Submit Upload Job

curl --request POST \
  --url https://api.egp.scale.com/v4/knowledge-bases/{knowledge_base_id}/uploads \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "data_source_config": {
    "source": "S3",
    "s3_bucket": "<string>",
    "aws_region": "<string>",
    "aws_account_id": "<string>",
    "s3_prefix": ""
  },
  "data_source_auth_config": {
    "source": "SharePoint",
    "client_secret": "<string>",
    "encrypted": false
  },
  "chunking_strategy_config": {
    "strategy": "character",
    "separator": "\n\n",
    "chunk_size": 1000,
    "chunk_overlap": 200
  },
  "force_reupload": false,
  "tagging_information": {
    "type": "per_file",
    "tags_to_apply": {}
  }
}
'

import requests

url = "https://api.egp.scale.com/v4/knowledge-bases/{knowledge_base_id}/uploads"

payload = {
    "data_source_config": {
        "source": "S3",
        "s3_bucket": "<string>",
        "aws_region": "<string>",
        "aws_account_id": "<string>",
        "s3_prefix": ""
    },
    "data_source_auth_config": {
        "source": "SharePoint",
        "client_secret": "<string>",
        "encrypted": False
    },
    "chunking_strategy_config": {
        "strategy": "character",
        "separator": "

",
        "chunk_size": 1000,
        "chunk_overlap": 200
    },
    "force_reupload": False,
    "tagging_information": {
        "type": "per_file",
        "tags_to_apply": {}
    }
}
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({
    data_source_config: {
      source: 'S3',
      s3_bucket: '<string>',
      aws_region: '<string>',
      aws_account_id: '<string>',
      s3_prefix: ''
    },
    data_source_auth_config: {source: 'SharePoint', client_secret: '<string>', encrypted: false},
    chunking_strategy_config: {strategy: 'character', separator: '\n\n', chunk_size: 1000, chunk_overlap: 200},
    force_reupload: false,
    tagging_information: {type: 'per_file', tags_to_apply: {}}
  })
};

fetch('https://api.egp.scale.com/v4/knowledge-bases/{knowledge_base_id}/uploads', 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/knowledge-bases/{knowledge_base_id}/uploads",
  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([
    'data_source_config' => [
        'source' => 'S3',
        's3_bucket' => '<string>',
        'aws_region' => '<string>',
        'aws_account_id' => '<string>',
        's3_prefix' => ''
    ],
    'data_source_auth_config' => [
        'source' => 'SharePoint',
        'client_secret' => '<string>',
        'encrypted' => false
    ],
    'chunking_strategy_config' => [
        'strategy' => 'character',
        'separator' => '

',
        'chunk_size' => 1000,
        'chunk_overlap' => 200
    ],
    'force_reupload' => false,
    'tagging_information' => [
        'type' => 'per_file',
        'tags_to_apply' => [
                
        ]
    ]
  ]),
  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://api.egp.scale.com/v4/knowledge-bases/{knowledge_base_id}/uploads"

	payload := strings.NewReader("{\n  \"data_source_config\": {\n    \"source\": \"S3\",\n    \"s3_bucket\": \"<string>\",\n    \"aws_region\": \"<string>\",\n    \"aws_account_id\": \"<string>\",\n    \"s3_prefix\": \"\"\n  },\n  \"data_source_auth_config\": {\n    \"source\": \"SharePoint\",\n    \"client_secret\": \"<string>\",\n    \"encrypted\": false\n  },\n  \"chunking_strategy_config\": {\n    \"strategy\": \"character\",\n    \"separator\": \"\\n\\n\",\n    \"chunk_size\": 1000,\n    \"chunk_overlap\": 200\n  },\n  \"force_reupload\": false,\n  \"tagging_information\": {\n    \"type\": \"per_file\",\n    \"tags_to_apply\": {}\n  }\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://api.egp.scale.com/v4/knowledge-bases/{knowledge_base_id}/uploads")
  .header("x-api-key", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"data_source_config\": {\n    \"source\": \"S3\",\n    \"s3_bucket\": \"<string>\",\n    \"aws_region\": \"<string>\",\n    \"aws_account_id\": \"<string>\",\n    \"s3_prefix\": \"\"\n  },\n  \"data_source_auth_config\": {\n    \"source\": \"SharePoint\",\n    \"client_secret\": \"<string>\",\n    \"encrypted\": false\n  },\n  \"chunking_strategy_config\": {\n    \"strategy\": \"character\",\n    \"separator\": \"\\n\\n\",\n    \"chunk_size\": 1000,\n    \"chunk_overlap\": 200\n  },\n  \"force_reupload\": false,\n  \"tagging_information\": {\n    \"type\": \"per_file\",\n    \"tags_to_apply\": {}\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.egp.scale.com/v4/knowledge-bases/{knowledge_base_id}/uploads")

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  \"data_source_config\": {\n    \"source\": \"S3\",\n    \"s3_bucket\": \"<string>\",\n    \"aws_region\": \"<string>\",\n    \"aws_account_id\": \"<string>\",\n    \"s3_prefix\": \"\"\n  },\n  \"data_source_auth_config\": {\n    \"source\": \"SharePoint\",\n    \"client_secret\": \"<string>\",\n    \"encrypted\": false\n  },\n  \"chunking_strategy_config\": {\n    \"strategy\": \"character\",\n    \"separator\": \"\\n\\n\",\n    \"chunk_size\": 1000,\n    \"chunk_overlap\": 200\n  },\n  \"force_reupload\": false,\n  \"tagging_information\": {\n    \"type\": \"per_file\",\n    \"tags_to_apply\": {}\n  }\n}"

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

{
  "upload_id": "<string>"
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

Knowledge Bases

Submit Upload Job

Starts an asynchronous ingestion job that syncs the knowledge base with a data source, and returns immediately with an upload_id to poll via the Get Upload endpoint. The request body is a union that supports three modes: an inline data source config, a reference to a previously created data source by data_source_id, or a set of locally provided chunks. On each run the job detects new, updated, and deleted artifacts since the last upload, then extracts, chunks (per the chunking strategy config), and embeds new/updated content while removing deleted artifacts, so uploads are eventually consistent and idempotent — retrying with the same data source and chunking config resumes without duplication, while changing the chunking config forces re-chunking. Before starting, it validates data source access and the chunking config, and it rejects the request if another upload for the same data source is already in progress or if the knowledge base is mid-migration. PER_FILE tagging information is not accepted here (use the file-upload endpoint for that); it is rejected with a validation error. If the backend fails to launch the ingestion workflow the upload is marked failed and an error is returned.

POST

knowledge-bases

{knowledge_base_id}

uploads

Submit Upload Job

curl --request POST \
  --url https://api.egp.scale.com/v4/knowledge-bases/{knowledge_base_id}/uploads \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "data_source_config": {
    "source": "S3",
    "s3_bucket": "<string>",
    "aws_region": "<string>",
    "aws_account_id": "<string>",
    "s3_prefix": ""
  },
  "data_source_auth_config": {
    "source": "SharePoint",
    "client_secret": "<string>",
    "encrypted": false
  },
  "chunking_strategy_config": {
    "strategy": "character",
    "separator": "\n\n",
    "chunk_size": 1000,
    "chunk_overlap": 200
  },
  "force_reupload": false,
  "tagging_information": {
    "type": "per_file",
    "tags_to_apply": {}
  }
}
'

import requests

url = "https://api.egp.scale.com/v4/knowledge-bases/{knowledge_base_id}/uploads"

payload = {
    "data_source_config": {
        "source": "S3",
        "s3_bucket": "<string>",
        "aws_region": "<string>",
        "aws_account_id": "<string>",
        "s3_prefix": ""
    },
    "data_source_auth_config": {
        "source": "SharePoint",
        "client_secret": "<string>",
        "encrypted": False
    },
    "chunking_strategy_config": {
        "strategy": "character",
        "separator": "

",
        "chunk_size": 1000,
        "chunk_overlap": 200
    },
    "force_reupload": False,
    "tagging_information": {
        "type": "per_file",
        "tags_to_apply": {}
    }
}
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({
    data_source_config: {
      source: 'S3',
      s3_bucket: '<string>',
      aws_region: '<string>',
      aws_account_id: '<string>',
      s3_prefix: ''
    },
    data_source_auth_config: {source: 'SharePoint', client_secret: '<string>', encrypted: false},
    chunking_strategy_config: {strategy: 'character', separator: '\n\n', chunk_size: 1000, chunk_overlap: 200},
    force_reupload: false,
    tagging_information: {type: 'per_file', tags_to_apply: {}}
  })
};

fetch('https://api.egp.scale.com/v4/knowledge-bases/{knowledge_base_id}/uploads', 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/knowledge-bases/{knowledge_base_id}/uploads",
  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([
    'data_source_config' => [
        'source' => 'S3',
        's3_bucket' => '<string>',
        'aws_region' => '<string>',
        'aws_account_id' => '<string>',
        's3_prefix' => ''
    ],
    'data_source_auth_config' => [
        'source' => 'SharePoint',
        'client_secret' => '<string>',
        'encrypted' => false
    ],
    'chunking_strategy_config' => [
        'strategy' => 'character',
        'separator' => '

',
        'chunk_size' => 1000,
        'chunk_overlap' => 200
    ],
    'force_reupload' => false,
    'tagging_information' => [
        'type' => 'per_file',
        'tags_to_apply' => [
                
        ]
    ]
  ]),
  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://api.egp.scale.com/v4/knowledge-bases/{knowledge_base_id}/uploads"

	payload := strings.NewReader("{\n  \"data_source_config\": {\n    \"source\": \"S3\",\n    \"s3_bucket\": \"<string>\",\n    \"aws_region\": \"<string>\",\n    \"aws_account_id\": \"<string>\",\n    \"s3_prefix\": \"\"\n  },\n  \"data_source_auth_config\": {\n    \"source\": \"SharePoint\",\n    \"client_secret\": \"<string>\",\n    \"encrypted\": false\n  },\n  \"chunking_strategy_config\": {\n    \"strategy\": \"character\",\n    \"separator\": \"\\n\\n\",\n    \"chunk_size\": 1000,\n    \"chunk_overlap\": 200\n  },\n  \"force_reupload\": false,\n  \"tagging_information\": {\n    \"type\": \"per_file\",\n    \"tags_to_apply\": {}\n  }\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://api.egp.scale.com/v4/knowledge-bases/{knowledge_base_id}/uploads")
  .header("x-api-key", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"data_source_config\": {\n    \"source\": \"S3\",\n    \"s3_bucket\": \"<string>\",\n    \"aws_region\": \"<string>\",\n    \"aws_account_id\": \"<string>\",\n    \"s3_prefix\": \"\"\n  },\n  \"data_source_auth_config\": {\n    \"source\": \"SharePoint\",\n    \"client_secret\": \"<string>\",\n    \"encrypted\": false\n  },\n  \"chunking_strategy_config\": {\n    \"strategy\": \"character\",\n    \"separator\": \"\\n\\n\",\n    \"chunk_size\": 1000,\n    \"chunk_overlap\": 200\n  },\n  \"force_reupload\": false,\n  \"tagging_information\": {\n    \"type\": \"per_file\",\n    \"tags_to_apply\": {}\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.egp.scale.com/v4/knowledge-bases/{knowledge_base_id}/uploads")

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  \"data_source_config\": {\n    \"source\": \"S3\",\n    \"s3_bucket\": \"<string>\",\n    \"aws_region\": \"<string>\",\n    \"aws_account_id\": \"<string>\",\n    \"s3_prefix\": \"\"\n  },\n  \"data_source_auth_config\": {\n    \"source\": \"SharePoint\",\n    \"client_secret\": \"<string>\",\n    \"encrypted\": false\n  },\n  \"chunking_strategy_config\": {\n    \"strategy\": \"character\",\n    \"separator\": \"\\n\\n\",\n    \"chunk_size\": 1000,\n    \"chunk_overlap\": 200\n  },\n  \"force_reupload\": false,\n  \"tagging_information\": {\n    \"type\": \"per_file\",\n    \"tags_to_apply\": {}\n  }\n}"

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

{
  "upload_id": "<string>"
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

Authorizations

x-api-key

string

header

required

Headers

x-selected-account-id

string | null

x-project-id

string | null

Path Parameters

knowledge_base_id

string

required

Body

application/json

DataSource Upload Request
Local Chunks Upload Request
DataSource Upload Request

data_source_config

S3 DataSource Config · object

required

Configuration for the data source which describes where to find the data.

Show child attributes

data_source_auth_config

SharePoint DataSource Auth Config · object

Configuration for the data source which describes how to authenticate to the data source.

SharePoint DataSource Auth Config
SharePoint Page DataSource Auth Config
Azure DataSource Auth Config
Google Cloud Storage DataSource Auth Config
Google Drive DataSource Auth Config
S3 DataSource Auth Config
Confluence DataSource Auth Config
Slack DataSource Auth Config
Snowflake DataSource Auth Config
Databricks DataSource Auth Config
SQL Database DataSource Auth Config
MongoDB DataSource Auth Config
BigQuery DataSource Auth Config
FHIRDataSourceAuthConfig

Show child attributes

chunking_strategy_config

CharacterChunkingStrategyConfig · object

Configuration for the chunking strategy which describes how to chunk the data.

CharacterChunkingStrategyConfig
TokenChunkingStrategyConfig
CustomChunkingStrategyConfig
PreChunkedStrategyConfig
EnhancedChunkingStrategyConfig

Show child attributes

force_reupload

boolean | null

default:false

Force reingest, regardless the change of the source file.

tagging_information

TaggingInformationPerFile · object

A dictionary of tags to apply to all artifacts added from the data source.

TaggingInformationPerFile
TaggingInformationAll

Show child attributes

Response

Successful Response

upload_id

string

required

ID of the created knowledge base upload job.

Knowledge Bases

Chunks

Agents

Completions

Chat Completions

Models

Users

Accounts

Organizations

Question Sets

Evaluations

Evaluation Configs

Evaluation Datasets

Studio Projects

Application Specs

Questions

Knowledge Base Data Sources

Model Templates V3 (Beta)

Model server

API Reference

Fine Tuning Jobs V3 (Beta)

Training Datasets V3 (Beta)

package deployments

Beta

Applications

ChatThreads

Interactions

MonitoringDashboard

Chat Themes

Sessions

account groups

Submit Upload Job

Authorizations

Headers

Path Parameters

Body

Response