import { CodeGroup } from '@/app/components/develop/code.tsx'
import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from '@/app/components/develop/md.tsx'
# 知识库 API
  ### 鉴权
  Dify Service API 使用 `API-Key` 进行鉴权。
  建议开发者把 `API-Key` 放在后端存储,而非分享或者放在客户端存储,以免 `API-Key` 泄露,导致财产损失。
  所有 API 请求都应在 **`Authorization`** HTTP Header 中包含您的 `API-Key`,如下所示:
  
    ```javascript
      Authorization: Bearer {API_KEY}
    ```
  
---
  
    此接口基于已存在知识库,在此知识库的基础上通过文本创建新的文档
    ### Path
    
      
        知识库 ID
      
    
    ### Request Body
    
      
        文档名称
      
      
        文档内容
      
      
        索引方式
          - high_quality 高质量:使用  embedding 模型进行嵌入,构建为向量数据库索引
          - economy 经济:使用 Keyword Table Index 的倒排索引进行构建
      
      
        处理规则
          - mode (string) 清洗、分段模式 ,automatic 自动 / custom 自定义
          - rules (object) 自定义规则(自动模式下,该字段为空)
            - pre_processing_rules (array[object]) 预处理规则
              - id (string) 预处理规则的唯一标识符
                - 枚举:
                  - remove_extra_spaces 替换连续空格、换行符、制表符
                  - remove_urls_emails 删除 URL、电子邮件地址
              - enabled (bool) 是否选中该规则,不传入文档 ID 时代表默认值
            - segmentation (object) 分段规则
              - separator 自定义分段标识符,目前仅允许设置一个分隔符。默认为 \n
              - max_tokens 最大长度 (token) 默认为 1000
      
    
  
  
    
    ```bash {{ title: 'cURL' }}
    curl --location --request --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": ""
    }
    ```
    
  
---
  
    此接口基于已存在知识库,在此知识库的基础上通过文件创建新的文档
    ### Path
    
      
        知识库 ID
      
    
    ### Request Bodys
    
      
        - original_document_id 源文档 ID (选填)
          - 用于重新上传文档或修改文档清洗、分段配置,缺失的信息从源文档复制
          - 源文档不可为归档的文档
          - 当传入 original_document_id 时,代表文档进行更新操作,process_rule 为可填项目,不填默认使用源文档的分段方式
          - 未传入 original_document_id 时,代表文档进行新增操作,process_rule 为必填
        - indexing_technique 索引方式
          - high_quality 高质量:使用  embedding 模型进行嵌入,构建为向量数据库索引
          - economy 经济:使用 Keyword Table Index 的倒排索引进行构建
        - process_rule 处理规则
          - mode (string) 清洗、分段模式 ,automatic 自动 / custom 自定义
          - rules (object) 自定义规则(自动模式下,该字段为空)
            - pre_processing_rules (array[object]) 预处理规则
              - id (string) 预处理规则的唯一标识符
                - 枚举:
                  - remove_extra_spaces 替换连续空格、换行符、制表符
                  - remove_urls_emails 删除 URL、电子邮件地址
              - enabled (bool) 是否选中该规则,不传入文档 ID 时代表默认值
            - segmentation (object) 分段规则
              - separator 自定义分段标识符,目前仅允许设置一个分隔符。默认为 \n
              - max_tokens 最大长度 (token) 默认为 1000
      
      
        需要上传的文件。
      
    
  
  
    
    ```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
    
      
        知识库名称
      
    
  
  
    
    ```bash {{ title: 'cURL' }}
    curl --location --request POST '${props.apiBaseUrl}/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
    
      
        页码
      
      
        返回条数,默认 20,范围 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": "知识库名称",
          "description": "描述信息",
          "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
    }
    ```
    
  
---
  
    此接口基于已存在知识库,在此知识库的基础上通过文本更新文档
    ### Path
    
      
        知识库 ID
      
      
        文档 ID
      
    
    ### Request Body
    
      
        文档名称 (选填)
      
      
        文档内容(选填)
      
      
        处理规则(选填)
          - mode (string) 清洗、分段模式 ,automatic 自动 / custom 自定义
          - rules (object) 自定义规则(自动模式下,该字段为空)
            - pre_processing_rules (array[object]) 预处理规则
              - id (string) 预处理规则的唯一标识符
                - 枚举:
                  - remove_extra_spaces 替换连续空格、换行符、制表符
                  - remove_urls_emails 删除 URL、电子邮件地址
              - enabled (bool) 是否选中该规则,不传入文档 ID 时代表默认值
            - segmentation (object) 分段规则
              - separator 自定义分段标识符,目前仅允许设置一个分隔符。默认为 \n
              - max_tokens 最大长度 (token) 默认为 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": ""
    }
    ```
    
  
---
  
    此接口基于已存在知识库,在此知识库的基础上通过文件更新文档的操作。
    ### Path
    
      
        知识库 ID
      
      
        文档 ID
      
    
    ### Request Body
    
      
        文档名称 (选填)
      
      
        需要上传的文件
      
      
        处理规则(选填)
          - mode (string) 清洗、分段模式 ,automatic 自动 / custom 自定义
          - rules (object) 自定义规则(自动模式下,该字段为空)
            - pre_processing_rules (array[object]) 预处理规则
              - id (string) 预处理规则的唯一标识符
                - 枚举:
                  - remove_extra_spaces 替换连续空格、换行符、制表符
                  - remove_urls_emails 删除 URL、电子邮件地址
              - enabled (bool) 是否选中该规则,不传入文档 ID 时代表默认值
            - segmentation (object) 分段规则
              - separator 自定义分段标识符,目前仅允许设置一个分隔符。默认为 \n
              - max_tokens 最大长度 (token) 默认为 1000
      
    
  
  
    
    ```bash {{ title: 'cURL' }}
    curl --location --request POST '${props.apiBaseUrl}/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"'
    ```
    
    
    ```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"
    }
    ```
    
  
---
  
    ### Path
    
      
        知识库 ID
      
      
        上传文档的批次号
      
    
  
  
    
    ```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
      }]
    }
    ```
    
  
---
  
    ### Path
    
      
        知识库 ID
      
      
        文档 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"
    }
    ```
    
  
---
  
    ### Path
    
      
        知识库 ID
      
    
    ### Query
    
      
        搜索关键词,可选,目前仅搜索文档名称
      
      
        页码,可选
      
      
        返回条数,可选,默认 20,范围 1-100
      
    
  
  
    
    ```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
    }
    ```
    
  
---
  
    ### Path
    
      
        知识库 ID
      
      
        文档 ID
      
    
    ### Request Body
    
      
        - content (text) 文本内容/问题内容,必填
        - answer (text) 答案内容,非必填,如果知识库的模式为qa模式则传值
        - keywords (list) 关键字,非必填
      
    
  
  
    
    ```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
    
      
        知识库 ID
      
      
        文档 ID
      
    
     ### Query
    
      
        搜索关键词,可选
      
      
        搜索状态,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
    
      
        知识库 ID
      
      
        文档分段ID
      
    
  
  
    
    ```bash {{ title: 'cURL' }}
    curl --location --request DELETE '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}' \
    --header 'Authorization: Bearer {api_key}' \
    --header 'Content-Type: application/json'
    ```
    
    
    ```json {{ title: 'Response' }}
    {
      "result": "success"
    }
    ```
    
  
---
  
    ### POST
    
      
        知识库 ID
      
      
        文档分段ID
      
    
    ### Request Body
    
      
        - content (text) 文本内容/问题内容,必填
        - answer (text) 答案内容,非必填,如果知识库的模式为qa模式则传值
        - keywords (list) 关键字,非必填
        - enabled (bool) false/true,非必填
      
    
  
  
    
    ```bash {{ title: 'cURL' }}
    curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}' \
    --header 'Authorization: Bearer {api_key}' \
    --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"
    }
    ```
    
  
---
  
    ### 错误信息
    
      
        返回的错误代码
      
    
    
      
        返回的错误状态
      
    
    
      
        返回的错误信息
      
    
  
  
    
    ```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. |