import { CodeGroup } from '@/app/components/develop/code.tsx'
import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from '@/app/components/develop/md.tsx'

# Dataset API
<br/>
<br/>
<Heading
  url='/datasets'
  method='POST'
  title='Create an empty dataset'
  name='#create_empty_dataset'
/>
<Row>
  <Col>
    ### Request Body
    <Properties>
      <Property name='name' type='string' key='name'>
        Dataset name
      </Property>
    </Properties>
  </Col>
  <Col sticky>
    <CodeGroup 
      title="Request" 
      tag="POST" 
      label="/datasets"
      targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json' \\\n--data-raw '{"name": "name"}'`}
    >
    ```bash {{ title: 'cURL' }}
    curl --location --request POST '${apiBaseUrl}/v1/datasets' \
    --header 'Authorization: Bearer {api_key}' \
    --header 'Content-Type: application/json' \
    --data-raw '{
      "name": "name"
    }'
    ```
    </CodeGroup>
    <CodeGroup title="Response">
    ```json {{ title: 'Response' }}
    {
      "id": "",
      "name": "name",
      "description": null,
      "provider": "vendor",
      "permission": "only_me",
      "data_source_type": null,
      "indexing_technique": null,
      "app_count": 0,
      "document_count": 0,
      "word_count": 0,
      "created_by": "",
      "created_at": 1695636173,
      "updated_by": "",
      "updated_at": 1695636173,
      "embedding_model": null,
      "embedding_model_provider": null,
      "embedding_available": null
    }
    ```
    </CodeGroup>
  </Col>
</Row>

---

<Heading
  url='/datasets'
  method='GET'
  title='Dataset list'
  name='#dataset_list'
/>
<Row>
  <Col>
    ### Path Query
    <Properties>
      <Property name='page' type='string' key='page'>
        Page number
      </Property>
      <Property name='limit' type='string' key='limit'>
        Number of items returned, default 20, range 1-100
      </Property>
    </Properties>
  </Col>
  <Col sticky>
    <CodeGroup 
      title="Request" 
      tag="POST" 
      label="/datasets"
      targetCode={`curl --location --request GET '${props.apiBaseUrl}/datasets?page=1&limit=20' \\\n--header 'Authorization: Bearer {api_key}'`}
    >
    ```bash {{ title: 'cURL' }}
    curl --location --request GET 'https://api.dify.ai/v1/datasets?page=1&limit=20' \
    --header 'Authorization: Bearer {api_key}'
    ```
    </CodeGroup>
    <CodeGroup title="Response">
    ```json {{ title: 'Response' }}
    {
      "data": [
        {
          "id": "",
          "name": "name",
          "description": "desc",
          "permission": "only_me",
          "data_source_type": "upload_file",
          "indexing_technique": "",
          "app_count": 2,
          "document_count": 10,
          "word_count": 1200,
          "created_by": "",
          "created_at": "",
          "updated_by": "",
          "updated_at": ""
        },
        ...
      ],
      "has_more": true,
      "limit": 20,
      "total": 50,
      "page": 1
    }
    ```
    </CodeGroup>
  </Col>
</Row>

---

<Heading
  url='/datasets/{dataset_id}/document/create_by_text'
  method='POST'
  title='Create a document from text'
  name='#create_by_text'
/>
<Row>
  <Col>
    This api is based on an existing dataset and creates a new document through text based on this dataset.

    ### Path Params
    <Properties>
      <Property name='dataset_id' type='string' key='dataset_id'>
        Dataset ID
      </Property>
    </Properties>

    ### Request Body
    <Properties>
      <Property name='name' type='string' key='name'>
        Document name
      </Property>
      <Property name='text' type='string' key='text'>
        Document content
      </Property>
      <Property name='indexing_technique' type='string' key='indexing_technique'>
        Index mode
          - high_quality High quality: embedding using embedding model, built as vector database index
          - economy Economy: Build using inverted index of Keyword Table Index
      </Property>
      <Property name='process_rule' type='object' key='process_rule'>
        Processing rules
          - mode (string) Cleaning, segmentation mode, automatic / custom
          - rules (text) Custom rules (in automatic mode, this field is empty)
            - pre_processing_rules (array[object]) Preprocessing rules
              - id (string) Unique identifier for the preprocessing rule
                - enumerate 
                  - remove_extra_spaces Replace consecutive spaces, newlines, tabs
                  - remove_urls_emails Delete URL, email address
              - enabled (bool) Whether to select this rule or not. If no document ID is passed in, it represents the default value.
            - segmentation (object) segmentation rules
              - separator Custom segment identifier, currently only allows one delimiter to be set. Default is \n
              - max_tokens Maximum length (token) defaults to 1000
      </Property>
    </Properties>
  </Col>
  <Col sticky>
    <CodeGroup 
      title="Request" 
      tag="POST" 
      label="/datasets/{dataset_id}/document/create_by_text"
      targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/document/create_by_text' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json' \\\n--data-raw '{"name": "text","text": "text","indexing_technique": "high_quality","process_rule": {"mode": "automatic"}}'`}
    >
    ```bash {{ title: 'cURL' }}
    curl --location --request POST 'https://api.dify.ai/v1/datasets/{dataset_id}/document/create_by_text' \
    --header 'Authorization: Bearer {api_key}' \
    --header 'Content-Type: application/json' \
    --data-raw '{
        "name": "text",
        "text": "text",
        "indexing_technique": "high_quality",
        "process_rule": {
            "mode": "automatic"
        }
    }'
    ```
    </CodeGroup>
    <CodeGroup title="Response">
    ```json {{ title: 'Response' }}
    {
      "document": {
        "id": "",
        "position": 1,
        "data_source_type": "upload_file",
        "data_source_info": {
            "upload_file_id": ""
        },
        "dataset_process_rule_id": "",
        "name": "text.txt",
        "created_from": "api",
        "created_by": "",
        "created_at": 1695690280,
        "tokens": 0,
        "indexing_status": "waiting",
        "error": null,
        "enabled": true,
        "disabled_at": null,
        "disabled_by": null,
        "archived": false,
        "display_status": "queuing",
        "word_count": 0,
        "hit_count": 0,
        "doc_form": "text_model"
      },
      "batch": ""
    }
    ```
    </CodeGroup>
  </Col>
</Row>

---

<Heading
  url='/datasets/{dataset_id}/document/create_by_file'
  method='POST'
  title='Create documents from files'
  name='#create_by_file'
/>
<Row>
  <Col>
    This api is based on an existing dataset and creates a new document through a file based on this dataset.
    ### Path Params
    <Properties>
      <Property name='dataset_id' type='string' key='dataset_id'>
        Dataset ID
      </Property>
    </Properties>

    ### Request Body
    <Properties>
      <Property name='original_document_id' type='string' key='original_document_id'>
        Source document ID (optional)
          - Used to re-upload the document or modify the document cleaning and segmentation configuration. The missing information is copied from the source document
          - The source document cannot be an archived document
          - When original_document_id is passed in, the update operation is performed on behalf of the document. process_rule is a fillable item. If not filled in, the segmentation method of the source document will be used by defaul
          - When original_document_id is not passed in, the new operation is performed on behalf of the document, and process_rule is required
      </Property>
      <Property name='file' type='multipart/form-data' key='file'>
        Files that need to be uploaded.
      </Property>
      <Property name='indexing_technique' type='string' key='indexing_technique'>
        Index mode
          - high_quality High quality: embedding using embedding model, built as vector database index
          - economy Economy: Build using inverted index of Keyword Table Index
      </Property>
      <Property name='process_rule' type='object' key='process_rule'>
        Processing rules
          - mode (string) Cleaning, segmentation mode, automatic / custom
          - rules (text) Custom rules (in automatic mode, this field is empty)
            - pre_processing_rules (array[object]) Preprocessing rules
              - id (string) Unique identifier for the preprocessing rule
                - enumerate 
                  - remove_extra_spaces Replace consecutive spaces, newlines, tabs
                  - remove_urls_emails Delete URL, email address
              - enabled (bool) Whether to select this rule or not. If no document ID is passed in, it represents the default value.
            - segmentation (object) segmentation rules
              - separator Custom segment identifier, currently only allows one delimiter to be set. Default is \n
              - max_tokens Maximum length (token) defaults to 1000
      </Property>
    </Properties>
  </Col>
  <Col sticky>
    <CodeGroup 
      title="Request" 
      tag="POST" 
      label="/datasets/{dataset_id}/document/create_by_file"
      targetCode={`curl --location POST '${props.apiBaseUrl}/datasets/{dataset_id}/document/create_by_file' \\\n--header 'Authorization: Bearer {api_key}' \\\n--form 'data="{"name":"Dify","indexing_technique":"high_quality","process_rule":{"rules":{"pre_processing_rules":[{"id":"remove_extra_spaces","enabled":true},{"id":"remove_urls_emails","enabled":true}],"segmentation":{"separator":"###","max_tokens":500}},"mode":"custom"}}";type=text/plain' \\\n--form 'file=@"/path/to/file"'`}
    >
    ```bash {{ title: 'cURL' }}
    curl --location POST 'https://api.dify.ai/v1/datasets/{dataset_id}/document/create_by_file' \
    --header 'Authorization: Bearer {api_key}' \
    --form 'data="{\"name\":\"Dify\",\"indexing_technique\":\"high_quality\",\"process_rule\":{\"rules\":{\"pre_processing_rules\":[{\"id\":\"remove_extra_spaces\",\"enabled\":true},{\"id\":\"remove_urls_emails\",\"enabled\":true}],\"segmentation\":{\"separator\":\"###\",\"max_tokens\":500}},\"mode\":\"custom\"}}";type=text/plain' \
    --form 'file=@"/path/to/file"'
    ```
    </CodeGroup>
    <CodeGroup title="Response">
    ```json {{ title: 'Response' }}
    {
      "document": {
        "id": "",
        "position": 1,
        "data_source_type": "upload_file",
        "data_source_info": {
          "upload_file_id": ""
        },
        "dataset_process_rule_id": "",
        "name": "Dify.txt",
        "created_from": "api",
        "created_by": "",
        "created_at": 1695308667,
        "tokens": 0,
        "indexing_status": "waiting",
        "error": null,
        "enabled": true,
        "disabled_at": null,
        "disabled_by": null,
        "archived": false,
        "display_status": "queuing",
        "word_count": 0,
        "hit_count": 0,
        "doc_form": "text_model"
      },
      "batch": ""
    }
    ```
    </CodeGroup>
  </Col>
</Row>

---

<Heading
  url='/datasets/{dataset_id}/documents/{document_id}/update_by_text'
  method='POST'
  title='Update document via text'
  name='#update_by_text'
/>
<Row>
  <Col>
    This api is based on an existing dataset and updates the document through text based on this dataset.

    ### Path Params
    <Properties>
      <Property name='dataset_id' type='string' key='dataset_id'>
        Dataset ID
      </Property>
      <Property name='document_id' type='string' key='document_id'>
        Document ID
      </Property>
    </Properties>

    ### Request Body
    <Properties>
      <Property name='name' type='string' key='name'>
        Document name (optional)
      </Property>
      <Property name='text' type='string' key='text'>
        Document content (optional)
      </Property>
      <Property name='process_rule' type='object' key='process_rule'>
        Processing rules
          - mode (string) Cleaning, segmentation mode, automatic / custom
          - rules (text) Custom rules (in automatic mode, this field is empty)
            - pre_processing_rules (array[object]) Preprocessing rules
              - id (string) Unique identifier for the preprocessing rule
                - enumerate 
                  - remove_extra_spaces Replace consecutive spaces, newlines, tabs
                  - remove_urls_emails Delete URL, email address
              - enabled (bool) Whether to select this rule or not. If no document ID is passed in, it represents the default value.
            - segmentation (object) segmentation rules
              - separator Custom segment identifier, currently only allows one delimiter to be set. Default is \n
              - max_tokens Maximum length (token) defaults to 1000
      </Property>
    </Properties>
  </Col>
  <Col sticky>
    <CodeGroup 
      title="Request" 
      tag="POST" 
      label="/datasets/{dataset_id}/documents/{document_id}/update_by_text"
      targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/update_by_text' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json' \\\n--data-raw '{"name": "name","text": "text"}'`}
    >
    ```bash {{ title: 'cURL' }}
    curl --location --request POST 'https://api.dify.ai/v1/datasets/{dataset_id}/documents/{document_id}/update_by_text' \
    --header 'Authorization: Bearer {api_key}' \
    --header 'Content-Type: application/json' \
    --data-raw '{
        "name": "name",
        "text": "text"
    }'
    ```
    </CodeGroup>
    <CodeGroup title="Response">
    ```json {{ title: 'Response' }}
    {
      "document": {
        "id": "",
        "position": 1,
        "data_source_type": "upload_file",
        "data_source_info": {
          "upload_file_id": ""
        },
        "dataset_process_rule_id": "",
        "name": "name.txt",
        "created_from": "api",
        "created_by": "",
        "created_at": 1695308667,
        "tokens": 0,
        "indexing_status": "waiting",
        "error": null,
        "enabled": true,
        "disabled_at": null,
        "disabled_by": null,
        "archived": false,
        "display_status": "queuing",
        "word_count": 0,
        "hit_count": 0,
        "doc_form": "text_model"
      },
      "batch": ""
    }
    ```
    </CodeGroup>
  </Col>
</Row>

---

<Heading
  url='/datasets/{dataset_id}/documents/{document_id}/update_by_file'
  method='POST'
  title='Update a document from a file'
  name='#update_by_file'
/>
<Row>
  <Col>
    This api is based on an existing dataset, and updates documents through files based on this dataset

    ### Path Params
    <Properties>
      <Property name='dataset_id' type='string' key='dataset_id'>
        Dataset ID
      </Property>
      <Property name='document_id' type='string' key='document_id'>
        Document ID
      </Property>
    </Properties>

    ### Request Body
    <Properties>
      <Property name='name' type='string' key='name'>
        Document name (optional)
      </Property>
      <Property name='file' type='multipart/form-data' key='file'>
        Files to be uploaded
      </Property>
      <Property name='process_rule' type='object' key='process_rule'>
        Processing rules
          - mode (string) Cleaning, segmentation mode, automatic / custom
          - rules (text) Custom rules (in automatic mode, this field is empty)
            - pre_processing_rules (array[object]) Preprocessing rules
              - id (string) Unique identifier for the preprocessing rule
                - enumerate 
                  - remove_extra_spaces Replace consecutive spaces, newlines, tabs
                  - remove_urls_emails Delete URL, email address
              - enabled (bool) Whether to select this rule or not. If no document ID is passed in, it represents the default value.
            - segmentation (object) segmentation rules
              - separator Custom segment identifier, currently only allows one delimiter to be set. Default is \n
              - max_tokens Maximum length (token) defaults to 1000
      </Property>
    </Properties>
  </Col>
  <Col sticky>
    <CodeGroup 
      title="Request" 
      tag="POST" 
      label="/datasets/{dataset_id}/documents/{document_id}/update_by_file"
      targetCode={`curl --location POST '${props.apiBaseUrl}/datasets/{dataset_id}/document/{document_id}/create_by_file' \\\n--header 'Authorization: Bearer {api_key}' \\\n--form 'data="{"name":"Dify","indexing_technique":"high_quality","process_rule":{"rules":{"pre_processing_rules":[{"id":"remove_extra_spaces","enabled":true},{"id":"remove_urls_emails","enabled":true}],"segmentation":{"separator":"###","max_tokens":500}},"mode":"custom"}}";type=text/plain' \\\n--form 'file=@"/path/to/file"'`}
    >
    ```bash {{ title: 'cURL' }}
    curl --location POST 'https://api.dify.ai/v1/datasets/{dataset_id}/document/{document_id}/create_by_file' \
    --header 'Authorization: Bearer {api_key}' \
    --form 'data="{\"name\":\"Dify\",\"indexing_technique\":\"high_quality\",\"process_rule\":{\"rules\":{\"pre_processing_rules\":[{\"id\":\"remove_extra_spaces\",\"enabled\":true},{\"id\":\"remove_urls_emails\",\"enabled\":true}],\"segmentation\":{\"separator\":\"###\",\"max_tokens\":500}},\"mode\":\"custom\"}}";type=text/plain' \
    --form 'file=@"/path/to/file"'
    ```
    </CodeGroup>
    <CodeGroup title="Response">
    ```json {{ title: 'Response' }}
    {
      "document": {
        "id": "",
        "position": 1,
        "data_source_type": "upload_file",
        "data_source_info": {
          "upload_file_id": ""
        },
        "dataset_process_rule_id": "",
        "name": "Dify.txt",
        "created_from": "api",
        "created_by": "",
        "created_at": 1695308667,
        "tokens": 0,
        "indexing_status": "waiting",
        "error": null,
        "enabled": true,
        "disabled_at": null,
        "disabled_by": null,
        "archived": false,
        "display_status": "queuing",
        "word_count": 0,
        "hit_count": 0,
        "doc_form": "text_model"
      },
      "batch": "20230921150427533684"
    }
    ```
    </CodeGroup>
  </Col>
</Row>

---

<Heading
  url='/datasets/{dataset_id}/batch/{batch}/indexing-status'
  method='GET'
  title='Get document embedding status (progress)'
  name='#indexing_status'
/>
<Row>
  <Col>
    ### Path Params
    <Properties>
      <Property name='dataset_id' type='string' key='dataset_id'>
        Dataset ID
      </Property>
      <Property name='batch' type='string' key='batch'>
        Batch number of uploaded documents
      </Property>
    </Properties>
  </Col>
  <Col sticky>
    <CodeGroup 
      title="Request" 
      tag="GET" 
      label="/datasets/{dataset_id}/batch/{batch}/indexing-status"
      targetCode={`curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{batch}/indexing-status' \\\n--header 'Authorization: Bearer {api_key}'`}
    >
    ```bash {{ title: 'cURL' }}
    curl --location --request GET 'https://api.dify.ai/v1/datasets/{dataset_id}/documents/{batch}/indexing-status' \
    --header 'Authorization: Bearer {api_key}' \
    ```
    </CodeGroup>
    <CodeGroup title="Response">
    ```json {{ title: 'Response' }}
    {
      "data":[{
        "id": "",
        "indexing_status": "indexing", 
        "processing_started_at": 1681623462.0,
        "parsing_completed_at": 1681623462.0,
        "cleaning_completed_at": 1681623462.0,
        "splitting_completed_at": 1681623462.0,
        "completed_at": null,
        "paused_at": null,
        "error": null,
        "stopped_at": null,
        "completed_segments": 24,
        "total_segments": 100
      }]
    }
    ```
    </CodeGroup>
  </Col>
</Row>

---

<Heading
  url='/datasets/{dataset_id}/documents/{document_id}'
  method='DELETE'
  title='Delete document'
  name='#delete_document'
/>
<Row>
  <Col>
    ### Path Params
    <Properties>
      <Property name='dataset_id' type='string' key='dataset_id'>
        Dataset ID
      </Property>
      <Property name='document_id' type='string' key='document_id'>
        Document ID
      </Property>
    </Properties>
  </Col>
  <Col sticky>
    <CodeGroup 
      title="Request" 
      tag="DELETE" 
      label="/datasets/{dataset_id}/documents/{document_id}"
      targetCode={`curl --location --request DELETE '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}' \\\n--header 'Authorization: Bearer {api_key}'`}
    >
    ```bash {{ title: 'cURL' }}
    curl --location --request DELETE 'https://api.dify.ai/v1/datasets/{dataset_id}/documents/{document_id}' \
    --header 'Authorization: Bearer {api_key}' \
    ```
    </CodeGroup>
    <CodeGroup title="Response">
    ```json {{ title: 'Response' }}
    {
      "result": "success"
    }
    ```
    </CodeGroup>
  </Col>
</Row>

---

<Heading
  url='/datasets/{dataset_id}/documents'
  method='GET'
  title='Dataset document list'
  name='#dataset_document_list'
/>
<Row>
  <Col>
    ### Path Params
    <Properties>
      <Property name='dataset_id' type='string' key='dataset_id'>
        Dataset ID
      </Property>
    </Properties>

    ### Path Query
    <Properties>
      <Property name='keyword' type='string' key='keyword'>
        Search keywords, currently only search document names(optional)
      </Property>
      <Property name='page' type='string' key='page'>
        Page number(optional)
      </Property>
      <Property name='limit' type='string' key='limit'>
        Number of items returned, default 20, range 1-100(optional)
      </Property>
    </Properties>
  </Col>
  <Col sticky>
    <CodeGroup 
      title="Request" 
      tag="GET" 
      label="/datasets/{dataset_id}/documents"
      targetCode={`curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents' \\\n--header 'Authorization: Bearer {api_key}'`}
    >
    ```bash {{ title: 'cURL' }}
    curl --location --request GET 'https://api.dify.ai/v1/datasets/{dataset_id}/documents' \
    --header 'Authorization: Bearer {api_key}' \
    ```
    </CodeGroup>
    <CodeGroup title="Response">
    ```json {{ title: 'Response' }}
    {
      "data": [
        {
          "id": "",
          "position": 1,
          "data_source_type": "file_upload",
          "data_source_info": null,
          "dataset_process_rule_id": null,
          "name": "dify",
          "created_from": "",
          "created_by": "",
          "created_at": 1681623639,
          "tokens": 0,
          "indexing_status": "waiting",
          "error": null,
          "enabled": true,
          "disabled_at": null,
          "disabled_by": null,
          "archived": false
        },
      ],
      "has_more": false,
      "limit": 20,
      "total": 9,
      "page": 1
    }
    ```
    </CodeGroup>
  </Col>
</Row>

---

<Heading
  url='/datasets/{dataset_id}/documents/{document_id}/segments'
  method='POST'
  title='Add segment'
  name='#create_new_segment'
/>
<Row>
  <Col>
    ### Path Params
    <Properties>
      <Property name='dataset_id' type='string' key='dataset_id'>
        Dataset ID
      </Property>
      <Property name='document_id' type='string' key='document_id'>
        Document ID
      </Property>
    </Properties>

    ### Request Body
    <Properties>
      <Property name='segments' type='object list' key='segments'>
        segments (object list) Segmented content
          - content (text) Text content/question content, required
          - answer(text) Answer content, if the mode of the data set is qa mode, pass the value(optional)
          - keywords(list) Keywords(optional)
      </Property>
    </Properties>
  </Col>
  <Col sticky>
    <CodeGroup 
      title="Request" 
      tag="POST" 
      label="/datasets/{dataset_id}/documents/{document_id}/segments"
      targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json' \\\n--data-raw '{"segments": [{"content": "1","answer": "1","keywords": ["a"]}]}'`}
    >
    ```bash {{ title: 'cURL' }}
    curl --location --request POST 'https://api.dify.ai/v1/datasets/{dataset_id}/documents/{document_id}/segments' \
    --header 'Authorization: Bearer {api_key}' \
    --header 'Content-Type: application/json' \
    --data-raw '{
      "segments": [
        {
          "content": "1",
          "answer": "1",
          "keywords": ["a"]
        }
      ]
    }'
    ```
    </CodeGroup>
    <CodeGroup title="Response">
    ```json {{ title: 'Response' }}
    {
      "data": [{
        "id": "",
        "position": 1,
        "document_id": "",
        "content": "1",
        "answer": "1",
        "word_count": 25,
        "tokens": 0,
        "keywords": [
          "a"
        ],
        "index_node_id": "",
        "index_node_hash": "",
        "hit_count": 0,
        "enabled": true,
        "disabled_at": null,
        "disabled_by": null,
        "status": "completed",
        "created_by": "",
        "created_at": 1695312007,
        "indexing_at": 1695312007,
        "completed_at": 1695312007,
        "error": null,
        "stopped_at": null
      }],
      "doc_form": "text_model"
    }
    ```
    </CodeGroup>
  </Col>
</Row>

---

Error message
- **document_indexing**: Document indexing failed
- **provider_not_initialize**: Embedding model is not configured
- **not_found**, Document does not exist
- **dataset_name_duplicate**: Duplicate dataset name
- **provider_quota_exceeded**: Model quota exceeds limit
- **dataset_not_initialized**: The dataset has not been initialized yet
- **unsupported_file_type**: Unsupported file types.
  - Currently only supports, txt, markdown, md, pdf, html, htm, xlsx, docx, csv
- **too_many_files**: There are too many files. Currently, only a single file is uploaded
- **file_too_large*: The file is too large, support below 15M based on you environment configuration