Python
import os
from scale_gp import SGPClient
client = SGPClient(
api_key=os.environ.get("SGP_API_KEY"), # This is the default and can be omitted
)
training_dataset = client.training_datasets.create(
account_id="account_id",
file="file",
name="name",
schema_type="GENERATION",
)
print(training_dataset.id)package main
import (
"context"
"fmt"
"github.com/stainless-sdks/sgp-go"
"github.com/stainless-sdks/sgp-go/option"
)
func main() {
client := sgp.NewClient(
option.WithAPIKey("My API Key"),
)
trainingDataset, err := client.TrainingDatasets.New(context.TODO(), sgp.TrainingDatasetNewParams{
AccountID: sgp.F("account_id"),
File: sgp.F("file"),
Name: sgp.F("name"),
SchemaType: sgp.F(sgp.TrainingDatasetNewParamsSchemaTypeGeneration),
})
if err != nil {
panic(err.Error())
}
fmt.Printf("%+v\n", trainingDataset.ID)
}
curl --request POST \
--url https://api.egp.scale.com/v4/training-datasets \
--header 'Content-Type: multipart/form-data' \
--form 'account_id=<string>' \
--form 'name=<string>' \
--form file='@example-file'const form = new FormData();
form.append('account_id', '<string>');
form.append('name', '<string>');
form.append('file', '<string>');
const options = {method: 'POST'};
options.body = form;
fetch('https://api.egp.scale.com/v4/training-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://api.egp.scale.com/v4/training-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 => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"account_id\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"name\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001--",
CURLOPT_HTTPHEADER => [
"Content-Type: multipart/form-data; boundary=---011000010111000001101001"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}HttpResponse<String> response = Unirest.post("https://api.egp.scale.com/v4/training-datasets")
.header("Content-Type", "multipart/form-data; boundary=---011000010111000001101001")
.body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"account_id\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"name\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001--")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.egp.scale.com/v4/training-datasets")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'multipart/form-data; boundary=---011000010111000001101001'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"account_id\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"name\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001--"
response = http.request(request)
puts response.read_body{
"name": "<string>",
"id": "<string>",
"created_at": "2023-11-07T05:31:56Z",
"account_id": "<string>",
"created_by_user_id": "<string>"
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>",
"input": "<unknown>",
"ctx": {}
}
]
}Training Datasets V3 (Beta)
Create Training Dataset
POST
/
v4
/
training-datasets
Python
import os
from scale_gp import SGPClient
client = SGPClient(
api_key=os.environ.get("SGP_API_KEY"), # This is the default and can be omitted
)
training_dataset = client.training_datasets.create(
account_id="account_id",
file="file",
name="name",
schema_type="GENERATION",
)
print(training_dataset.id)package main
import (
"context"
"fmt"
"github.com/stainless-sdks/sgp-go"
"github.com/stainless-sdks/sgp-go/option"
)
func main() {
client := sgp.NewClient(
option.WithAPIKey("My API Key"),
)
trainingDataset, err := client.TrainingDatasets.New(context.TODO(), sgp.TrainingDatasetNewParams{
AccountID: sgp.F("account_id"),
File: sgp.F("file"),
Name: sgp.F("name"),
SchemaType: sgp.F(sgp.TrainingDatasetNewParamsSchemaTypeGeneration),
})
if err != nil {
panic(err.Error())
}
fmt.Printf("%+v\n", trainingDataset.ID)
}
curl --request POST \
--url https://api.egp.scale.com/v4/training-datasets \
--header 'Content-Type: multipart/form-data' \
--form 'account_id=<string>' \
--form 'name=<string>' \
--form file='@example-file'const form = new FormData();
form.append('account_id', '<string>');
form.append('name', '<string>');
form.append('file', '<string>');
const options = {method: 'POST'};
options.body = form;
fetch('https://api.egp.scale.com/v4/training-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://api.egp.scale.com/v4/training-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 => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"account_id\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"name\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001--",
CURLOPT_HTTPHEADER => [
"Content-Type: multipart/form-data; boundary=---011000010111000001101001"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}HttpResponse<String> response = Unirest.post("https://api.egp.scale.com/v4/training-datasets")
.header("Content-Type", "multipart/form-data; boundary=---011000010111000001101001")
.body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"account_id\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"name\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001--")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.egp.scale.com/v4/training-datasets")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'multipart/form-data; boundary=---011000010111000001101001'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"account_id\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"name\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001--"
response = http.request(request)
puts response.read_body{
"name": "<string>",
"id": "<string>",
"created_at": "2023-11-07T05:31:56Z",
"account_id": "<string>",
"created_by_user_id": "<string>"
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>",
"input": "<unknown>",
"ctx": {}
}
]
}Body
multipart/form-data
The ID of the account that owns the given entity.
The name of the dataset
The schema type of the dataset, currently only GENERATION is supported
Available options:
GENERATION, RERANKING_QUESTIONS The file to upload as the training dataset
Response
Successful Response
The name of the dataset
The schema type of the dataset, currently only GENERATION is supported
Available options:
GENERATION, RERANKING_QUESTIONS The data source of the dataset, used to determine how to parse the location
Available options:
S3, SharePoint, SharePointPage, LocalFile, LocalChunks, GoogleDrive, AzureBlobStorage, GoogleCloudStorage, Confluence, Slack, Snowflake, Databricks, SQLDatabase, MongoDB, BigQuery The unique identifier of the entity.
The date and time when the entity was created in ISO format.
The ID of the account that owns the given entity.
The user who originally created the entity.
The type of identity that created the entity.
Available options:
user, service_account ⌘I

