Create an Empty Knowledge Base

POST

datasets

curl --request POST \
  --url https://{api_base_url}/datasets \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "<string>",
  "description": "",
  "embedding_model": "<string>",
  "embedding_model_provider": "<string>",
  "external_knowledge_api_id": "<string>",
  "external_knowledge_id": "<string>",
  "permission": "only_me",
  "provider": "vendor",
  "summary_index_setting": {
    "enable": true,
    "model_name": "<string>",
    "model_provider_name": "<string>",
    "summary_prompt": "<string>"
  }
}
'

import requests

url = "https://{api_base_url}/datasets"

payload = {
    "name": "<string>",
    "description": "",
    "embedding_model": "<string>",
    "embedding_model_provider": "<string>",
    "external_knowledge_api_id": "<string>",
    "external_knowledge_id": "<string>",
    "permission": "only_me",
    "provider": "vendor",
    "summary_index_setting": {
        "enable": True,
        "model_name": "<string>",
        "model_provider_name": "<string>",
        "summary_prompt": "<string>"
    }
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    name: '<string>',
    description: '',
    embedding_model: '<string>',
    embedding_model_provider: '<string>',
    external_knowledge_api_id: '<string>',
    external_knowledge_id: '<string>',
    permission: 'only_me',
    provider: 'vendor',
    summary_index_setting: {
      enable: true,
      model_name: '<string>',
      model_provider_name: '<string>',
      summary_prompt: '<string>'
    }
  })
};

fetch('https://{api_base_url}/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_base_url}/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([
    'name' => '<string>',
    'description' => '',
    'embedding_model' => '<string>',
    'embedding_model_provider' => '<string>',
    'external_knowledge_api_id' => '<string>',
    'external_knowledge_id' => '<string>',
    'permission' => 'only_me',
    'provider' => 'vendor',
    'summary_index_setting' => [
        'enable' => true,
        'model_name' => '<string>',
        'model_provider_name' => '<string>',
        'summary_prompt' => '<string>'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($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_base_url}/datasets"

	payload := strings.NewReader("{\n  \"name\": \"<string>\",\n  \"description\": \"\",\n  \"embedding_model\": \"<string>\",\n  \"embedding_model_provider\": \"<string>\",\n  \"external_knowledge_api_id\": \"<string>\",\n  \"external_knowledge_id\": \"<string>\",\n  \"permission\": \"only_me\",\n  \"provider\": \"vendor\",\n  \"summary_index_setting\": {\n    \"enable\": true,\n    \"model_name\": \"<string>\",\n    \"model_provider_name\": \"<string>\",\n    \"summary_prompt\": \"<string>\"\n  }\n}")

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

	req.Header.Add("Authorization", "Bearer <token>")
	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_base_url}/datasets")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"name\": \"<string>\",\n  \"description\": \"\",\n  \"embedding_model\": \"<string>\",\n  \"embedding_model_provider\": \"<string>\",\n  \"external_knowledge_api_id\": \"<string>\",\n  \"external_knowledge_id\": \"<string>\",\n  \"permission\": \"only_me\",\n  \"provider\": \"vendor\",\n  \"summary_index_setting\": {\n    \"enable\": true,\n    \"model_name\": \"<string>\",\n    \"model_provider_name\": \"<string>\",\n    \"summary_prompt\": \"<string>\"\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://{api_base_url}/datasets")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"name\": \"<string>\",\n  \"description\": \"\",\n  \"embedding_model\": \"<string>\",\n  \"embedding_model_provider\": \"<string>\",\n  \"external_knowledge_api_id\": \"<string>\",\n  \"external_knowledge_id\": \"<string>\",\n  \"permission\": \"only_me\",\n  \"provider\": \"vendor\",\n  \"summary_index_setting\": {\n    \"enable\": true,\n    \"model_name\": \"<string>\",\n    \"model_provider_name\": \"<string>\",\n    \"summary_prompt\": \"<string>\"\n  }\n}"

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

{
  "app_count": 0,
  "author_name": "admin",
  "built_in_field_enabled": true,
  "chunk_structure": null,
  "created_at": 1741267200,
  "created_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
  "data_source_type": null,
  "description": "Technical documentation for the product API",
  "doc_form": "text_model",
  "doc_metadata": [],
  "document_count": 0,
  "embedding_available": true,
  "embedding_model": "text-embedding-3-small",
  "embedding_model_provider": "langgenius/openai/openai",
  "enable_api": true,
  "external_knowledge_info": null,
  "external_retrieval_model": null,
  "icon_info": null,
  "id": "c42e2a6e-40b3-4330-96f8-f1e4d768e8c9",
  "indexing_technique": "high_quality",
  "is_multimodal": false,
  "is_published": false,
  "maintainer": "admin",
  "name": "Product Documentation",
  "permission": "only_me",
  "pipeline_id": null,
  "provider": "vendor",
  "retrieval_model_dict": {
    "reranking_enable": false,
    "reranking_mode": null,
    "reranking_model": {
      "reranking_model_name": "",
      "reranking_provider_name": ""
    },
    "score_threshold": null,
    "score_threshold_enabled": false,
    "search_method": "semantic_search",
    "top_k": 3,
    "weights": null
  },
  "runtime_mode": null,
  "summary_index_setting": null,
  "tags": [],
  "total_available_documents": 0,
  "total_documents": 0,
  "updated_at": 1741267200,
  "updated_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
  "word_count": 0
}

{
  "code": "invalid_param",
  "message": "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider.",
  "status": 400
}

{
  "code": "forbidden",
  "message": "Sorry, you have reached the knowledge base request rate limit of your subscription.",
  "status": 403
}

{
  "code": "dataset_name_duplicate",
  "message": "The dataset name already exists. Please modify your dataset name.",
  "status": 409
}

Authorizations

Authorization

string

header

required

Every request authenticates with an API key: Authorization: Bearer {API_KEY}. App endpoints take an app API key; knowledge endpoints take a knowledge base API key (Get Started).

Keep keys server-side; never embed them in client code. Requests with a missing or invalid key fail with HTTP 401 (unauthorized).

Body

application/json

name

string

required

Name of the knowledge base.

Required string length: 1 - 40

description

string

default:""

Description of the knowledge base.

Maximum string length: 400

embedding_model

string

Embedding model name. Use the model field from Get Available Models with model_type=text-embedding.

embedding_model_provider

string

Embedding model provider identifier, formatted as organization/plugin_name/provider_name (e.g. langgenius/openai/openai). A bare name like openai expands to langgenius/<name>/<name> and works only for langgenius-published plugins.

Get valid values from the provider field of Get Available Models with model_type=text-embedding.

external_knowledge_api_id

string

ID of the external knowledge API connection.

external_knowledge_id

string

ID of the external knowledge base.

indexing_technique

enum<string> | null

high_quality uses embedding models for precise search; economy uses keyword-based indexing.

Available options:

high_quality,

economy

permission

enum<string>

default:only_me

Controls who can access this knowledge base. only_me restricts to the creator, all_team_members grants access to the entire workspace, partial_members grants access to specified members.

Available options:

only_me,

all_team_members,

partial_members

provider

enum<string>

default:vendor

vendor for internal knowledge base, external for external knowledge base.

Available options:

vendor,

external

retrieval_model

object

Retrieval model configuration. Controls how chunks are searched and ranked when querying this knowledge base.

Show child attributes

summary_index_setting

object | null

Summary index configuration.

Show child attributes

Response

Knowledge base created successfully.

app_count

integer

Number of applications currently using this knowledge base.

author_name

string

Display name of the creator.

built_in_field_enabled

boolean

Whether built-in metadata fields (e.g., document_name, uploader) are enabled.

chunk_structure

string | null

Chunk structure configuration.

created_at

number

Creation timestamp (Unix epoch in seconds).

created_by

string

ID of the user who created the knowledge base.

data_source_type

string

Data source type of the documents, null if not yet configured.

description

string

Optional text describing the purpose or contents of the knowledge base.

doc_form

string

Document chunking mode. text_model for standard text chunking, hierarchical_model for parent-child structure, qa_model for QA pair extraction.

doc_metadata

object[]

Metadata field definitions for the knowledge base.

Show child attributes

document_count

integer

Total number of documents in the knowledge base.

embedding_available

boolean

Whether the configured embedding model is currently available.

embedding_model

string

Name of the embedding model used for indexing.

embedding_model_provider

string

Embedding model provider identifier, formatted as organization/plugin_name/provider_name (e.g. langgenius/openai/openai). Legacy knowledge bases may return the bare short form (e.g. openai).

enable_api

boolean

Whether API access is enabled for this knowledge base.

external_knowledge_info

object | null

Connection details for external knowledge bases. Present when provider is external.

Show child attributes

external_retrieval_model

object | null

Retrieval settings for external knowledge bases. null for internal knowledge bases.

Show child attributes

icon_info

object | null

Icon display configuration for the knowledge base.

Show child attributes

string

Unique identifier of the knowledge base.

indexing_technique

string

high_quality uses embedding models for precise search; economy uses keyword-based indexing.

is_multimodal

boolean

Whether multimodal content processing is enabled.

is_published

boolean

Whether the knowledge base is published.

maintainer

string | null

Display name of the knowledge base maintainer. null if not set.

name

string

Display name of the knowledge base. Unique within the workspace.

partial_member_list

string[] | null

Account IDs of members granted access when permission is partial_members. Always present on the update response; on the detail response, present only when permission is partial_members.

permission

string

Controls who can access this knowledge base. Possible values: only_me, all_team_members, partial_members.

pipeline_id

string | null

Pipeline ID, if a custom processing pipeline is configured.

provider

string

Provider type. vendor for internally managed, external for external knowledge base connections.

retrieval_model_dict

object

Retrieval configuration for the knowledge base.

Show child attributes

runtime_mode

string | null

Runtime processing mode.

summary_index_setting

object | null

Summary index configuration.

Show child attributes

tags

object[]

Tags associated with this knowledge base.

Show child attributes

total_available_documents

integer

Number of documents that are enabled and available.

total_documents

integer

Total number of documents.

updated_at

number

Last update timestamp (Unix epoch in seconds).

updated_by

string

ID of the user who last updated the knowledge base.

word_count

integer

Total word count across all documents.

Last modified on September 8, 2026

Create an Empty Knowledge Base

curl --request POST \
  --url https://{api_base_url}/datasets \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "<string>",
  "description": "",
  "embedding_model": "<string>",
  "embedding_model_provider": "<string>",
  "external_knowledge_api_id": "<string>",
  "external_knowledge_id": "<string>",
  "permission": "only_me",
  "provider": "vendor",
  "summary_index_setting": {
    "enable": true,
    "model_name": "<string>",
    "model_provider_name": "<string>",
    "summary_prompt": "<string>"
  }
}
'

import requests

url = "https://{api_base_url}/datasets"

payload = {
    "name": "<string>",
    "description": "",
    "embedding_model": "<string>",
    "embedding_model_provider": "<string>",
    "external_knowledge_api_id": "<string>",
    "external_knowledge_id": "<string>",
    "permission": "only_me",
    "provider": "vendor",
    "summary_index_setting": {
        "enable": True,
        "model_name": "<string>",
        "model_provider_name": "<string>",
        "summary_prompt": "<string>"
    }
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    name: '<string>',
    description: '',
    embedding_model: '<string>',
    embedding_model_provider: '<string>',
    external_knowledge_api_id: '<string>',
    external_knowledge_id: '<string>',
    permission: 'only_me',
    provider: 'vendor',
    summary_index_setting: {
      enable: true,
      model_name: '<string>',
      model_provider_name: '<string>',
      summary_prompt: '<string>'
    }
  })
};

fetch('https://{api_base_url}/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_base_url}/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([
    'name' => '<string>',
    'description' => '',
    'embedding_model' => '<string>',
    'embedding_model_provider' => '<string>',
    'external_knowledge_api_id' => '<string>',
    'external_knowledge_id' => '<string>',
    'permission' => 'only_me',
    'provider' => 'vendor',
    'summary_index_setting' => [
        'enable' => true,
        'model_name' => '<string>',
        'model_provider_name' => '<string>',
        'summary_prompt' => '<string>'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($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_base_url}/datasets"

	payload := strings.NewReader("{\n  \"name\": \"<string>\",\n  \"description\": \"\",\n  \"embedding_model\": \"<string>\",\n  \"embedding_model_provider\": \"<string>\",\n  \"external_knowledge_api_id\": \"<string>\",\n  \"external_knowledge_id\": \"<string>\",\n  \"permission\": \"only_me\",\n  \"provider\": \"vendor\",\n  \"summary_index_setting\": {\n    \"enable\": true,\n    \"model_name\": \"<string>\",\n    \"model_provider_name\": \"<string>\",\n    \"summary_prompt\": \"<string>\"\n  }\n}")

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

	req.Header.Add("Authorization", "Bearer <token>")
	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_base_url}/datasets")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"name\": \"<string>\",\n  \"description\": \"\",\n  \"embedding_model\": \"<string>\",\n  \"embedding_model_provider\": \"<string>\",\n  \"external_knowledge_api_id\": \"<string>\",\n  \"external_knowledge_id\": \"<string>\",\n  \"permission\": \"only_me\",\n  \"provider\": \"vendor\",\n  \"summary_index_setting\": {\n    \"enable\": true,\n    \"model_name\": \"<string>\",\n    \"model_provider_name\": \"<string>\",\n    \"summary_prompt\": \"<string>\"\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://{api_base_url}/datasets")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"name\": \"<string>\",\n  \"description\": \"\",\n  \"embedding_model\": \"<string>\",\n  \"embedding_model_provider\": \"<string>\",\n  \"external_knowledge_api_id\": \"<string>\",\n  \"external_knowledge_id\": \"<string>\",\n  \"permission\": \"only_me\",\n  \"provider\": \"vendor\",\n  \"summary_index_setting\": {\n    \"enable\": true,\n    \"model_name\": \"<string>\",\n    \"model_provider_name\": \"<string>\",\n    \"summary_prompt\": \"<string>\"\n  }\n}"

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

{
  "app_count": 0,
  "author_name": "admin",
  "built_in_field_enabled": true,
  "chunk_structure": null,
  "created_at": 1741267200,
  "created_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
  "data_source_type": null,
  "description": "Technical documentation for the product API",
  "doc_form": "text_model",
  "doc_metadata": [],
  "document_count": 0,
  "embedding_available": true,
  "embedding_model": "text-embedding-3-small",
  "embedding_model_provider": "langgenius/openai/openai",
  "enable_api": true,
  "external_knowledge_info": null,
  "external_retrieval_model": null,
  "icon_info": null,
  "id": "c42e2a6e-40b3-4330-96f8-f1e4d768e8c9",
  "indexing_technique": "high_quality",
  "is_multimodal": false,
  "is_published": false,
  "maintainer": "admin",
  "name": "Product Documentation",
  "permission": "only_me",
  "pipeline_id": null,
  "provider": "vendor",
  "retrieval_model_dict": {
    "reranking_enable": false,
    "reranking_mode": null,
    "reranking_model": {
      "reranking_model_name": "",
      "reranking_provider_name": ""
    },
    "score_threshold": null,
    "score_threshold_enabled": false,
    "search_method": "semantic_search",
    "top_k": 3,
    "weights": null
  },
  "runtime_mode": null,
  "summary_index_setting": null,
  "tags": [],
  "total_available_documents": 0,
  "total_documents": 0,
  "updated_at": 1741267200,
  "updated_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
  "word_count": 0
}

{
  "code": "invalid_param",
  "message": "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider.",
  "status": 400
}

{
  "code": "forbidden",
  "message": "Sorry, you have reached the knowledge base request rate limit of your subscription.",
  "status": 403
}

{
  "code": "dataset_name_duplicate",
  "message": "The dataset name already exists. Please modify your dataset name.",
  "status": 409
}

Guides

App APIs

Knowledge APIs

Create an Empty Knowledge Base

Authorizations

Body

Response