Create a dataset
curl --request POST \
--url https://agent.tinyfish.ai/v1/datasets \
--header 'Content-Type: application/json' \
--header 'X-API-Key: <api-key>' \
--data '
{
"prompt": "Specialty coffee shops in Oakland with their website and rating",
"target_rows": 100,
"populate": true
}
'import requests
url = "https://agent.tinyfish.ai/v1/datasets"
payload = {
"prompt": "Specialty coffee shops in Oakland with their website and rating",
"target_rows": 100,
"populate": True
}
headers = {
"X-API-Key": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'X-API-Key': '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
prompt: 'Specialty coffee shops in Oakland with their website and rating',
target_rows: 100,
populate: true
})
};
fetch('https://agent.tinyfish.ai/v1/datasets', 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://agent.tinyfish.ai/v1/datasets",
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([
'prompt' => 'Specialty coffee shops in Oakland with their website and rating',
'target_rows' => 100,
'populate' => true
]),
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"X-API-Key: <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://agent.tinyfish.ai/v1/datasets"
payload := strings.NewReader("{\n \"prompt\": \"Specialty coffee shops in Oakland with their website and rating\",\n \"target_rows\": 100,\n \"populate\": true\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("X-API-Key", "<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://agent.tinyfish.ai/v1/datasets")
.header("X-API-Key", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"prompt\": \"Specialty coffee shops in Oakland with their website and rating\",\n \"target_rows\": 100,\n \"populate\": true\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://agent.tinyfish.ai/v1/datasets")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["X-API-Key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"prompt\": \"Specialty coffee shops in Oakland with their website and rating\",\n \"target_rows\": 100,\n \"populate\": true\n}"
response = http.request(request)
puts response.read_body{
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"name": "<string>",
"spec": {
"name": "<string>",
"description": "<string>",
"columns": [
{
"name": "<string>",
"type": "string",
"is_primary_key": true,
"label": "<string>",
"retrieval_hint": "<string>"
}
],
"keep_when": {
"column": "<string>"
}
},
"status": "empty",
"target_rows": 123,
"row_count": 123,
"run": {
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"status": "queued",
"started_at": "2023-11-07T05:31:56Z",
"finished_at": "2023-11-07T05:31:56Z",
"error": "<string>"
},
"created_at": "2023-11-07T05:31:56Z"
}{
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"name": "<string>",
"spec": {
"name": "<string>",
"description": "<string>",
"columns": [
{
"name": "<string>",
"type": "string",
"is_primary_key": true,
"label": "<string>",
"retrieval_hint": "<string>"
}
],
"keep_when": {
"column": "<string>"
}
},
"status": "empty",
"target_rows": 123,
"row_count": 123,
"run": {
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"status": "queued",
"started_at": "2023-11-07T05:31:56Z",
"finished_at": "2023-11-07T05:31:56Z",
"error": "<string>"
},
"created_at": "2023-11-07T05:31:56Z"
}{
"error": {
"code": "INVALID_INPUT",
"message": "Field \"url\" is required and must be a string",
"details": "<unknown>"
},
"request_id": "8f9dba20-e37b-4749-a919-2269e28b4a2c"
}{
"error": {
"code": "INVALID_INPUT",
"message": "Field \"url\" is required and must be a string",
"details": "<unknown>"
},
"request_id": "8f9dba20-e37b-4749-a919-2269e28b4a2c"
}{
"error": {
"code": "INVALID_INPUT",
"message": "Field \"url\" is required and must be a string",
"details": "<unknown>"
},
"request_id": "8f9dba20-e37b-4749-a919-2269e28b4a2c"
}{
"error": {
"code": "INVALID_INPUT",
"message": "Field \"url\" is required and must be a string",
"details": "<unknown>"
},
"request_id": "8f9dba20-e37b-4749-a919-2269e28b4a2c"
}{
"error": {
"code": "INVALID_INPUT",
"message": "Field \"url\" is required and must be a string",
"details": "<unknown>"
},
"request_id": "8f9dba20-e37b-4749-a919-2269e28b4a2c"
}{
"error": {
"code": "INVALID_INPUT",
"message": "Field \"url\" is required and must be a string",
"details": "<unknown>"
},
"request_id": "8f9dba20-e37b-4749-a919-2269e28b4a2c"
}{
"error": {
"code": "INVALID_INPUT",
"message": "Field \"url\" is required and must be a string",
"details": "<unknown>"
},
"request_id": "8f9dba20-e37b-4749-a919-2269e28b4a2c"
}{
"error": {
"code": "INVALID_INPUT",
"message": "Field \"url\" is required and must be a string",
"details": "<unknown>"
},
"request_id": "8f9dba20-e37b-4749-a919-2269e28b4a2c"
}{
"error": {
"code": "INVALID_INPUT",
"message": "Field \"url\" is required and must be a string",
"details": "<unknown>"
},
"request_id": "8f9dba20-e37b-4749-a919-2269e28b4a2c"
}{
"error": {
"code": "INVALID_INPUT",
"message": "Field \"url\" is required and must be a string",
"details": "<unknown>"
},
"request_id": "8f9dba20-e37b-4749-a919-2269e28b4a2c"
}API Reference
Create a dataset
Describe the dataset in a prompt, or send a spec from /v1/datasets/plan. The dataset starts filling in the background; poll GET /v1/datasets/ and stop once status is no longer populating: ready, empty (no rows landed), failed or cancelled, with run.status and run.error saying how the fill ended. Or follow the run at /runs//events.
POST
/
v1
/
datasets
Create a dataset
curl --request POST \
--url https://agent.tinyfish.ai/v1/datasets \
--header 'Content-Type: application/json' \
--header 'X-API-Key: <api-key>' \
--data '
{
"prompt": "Specialty coffee shops in Oakland with their website and rating",
"target_rows": 100,
"populate": true
}
'import requests
url = "https://agent.tinyfish.ai/v1/datasets"
payload = {
"prompt": "Specialty coffee shops in Oakland with their website and rating",
"target_rows": 100,
"populate": True
}
headers = {
"X-API-Key": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'X-API-Key': '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
prompt: 'Specialty coffee shops in Oakland with their website and rating',
target_rows: 100,
populate: true
})
};
fetch('https://agent.tinyfish.ai/v1/datasets', 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://agent.tinyfish.ai/v1/datasets",
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([
'prompt' => 'Specialty coffee shops in Oakland with their website and rating',
'target_rows' => 100,
'populate' => true
]),
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"X-API-Key: <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://agent.tinyfish.ai/v1/datasets"
payload := strings.NewReader("{\n \"prompt\": \"Specialty coffee shops in Oakland with their website and rating\",\n \"target_rows\": 100,\n \"populate\": true\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("X-API-Key", "<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://agent.tinyfish.ai/v1/datasets")
.header("X-API-Key", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"prompt\": \"Specialty coffee shops in Oakland with their website and rating\",\n \"target_rows\": 100,\n \"populate\": true\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://agent.tinyfish.ai/v1/datasets")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["X-API-Key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"prompt\": \"Specialty coffee shops in Oakland with their website and rating\",\n \"target_rows\": 100,\n \"populate\": true\n}"
response = http.request(request)
puts response.read_body{
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"name": "<string>",
"spec": {
"name": "<string>",
"description": "<string>",
"columns": [
{
"name": "<string>",
"type": "string",
"is_primary_key": true,
"label": "<string>",
"retrieval_hint": "<string>"
}
],
"keep_when": {
"column": "<string>"
}
},
"status": "empty",
"target_rows": 123,
"row_count": 123,
"run": {
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"status": "queued",
"started_at": "2023-11-07T05:31:56Z",
"finished_at": "2023-11-07T05:31:56Z",
"error": "<string>"
},
"created_at": "2023-11-07T05:31:56Z"
}{
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"name": "<string>",
"spec": {
"name": "<string>",
"description": "<string>",
"columns": [
{
"name": "<string>",
"type": "string",
"is_primary_key": true,
"label": "<string>",
"retrieval_hint": "<string>"
}
],
"keep_when": {
"column": "<string>"
}
},
"status": "empty",
"target_rows": 123,
"row_count": 123,
"run": {
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"status": "queued",
"started_at": "2023-11-07T05:31:56Z",
"finished_at": "2023-11-07T05:31:56Z",
"error": "<string>"
},
"created_at": "2023-11-07T05:31:56Z"
}{
"error": {
"code": "INVALID_INPUT",
"message": "Field \"url\" is required and must be a string",
"details": "<unknown>"
},
"request_id": "8f9dba20-e37b-4749-a919-2269e28b4a2c"
}{
"error": {
"code": "INVALID_INPUT",
"message": "Field \"url\" is required and must be a string",
"details": "<unknown>"
},
"request_id": "8f9dba20-e37b-4749-a919-2269e28b4a2c"
}{
"error": {
"code": "INVALID_INPUT",
"message": "Field \"url\" is required and must be a string",
"details": "<unknown>"
},
"request_id": "8f9dba20-e37b-4749-a919-2269e28b4a2c"
}{
"error": {
"code": "INVALID_INPUT",
"message": "Field \"url\" is required and must be a string",
"details": "<unknown>"
},
"request_id": "8f9dba20-e37b-4749-a919-2269e28b4a2c"
}{
"error": {
"code": "INVALID_INPUT",
"message": "Field \"url\" is required and must be a string",
"details": "<unknown>"
},
"request_id": "8f9dba20-e37b-4749-a919-2269e28b4a2c"
}{
"error": {
"code": "INVALID_INPUT",
"message": "Field \"url\" is required and must be a string",
"details": "<unknown>"
},
"request_id": "8f9dba20-e37b-4749-a919-2269e28b4a2c"
}{
"error": {
"code": "INVALID_INPUT",
"message": "Field \"url\" is required and must be a string",
"details": "<unknown>"
},
"request_id": "8f9dba20-e37b-4749-a919-2269e28b4a2c"
}{
"error": {
"code": "INVALID_INPUT",
"message": "Field \"url\" is required and must be a string",
"details": "<unknown>"
},
"request_id": "8f9dba20-e37b-4749-a919-2269e28b4a2c"
}{
"error": {
"code": "INVALID_INPUT",
"message": "Field \"url\" is required and must be a string",
"details": "<unknown>"
},
"request_id": "8f9dba20-e37b-4749-a919-2269e28b4a2c"
}{
"error": {
"code": "INVALID_INPUT",
"message": "Field \"url\" is required and must be a string",
"details": "<unknown>"
},
"request_id": "8f9dba20-e37b-4749-a919-2269e28b4a2c"
}Authorizations
API key for authentication. Get your key from the API Keys page.
Body
application/json
Exactly one of prompt or spec
What the dataset should contain, in plain English
Required string length:
3 - 15000Example:
"Specialty coffee shops in Oakland with their website and rating"
A schema to use as is, such as one returned by POST /v1/datasets/plan
Show child attributes
Show child attributes
Rows to fill the dataset to, 1 to 250
Required range:
1 <= x <= 250Example:
100
Start filling the dataset right away
Response
Dataset created, not populating
A dataset and the state of its rows
Show child attributes
Show child attributes
empty: no rows yet; populating: a run is adding rows; ready: rows stand; failed or cancelled: how the latest run ended
Available options:
empty, populating, ready, failed, cancelled Rows a populate fills to
The latest run, however it ended; null when the dataset never ran
Show child attributes
Show child attributes
Was this page helpful?