import { CodeGroup } from '@/app/components/develop/code.tsx'
import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from '@/app/components/develop/md.tsx'
# Knowledge API
  ### Authentication
  Service API of Dify authenticates using an `API-Key`.
  It is suggested that developers store the `API-Key` in the backend instead of sharing or storing it in the client side to avoid the leakage of the `API-Key`, which may lead to property loss.
  All API requests should include your `API-Key` in the **`Authorization`** HTTP Header, as shown below:
  
    ```javascript
      Authorization: Bearer {API_KEY}
    ```
  
---
  
    This api is based on an existing Knowledge and creates a new document through text based on this Knowledge.
    ### Params
    
      
        Knowledge ID
      
    
    ### Request Body
    
      
        Document name
      
      
        Document content
      
      
        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
      
      
        Processing rules
          - mode (string) Cleaning, segmentation mode, automatic / custom
          - rules (object) 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
      
    
  
  
    
    ```bash {{ title: 'cURL' }}
    curl --location --request POST '${props.apiBaseUrl}/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"
        }
    }'
    ```
    
    
    ```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": ""
    }
    ```
    
  
---
  
    This api is based on an existing Knowledge and creates a new document through a file based on this Knowledge.
    ### Params
    
      
        Knowledge ID
      
    
    ### Request Body
    
      
        - 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
        - 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
        - process_rule Processing rules
          - mode (string) Cleaning, segmentation mode, automatic / custom
          - rules (object) 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
      
      
        Files that need to be uploaded.
      
    
  
  
    
    ```bash {{ title: 'cURL' }}
    curl --location --request POST '${props.apiBaseUrl}/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"'
    ```
    
    
    ```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": ""
    }
    ```
    
  
---
  
    ### Request Body
    
      
        Knowledge 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"
    }'
    ```
    
    
    ```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
    }
    ```
    
  
---
  
    ### Query
    
      
        Page number
      
      
        Number of items returned, default 20, range 1-100
      
    
  
  
    
    ```bash {{ title: 'cURL' }}
    curl --location --request GET '${props.apiBaseUrl}/datasets?page=1&limit=20' \
    --header 'Authorization: Bearer {api_key}'
    ```
    
    
    ```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
    }
    ```
    
  
---
  
    ### Params
    
      
        Knowledge ID
      
    
  
  
    
    ```bash {{ title: 'cURL' }}
    curl --location --request DELETE '${props.apiBaseUrl}/datasets/{dataset_id}' \
    --header 'Authorization: Bearer {api_key}'
    ```
    
    
    ```text {{ title: 'Response' }}
    204 No Content
    ```
    
  
---
  
    This api is based on an existing Knowledge and updates the document through text based on this Knowledge.
    ### Params
    
      
        Knowledge ID
      
      
        Document ID
      
    
    ### Request Body
    
      
        Document name (optional)
      
      
        Document content (optional)
      
      
        Processing rules
          - mode (string) Cleaning, segmentation mode, automatic / custom
          - rules (object) 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
      
    
  
  
    
    ```bash {{ title: 'cURL' }}
    curl --location --request POST '${props.apiBaseUrl}/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"
    }'
    ```
    
    
    ```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": ""
    }
    ```
    
  
---
  
    This api is based on an existing Knowledge, and updates documents through files based on this Knowledge
    ### Params
    
      
        Knowledge ID
      
      
        Document ID
      
    
    ### Request Body
    
      
        Document name (optional)
      
      
        Files to be uploaded
      
      
        Processing rules
          - mode (string) Cleaning, segmentation mode, automatic / custom
          - rules (object) 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
      
    
  
  
    
    ```bash {{ title: 'cURL' }}
    curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/update_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"'
    ```
    
    
    ```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"
    }
    ```
    
  
---
  
    ### Params
    
      
        Knowledge ID
      
      
        Batch number of uploaded documents
      
    
  
  
    
    ```bash {{ title: 'cURL' }}
    curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{batch}/indexing-status' \
    --header 'Authorization: Bearer {api_key}' \
    ```
    
    
    ```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
      }]
    }
    ```
    
  
---
  
    ### Params
    
      
        Knowledge ID
      
      
        Document ID
      
    
  
  
    
    ```bash {{ title: 'cURL' }}
    curl --location --request DELETE '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}' \
    --header 'Authorization: Bearer {api_key}' \
    ```
    
    
    ```json {{ title: 'Response' }}
    {
      "result": "success"
    }
    ```
    
  
---
  
    ### Params
    
      
        Knowledge ID
      
    
    ### Query
    
      
        Search keywords, currently only search document names(optional)
      
      
        Page number(optional)
      
      
        Number of items returned, default 20, range 1-100(optional)
      
    
  
  
    
    ```bash {{ title: 'cURL' }}
    curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents' \
    --header 'Authorization: Bearer {api_key}' \
    ```
    
    
    ```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
    }
    ```
    
  
---
  
    ### Params
    
      
        Knowledge ID
      
      
        Document ID
      
    
    ### Request Body
    
      
        - content (text) Text content/question content, required
        - answer (text) Answer content, if the mode of the Knowledge is qa mode, pass the value(optional)
        - keywords (list) Keywords(optional)
      
    
  
  
    
    ```bash {{ title: 'cURL' }}
    curl --location --request POST '${props.apiBaseUrl}/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"]
        }
      ]
    }'
    ```
    
    
    ```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"
    }
    ```
    
  
---
  
    ### Path
    
      
        Knowledge ID
      
      
        Document ID
      
    
     ### Query
    
      
        keyword,choosable
      
      
        Search status,completed
      
    
  
  
    
    ```bash {{ title: 'cURL' }}
    curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments' \
    --header 'Authorization: Bearer {api_key}' \
    --header 'Content-Type: application/json'
    ```
    
    
    ```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"
    }
    ```
    
  
---
  
    ### Path
    
      
        Knowledge ID
      
      
        Document Segment ID
      
    
  
  
    
    ```bash {{ title: 'cURL' }}
    curl --location --request DELETE '${props.apiBaseUrl}/datasets/{dataset_id}/segments/{segment_id}' \
    --header 'Authorization: Bearer {api_key}' \
    --header 'Content-Type: application/json'
    ```
    
    
    ```json {{ title: 'Response' }}
    {
      "result": "success"
    }
    ```
    
  
---
  
    ### POST
    
      
        Knowledge ID
      
      
        Document Segment ID
      
    
    ### Request Body
    
      
        - content (text) text content/question content,required
        - answer (text) Answer content, not required, passed if the Knowledge is in qa mode
        - keywords (list) keyword, not required
        - enabled (bool) false/true, not required
      
    
  
  
    
    ```bash {{ title: 'cURL' }}
    curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}' \
    --header 'Content-Type: application/json' \
    --data-raw '{
      "segment": {
          "content": "1",
          "answer": "1",
          "keywords": ["a"],
          "enabled": false
      }
    }'
    ```
    
    
    ```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"
    }
    ```
    
  
---
  
    ### Error message
    
      
        Error code
      
    
    
      
        Error status
      
    
    
      
        Error message
      
    
  
  
    
    ```json {{ title: 'Response' }}
      {
        "code": "no_file_uploaded",
        "message": "Please upload your file.",
        "status": 400
      }
    ```
    
  
  
    
      | code | status | message | 
  
  
    
      | no_file_uploaded | 400 | Please upload your file. | 
    
      | too_many_files | 400 | Only one file is allowed. | 
    
      | file_too_large | 413 | File size exceeded. | 
    
      | unsupported_file_type | 415 | File type not allowed. | 
    
      | high_quality_dataset_only | 400 | Current operation only supports 'high-quality' datasets. | 
    
      | dataset_not_initialized | 400 | The dataset is still being initialized or indexing. Please wait a moment. | 
    
      | archived_document_immutable | 403 | The archived document is not editable. | 
    
      | dataset_name_duplicate | 409 | The dataset name already exists. Please modify your dataset name. | 
    
      | invalid_action | 400 | Invalid action. | 
    
      | document_already_finished | 400 | The document has been processed. Please refresh the page or go to the document details. | 
    
      | document_indexing | 400 | The document is being processed and cannot be edited. | 
    
      | invalid_metadata | 400 | The metadata content is incorrect. Please check and verify. |