Query Data

Query the dataset

curl --request POST \
  --url https://platform.datagyro.com/v1/query \
  --header 'Content-Type: application/json' \
  --header 'apikey: <api-key>' \
  --data '
{
  "query_string": "Engineers",
  "dataset_id": "118",
  "limit": 10,
  "use_smaller_model": false
}
'

import requests

url = "https://platform.datagyro.com/v1/query"

payload = {
    "query_string": "Engineers",
    "dataset_id": "118",
    "limit": 10,
    "use_smaller_model": False
}
headers = {
    "apikey": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {apikey: '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    query_string: 'Engineers',
    dataset_id: '118',
    limit: 10,
    use_smaller_model: false
  })
};

fetch('https://platform.datagyro.com/v1/query', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://platform.datagyro.com/v1/query",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'query_string' => 'Engineers',
    'dataset_id' => '118',
    'limit' => 10,
    'use_smaller_model' => false
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "apikey: <api-key>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://platform.datagyro.com/v1/query"

	payload := strings.NewReader("{\n  \"query_string\": \"Engineers\",\n  \"dataset_id\": \"118\",\n  \"limit\": 10,\n  \"use_smaller_model\": false\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("apikey", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://platform.datagyro.com/v1/query")
  .header("apikey", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"query_string\": \"Engineers\",\n  \"dataset_id\": \"118\",\n  \"limit\": 10,\n  \"use_smaller_model\": false\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://platform.datagyro.com/v1/query")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["apikey"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"query_string\": \"Engineers\",\n  \"dataset_id\": \"118\",\n  \"limit\": 10,\n  \"use_smaller_model\": false\n}"

response = http.request(request)
puts response.read_body

data: {"type":"thoughts","data":{"filters":["headline contains 'engineer'"],"traits":["Profile mentions engineer"],"key_phrases":["engineer","engineering"],"metadata":"SQL construction notes"},"created":1748020550423}

POST

query

Query the dataset

curl --request POST \
  --url https://platform.datagyro.com/v1/query \
  --header 'Content-Type: application/json' \
  --header 'apikey: <api-key>' \
  --data '
{
  "query_string": "Engineers",
  "dataset_id": "118",
  "limit": 10,
  "use_smaller_model": false
}
'

import requests

url = "https://platform.datagyro.com/v1/query"

payload = {
    "query_string": "Engineers",
    "dataset_id": "118",
    "limit": 10,
    "use_smaller_model": False
}
headers = {
    "apikey": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {apikey: '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    query_string: 'Engineers',
    dataset_id: '118',
    limit: 10,
    use_smaller_model: false
  })
};

fetch('https://platform.datagyro.com/v1/query', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://platform.datagyro.com/v1/query",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'query_string' => 'Engineers',
    'dataset_id' => '118',
    'limit' => 10,
    'use_smaller_model' => false
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "apikey: <api-key>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://platform.datagyro.com/v1/query"

	payload := strings.NewReader("{\n  \"query_string\": \"Engineers\",\n  \"dataset_id\": \"118\",\n  \"limit\": 10,\n  \"use_smaller_model\": false\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("apikey", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://platform.datagyro.com/v1/query")
  .header("apikey", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"query_string\": \"Engineers\",\n  \"dataset_id\": \"118\",\n  \"limit\": 10,\n  \"use_smaller_model\": false\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://platform.datagyro.com/v1/query")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["apikey"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"query_string\": \"Engineers\",\n  \"dataset_id\": \"118\",\n  \"limit\": 10,\n  \"use_smaller_model\": false\n}"

response = http.request(request)
puts response.read_body

data: {"type":"thoughts","data":{"filters":["headline contains 'engineer'"],"traits":["Profile mentions engineer"],"key_phrases":["engineer","engineering"],"metadata":"SQL construction notes"},"created":1748020550423}

Core Concepts

Datasets

Each dataset in DataGyro has a unique identifier (dataset_id). You’ll need to specify which dataset you want to query in your request.

Query Parameters

query_string: The search term or phrase you want to find in the dataset
dataset_id: The unique identifier for the dataset you want to query
limit: Maximum number of results to return (default: 10)
use_smaller_model: Option to use a smaller model for faster processing (default: false)

Example Request

curl --request POST \
  --url https://platform.datagyro.com/v1/query \
  --header 'Content-Type: application/json' \
  --header 'Accept: text/event-stream' \
  --header 'apikey: YOUR_API_KEY' \
  --data '{
    "query_string": "Engineers",
    "dataset_id": "118",
    "limit": 10,
    "use_smaller_model": false
  }'

Note: The endpoint returns a Server-Sent Events stream, so make sure to include the Accept: text/event-stream header and handle the streaming response appropriately.

Response Format

The query endpoint returns a Server-Sent Events (SSE) stream that provides real-time updates during query processing. Each event contains a data field with JSON content.

Stream Event Types

The SSE stream returns four types of events in sequence:

1. Thoughts Event

Provides insights into the query processing logic:

data: {"type":"thoughts","data":{"filters":["headline contains 'engineer'"],"traits":["Profile mentions engineer"],"key_phrases":["engineer","engineering"],"metadata":"SQL construction notes"},"created":1748020550423}

2. SQL Event

Contains the generated SQL query:

data: {"type":"sql","data":{"sql":"SELECT id AS OUTPUT_ID, headline, current_title FROM public.linkedin_profiles WHERE LOWER(headline) LIKE LOWER('%engineer%')"},"created":1748020553674}

3. Results Event

Contains the actual query results:

data: {"type":"results","data":{"items":[{"id":"c0cc058f-0ef0-4ef5-bfea-fe0468d3814f","item":{"001_headline":"AI & VC Engineer","002_current_title":"Software Engineer","003_bio":"..."}}]},"created":1748020553784}

4. Close Event

Indicates the stream has completed:

data: {"type":"close","data":{"complete":true},"created":1748020553784}

Consuming the SSE Stream

To consume the SSE stream in JavaScript:

const eventSource = new EventSource('https://platform.datagyro.com/v1/query', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'apikey': 'YOUR_API_KEY'
  },
  body: JSON.stringify({
    query_string: "Engineers",
    dataset_id: "118",
    limit: 10
  })
});

eventSource.onmessage = function(event) {
  const data = JSON.parse(event.data);
  
  switch(data.type) {
    case 'thoughts':
      console.log('Processing insights:', data.data);
      break;
    case 'sql':
      console.log('Generated SQL:', data.data.sql);
      break;
    case 'results':
      console.log('Query results:', data.data.items);
      break;
    case 'close':
      console.log('Stream completed');
      eventSource.close();
      break;
  }
};

Error Handling

The API may return the following error responses:

400 Bad Request: Invalid parameters were provided
401 Unauthorized: Invalid or missing API key
404 Not Found: The specified dataset was not found
500 Server Error: An internal server error occurred

Error responses will include an error message and code:

{
  "error": "Invalid dataset ID provided",
  "error_code": "INVALID_DATASET"
}

Authorizations

apikey

string

header

required

API key for authentication

Body

application/json

query_string

string

required

The search query to execute against the dataset

Example:

"Engineers"

dataset_id

string

required

Identifier for the dataset to query

Example:

"118"

limit

integer

default:10

Maximum number of results to return

Required range: 1 <= x <= 100

use_smaller_model

boolean

default:false

Option to use a smaller model for faster but potentially less accurate results

Response

Server-Sent Events stream with query processing updates

SSE stream with events containing JSON data

API Documentation

Querying Data

Core Concepts

Datasets

Query Parameters

Example Request

Response Format

Stream Event Types

1. Thoughts Event

2. SQL Event

3. Results Event

4. Close Event

Consuming the SSE Stream

Error Handling

Authorizations

Body

Response

​Core Concepts

​Datasets

​Query Parameters

​Example Request

​Response Format

​Stream Event Types

​1. Thoughts Event

​2. SQL Event

​3. Results Event

​4. Close Event

​Consuming the SSE Stream

​Error Handling

Authorizations

Body

Response

Core Concepts

Datasets

Query Parameters

Example Request

Response Format

Stream Event Types

1. Thoughts Event

2. SQL Event

3. Results Event

4. Close Event

Consuming the SSE Stream

Error Handling