for adding a filter to the where clause that Niibi is generating. You enter the exact format it will be used in the SQL. The filter will be in relation AND to the conditions in the natural language sentence .

How to use filter

For instance if you ask the question How many companies are B2B With the filter USER_id = 123 you will get the following query:

SELECT COUNT(*) FROM features_company WHERE (LOWER(features_company.business_model) = 'b2b') AND (USER_id = 123) ORDER BY 1 DESC;

Example of Schema

columns and SqlName are mandatory

{
  "sourceName": "Acquisitions1", # this is not mandatory 
  "columns": [
    {
      "SqlName": "company",
      "defaultOnSelect": true,
      "distinctValues": [
        "whatsapp"
      ],
      "name": "startup, company", # the name in natural language 
      "type": "text", # type in DB can be one of [text time ,boll , number,...
      "nullable": "", #I need to check if we are using this 
      "id": "13313121", # not mandatory 
      "defaultEntity": false 
    }, ... ]

  "id": "55530345", # not mandatory 
  "SqlName": "acquisitions", # Table sql name 
  "tableName": "acquistions", # Not mandatory - NLP name of the data source 
  "jaqlSupport": "no", # not mandatory default  to no 
  "timezone": "", #not mandatory default  to empty 
  "executeSql": "yes", # not mandatory default  to no  
  "connectionString": "" # not mandatory default  to no  
}

Output : JSON

Name	Type	Description
`origQustion`	`string`	The question you asked.
`sql`	`string`	The translation.
`results`	`list`	List of resuld ecry raw id a dictionary like with column name , value.
`JAQL`	`dict`	JAQL representation of the sql query.
`Error`	`string`	IF Error Acord its reason.

Request Headers

Name	value
`Content-type`	`application/json`
`Accept`	`text/plain`

Example

{ 
  question : "How many whatsapp",
  maxResult : 5,
  schema :  {
    "sourceName": "Acquisitions4",
    "columns": [{
        "SqlName": "company",
        "defaultOnSelect": true,
        "distinctValues": [
            "whatsapp"
        ],
        "name": "startup, company",
        "type": "text",
        "nullable": "",
        "id": "13313121",
        "defaultEntity": false
    }],
    "id": "55530345",
    "SqlName": "acquisitions",
    "tableName": "acquistions",
    "jaqlSupport": "no",
    "timezone": "",
    "executeSql": "yes",
    "connectionString": ""
}

CURL Request

curl 'https://ask.nibi.ai/api/ask/v2/schema_nibitalkres' -H 'Accept: text/plain' -H 'Referer: https://ask.nibi.ai/' -H 'Origin: https://ask.nibi.ai' -H 'User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36' -H 'Authorization: Bearer eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpYXQiOjE1NDExMjE1MDAsIm5iZiI6MTU0MTEyMTUwMCwianRpIjoiNzdhMTlkOTUtYTIzOC00NDIxLWJiYTYtNzVhOGMzMzkxYzJiIiwiZXhwIjoxNTQxMTIzNTAwLCJpZGVudGl0eSI6eyJpZCI6NSwib3JncyI6W10sInNvdXJjZV9yb2xlIjpbeyJkcyI6IlNpc2Vuc2UiLCJyb2xlIjoiZGF0YVNvdXJjZVZpZXdlciJ9XSwiYXBwX3V1aWQiOjc3fSwiZnJlc2giOmZhbHNlLCJ0eXBlIjoiYWNjZXNzIn0.29ml072DafV4kuVyJdTvizkI3LckVyG97GpFqOzMq7k' -H 'Content-Type: application/json' --data-binary '{"question":"How many whatsapp","maxResults":5,"schema":{"sourceName":"Acquisitions4","columns":[{"SqlName":"company","defaultOnSelect":true,"distinctValues":["whatsapp"],"name":"startup, company","type":"text","nullable":"","id":"13313121","defaultEntity":false}],"id":"55530345","SqlName":"acquisitions","tableName":"acquistions","jaqlSupport":"no","timezone":"","executeSql":"yes","connectionString":""}}' --compressed

Response

{
    "origQustion": "How many whatsapp",
    "sql": "\nSELECT acquisitions.company AS \"startup\"\nFROM acquisitions\nWHERE LOWER(acquisitions.company) = 'whatsapp';\n",
    "results": [{
        "startup": "WhatsApp"
    }],
    "Error": ""
}