简体中文

通过 API 维护知识库

鉴权、调用方式与应用 Service API 保持一致，不同之处在于，所生成的单个知识库 API token 具备操作当前账号下所有可见知识库的权限，请注意数据安全。

使用知识库 API 的优势

通过 API 维护知识库可大幅提升数据处理效率，你可以通过命令行轻松同步数据，实现自动化操作，而无需在用户界面进行繁琐操作。

主要优势包括:

  • 自动同步: 将数据系统与 Dify 知识库无缝对接，构建高效工作流程；

  • 全面管理: 提供知识库列表，文档列表及详情查询等功能，方便你自建数据管理界面；

  • 灵活上传: 支持纯文本和文件上传方式,可针对分段（Chunks）内容的批量新增和修改操作；

  • 提高效率: 减少手动处理时间，提升 Dify 平台使用体验。

如何使用

进入知识库页面，在左侧的导航中切换至 API 页面。在该页面中你可以查看 Dify 提供的知识库 API 文档，并可以在 API 密钥 中管理可访问知识库 API 的凭据。

API 调用示例

通过文本创建文档

输入示例：

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"}}'

输出示例：

{
  "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": ""
}

通过文件创建文档

输入示例：

curl --location --request POST 'https://api.dify.ai/v1/datasets/{dataset_id}/document/create_by_file' \
--header 'Authorization: Bearer {api_key}' \
--form 'data="{"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"'

输出示例：

{
  "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": ""
}

创建空知识库

仅用来创建空知识库

输入示例：

curl --location --request POST 'https://api.dify.ai/v1/datasets' \
--header 'Authorization: Bearer {api_key}' \
--header 'Content-Type: application/json' \
--data-raw '{"name": "name", "permission": "only_me"}'

输出示例：

{
  "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
}

知识库列表

输入示例：

curl --location --request GET 'https://api.dify.ai/v1/datasets?page=1&limit=20' \
--header 'Authorization: Bearer {api_key}'

输出示例：

{
  "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
}

删除知识库

输入示例：

curl --location --request DELETE 'https://api.dify.ai/v1/datasets/{dataset_id}' \
--header 'Authorization: Bearer {api_key}'

输出示例：

204 No Content

通过文本更新文档

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

输入示例：

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"}'

输出示例：

{
  "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": ""
}

通过文件更新文档

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。

输入示例：

curl --location --request POST 'https://api.dify.ai/v1/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"'

输出示例：

{
  "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"
}

获取文档嵌入状态（进度）

输入示例：

curl --location --request GET 'https://api.dify.ai/v1/datasets/{dataset_id}/documents/{batch}/indexing-status' \
--header 'Authorization: Bearer {api_key}'

输出示例：

{
  "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
  }]
}

删除文档

输入示例：

curl --location --request DELETE 'https://api.dify.ai/v1/datasets/{dataset_id}/documents/{document_id}' \
--header 'Authorization: Bearer {api_key}'

输出示例：

{
  "result": "success"
}

知识库文档列表

输入示例：

curl --location --request GET 'https://api.dify.ai/v1/datasets/{dataset_id}/documents' \
--header 'Authorization: Bearer {api_key}'

输出示例：

{
  "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
}

新增分段

输入示例：

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"]}]}'

输出示例：

{
  "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"
}

查询文档分段

输入示例：

curl --location --request GET 'https://api.dify.ai/v1/datasets/{dataset_id}/documents/{document_id}/segments' \
--header 'Authorization: Bearer {api_key}' \
--header 'Content-Type: application/json'

输出示例：

{
  "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"
}

删除文档分段

输入示例：

curl --location --request DELETE 'https://api.dify.ai/v1/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}' \
--header 'Authorization: Bearer {api_key}' \
--header 'Content-Type: application/json'

输出示例：

{
  "result": "success"
}

更新文档分段

输入示例：

curl --location --request POST 'https://api.dify.ai/v1/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}}'

输出示例：

{
  "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

错误信息错误码原因描述

no_file_uploaded

400

请上传你的文件

too_many_files

400

只允许上传一个文件

file_too_large

413

文件大小超出限制

unsupported_file_type

415

不支持的文件类型。目前只支持以下内容格式：txt, markdown, md, pdf, html, html, xlsx, docx, csv

high_quality_dataset_only

400

当前操作仅支持"高质量"知识库

dataset_not_initialized

400

知识库仍在初始化或索引中。请稍候

archived_document_immutable

403

归档文档不可编辑

dataset_name_duplicate

409

知识库名称已存在，请修改你的知识库名称

invalid_action

400

无效操作

document_already_finished

400

文档已处理完成。请刷新页面或查看文档详情

document_indexing

400

文档正在处理中，无法编辑

invalid_metadata

400

元数据内容不正确。请检查并验证

Previous召回测试/引用归属Next外部知识库 API

Last updated