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. |