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 '${props.apiBaseUrl}/datasets/{dataset_id}/document/create-by-text' \ --header 'Authorization: Bearer {api_key}' \ --header 'Content-Type: application/json' \ --data-raw '{ "name": "text", "text": "text", "indexing_technique": "high_quality", "process_rule": { "mode": "automatic" } }' ``` ```json {{ title: 'Response' }} { "document": { "id": "", "position": 1, "data_source_type": "upload_file", "data_source_info": { "upload_file_id": "" }, "dataset_process_rule_id": "", "name": "text.txt", "created_from": "api", "created_by": "", "created_at": 1695690280, "tokens": 0, "indexing_status": "waiting", "error": null, "enabled": true, "disabled_at": null, "disabled_by": null, "archived": false, "display_status": "queuing", "word_count": 0, "hit_count": 0, "doc_form": "text_model" }, "batch": "" } ```
此接口基于已存在知识库,在此知识库的基础上通过文件创建新的文档 ### Path 知识库 ID ### Request Body - original_document_id 源文档 ID(选填) - 用于重新上传文档或修改文档清洗、分段配置,缺失的信息从源文档复制 - 源文档不可为归档的文档 - 当传入 original_document_id 时,代表文档进行更新操作,process_rule 为可填项目,不填默认使用源文档的分段方式 - 未传入 original_document_id 时,代表文档进行新增操作,process_rule 为必填 - indexing_technique 索引方式 - high_quality 高质量:使用 embedding 模型进行嵌入,构建为向量数据库索引 - economy 经济:使用 keyword table index 的倒排索引进行构建 - process_rule 处理规则 - mode (string) 清洗、分段模式 ,automatic 自动 / custom 自定义 - rules (object) 自定义规则(自动模式下,该字段为空) - pre_processing_rules (array[object]) 预处理规则 - id (string) 预处理规则的唯一标识符 - 枚举: - remove_extra_spaces 替换连续空格、换行符、制表符 - remove_urls_emails 删除 URL、电子邮件地址 - enabled (bool) 是否选中该规则,不传入文档 ID 时代表默认值 - segmentation (object) 分段规则 - separator 自定义分段标识符,目前仅允许设置一个分隔符。默认为 \n - max_tokens 最大长度(token)默认为 1000 需要上传的文件。 ```bash {{ title: 'cURL' }} curl --location --request POST '${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(必填) 知识库描述(选填) 索引模式(选填,建议填写) - high_quality 高质量 - economy 经济 权限(选填,默认 only_me) - only_me 仅自己 - all_team_members 所有团队成员 - partial_members 部分团队成员 Provider(选填,默认 vendor) - vendor 上传文件 - external 外部知识库 外部知识库 API_ID(选填) 外部知识库 ID(选填) ```bash {{ title: 'cURL' }} curl --location --request POST '${props.apiBaseUrl}/datasets' \ --header 'Authorization: Bearer {api_key}' \ --header 'Content-Type: application/json' \ --data-raw '{ "name": "name", "permission": "only_me" }' ``` ```json {{ title: 'Response' }} { "id": "", "name": "name", "description": null, "provider": "vendor", "permission": "only_me", "data_source_type": null, "indexing_technique": null, "app_count": 0, "document_count": 0, "word_count": 0, "created_by": "", "created_at": 1695636173, "updated_by": "", "updated_at": 1695636173, "embedding_model": null, "embedding_model_provider": null, "embedding_available": null } ```
### Query 页码 返回条数,默认 20,范围 1-100 ```bash {{ title: 'cURL' }} curl --location --request GET '${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 } ```
### Path 知识库 ID ```bash {{ title: 'cURL' }} curl --location --request DELETE '${props.apiBaseUrl}/datasets/{dataset_id}' \ --header 'Authorization: Bearer {api_key}' ``` ```text {{ title: 'Response' }} 204 No Content ```
此接口基于已存在知识库,在此知识库的基础上通过文本更新文档 ### Path 知识库 ID 文档 ID ### Request Body 文档名称(选填) 文档内容(选填) 处理规则(选填) - mode (string) 清洗、分段模式 ,automatic 自动 / custom 自定义 - rules (object) 自定义规则(自动模式下,该字段为空) - pre_processing_rules (array[object]) 预处理规则 - id (string) 预处理规则的唯一标识符 - 枚举: - remove_extra_spaces 替换连续空格、换行符、制表符 - remove_urls_emails 删除 URL、电子邮件地址 - enabled (bool) 是否选中该规则,不传入文档 ID 时代表默认值 - segmentation (object) 分段规则 - separator 自定义分段标识符,目前仅允许设置一个分隔符。默认为 \n - max_tokens 最大长度(token)默认为 1000 ```bash {{ title: 'cURL' }} curl --location --request POST '${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 '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/update-by-file' \ --header 'Authorization: Bearer {api_key}' \ --form 'data="{\"name\":\"Dify\",\"indexing_technique\":\"high_quality\",\"process_rule\":{\"rules\":{\"pre_processing_rules\":[{\"id\":\"remove_extra_spaces\",\"enabled\":true},{\"id\":\"remove_urls_emails\",\"enabled\":true}],\"segmentation\":{\"separator\":\"###\",\"max_tokens\":500}},\"mode\":\"custom\"}}";type=text/plain' \ --form 'file=@"/path/to/file"' ``` ```json {{ title: 'Response' }} { "document": { "id": "", "position": 1, "data_source_type": "upload_file", "data_source_info": { "upload_file_id": "" }, "dataset_process_rule_id": "", "name": "Dify.txt", "created_from": "api", "created_by": "", "created_at": 1695308667, "tokens": 0, "indexing_status": "waiting", "error": null, "enabled": true, "disabled_at": null, "disabled_by": null, "archived": false, "display_status": "queuing", "word_count": 0, "hit_count": 0, "doc_form": "text_model" }, "batch": "20230921150427533684" } ```
### Path 知识库 ID 上传文档的批次号 ```bash {{ title: 'cURL' }} curl --location --request GET '${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 Q&A 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 ID 文档分段ID ```bash {{ title: 'cURL' }} curl --location --request DELETE '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}' \ --header 'Authorization: Bearer {api_key}' \ --header 'Content-Type: application/json' ``` ```json {{ title: 'Response' }} { "result": "success" } ```
### POST 知识库 ID 文档 ID 文档分段ID ### Request Body - content (text) 文本内容/问题内容,必填 - answer (text) 答案内容,非必填,如果知识库的模式为 Q&A 模式则传值 - keywords (list) 关键字,非必填 - enabled (bool) false/true,非必填 ```bash {{ title: 'cURL' }} curl --location --request POST '${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" } ```
### Path 知识库 ID ### Request Body 检索关键词 检索参数(选填,如不填,按照默认方式召回) - search_method (text) 检索方法:以下三个关键字之一,必填 - keyword_search 关键字检索 - semantic_search 语义检索 - full_text_search 全文检索 - hybrid_search 混合检索 - reranking_enable (bool) 是否启用 Reranking,非必填,如果检索模式为 semantic_search 模式或者 hybrid_search 则传值 - reranking_mode (object) Rerank模型配置,非必填,如果启用了 reranking 则传值 - reranking_provider_name (string) Rerank 模型提供商 - reranking_model_name (string) Rerank 模型名称 - weights (double) 混合检索模式下语意检索的权重设置 - top_k (integer) 返回结果数量,非必填 - score_threshold_enabled (bool) 是否开启 score 阈值 - score_threshold (double) Score 阈值 未启用字段 ```bash {{ title: 'cURL' }} curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/retrieve' \ --header 'Authorization: Bearer {api_key}' \ --header 'Content-Type: application/json' \ --data-raw '{ "query": "test", "retrieval_model": { "search_method": "keyword_search", "reranking_enable": false, "reranking_mode": null, "reranking_model": { "reranking_provider_name": "", "reranking_model_name": "" }, "weights": null, "top_k": 2, "score_threshold_enabled": false, "score_threshold": null } }' ``` ```json {{ title: 'Response' }} { "query": { "content": "test" }, "records": [ { "segment": { "id": "7fa6f24f-8679-48b3-bc9d-bdf28d73f218", "position": 1, "document_id": "a8c6c36f-9f5d-4d7a-8472-f5d7b75d71d2", "content": "Operation guide", "answer": null, "word_count": 847, "tokens": 280, "keywords": [ "install", "java", "base", "scripts", "jdk", "manual", "internal", "opens", "add", "vmoptions" ], "index_node_id": "39dd8443-d960-45a8-bb46-7275ad7fbc8e", "index_node_hash": "0189157697b3c6a418ccf8264a09699f25858975578f3467c76d6bfc94df1d73", "hit_count": 0, "enabled": true, "disabled_at": null, "disabled_by": null, "status": "completed", "created_by": "dbcb1ab5-90c8-41a7-8b78-73b235eb6f6f", "created_at": 1728734540, "indexing_at": 1728734552, "completed_at": 1728734584, "error": null, "stopped_at": null, "document": { "id": "a8c6c36f-9f5d-4d7a-8472-f5d7b75d71d2", "data_source_type": "upload_file", "name": "readme.txt", "doc_type": null } }, "score": 3.730463140527718e-05, "tsne_position": null } ] } ```
### 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.