langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-21 03:55:25 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

dify 是否支持API方式创建知识库且创建文档向量化存储呢 ？ #3985

New Issue
Closed
opened 2026-02-21 18:04:15 -05:00 by yindo · 1 comment
yindo commented 2026-02-21 18:04:15 -05:00
Owner
Copy Link
Copy Source

Originally created by @wangyao123456a on GitHub (Jun 5, 2024).

Self Checks

  • This is only for bug report, if you would like to ask a question, please head to Discussions.
  • I have searched for existing issues search for existing issues, including closed ones.
  • I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
  • Please do not modify this template :) and fill in all the required fields.

Dify version

0.3.21

Cloud or Self Hosted

Cloud, Self Hosted (Docker), Self Hosted (Source)

Steps to reproduce

1

✔️ Expected Behavior

1

❌ Actual Behavior

1

Originally created by @wangyao123456a on GitHub (Jun 5, 2024). ### Self Checks - [X] This is only for bug report, if you would like to ask a question, please head to [Discussions](https://github.com/langgenius/dify/discussions/categories/general). - [X] I have searched for existing issues [search for existing issues](https://github.com/langgenius/dify/issues), including closed ones. - [X] I confirm that I am using English to submit this report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)). - [X] Please do not modify this template :) and fill in all the required fields. ### Dify version 0.3.21 ### Cloud or Self Hosted Cloud, Self Hosted (Docker), Self Hosted (Source) ### Steps to reproduce 1 ### ✔️ Expected Behavior 1 ### ❌ Actual Behavior 1
yindo closed this issue 2026-02-21 18:04:15 -05:00
yindo commented 2026-02-21 18:04:15 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Jun 5, 2024):

是的，Dify 版本 0.3.21 支持通过 API 创建知识库并进行文档向量化存储。

以下是相关的 API 代码示例：

  1. 通过 API 创建知识库（数据集）：

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

  2. 文档向量化和存储：

    • 通过文本创建文档：

      curl --location --request POST 'https://api.dify.ai/v1/datasets/<uuid:dataset_id>/document/create_by_text>' \
--header 'Authorization: Bearer {api_key}' \
--header 'Content-Type: application/json' \
--data-raw '{
    "name": "Dify",
    "text": "Dify means Do it for you...",
    "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"
    }
}'

    • 通过文件创建文档：

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

    • 获取文档嵌入状态：

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

    • 删除文档：

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

    • 获取文档列表：

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

    • 添加新段落：

      curl 'https://api.dify.ai/v1/datasets/aac47674-31a8-4f12-aab2-9603964c4789/documents/2034e0c1-1b75-4532-849e-24e72666595b/segment' \
  --header 'Authorization: Bearer {api_key}' \
  --header 'Content-Type: application/json' \
  --data-raw $'"segments":[
  {"content":"Dify means Do it for you",
  "keywords":["Dify","Do"]
  }
  ]'
  --compressed

这些 API 端点允许创建数据集和添加文档，并进行向量化和存储。

更多详细信息可以参考 Dify 文档 [1][2][3][4][5].

To continue talking to Dosu, mention @dosu.

@dosubot[bot] commented on GitHub (Jun 5, 2024): <!-- Answer --> 是的，Dify 版本 0.3.21 支持通过 API 创建知识库并进行文档向量化存储。 以下是相关的 API 代码示例： 1. **通过 API 创建知识库（数据集）**： ```bash curl --location --request POST 'https://api.dify.ai/v1/datasets' \ --header 'Authorization: Bearer {api_key}' \ --header 'Content-Type: application/json' \ --data-raw '{"name": "name"}' ``` 2. **文档向量化和存储**： - **通过文本创建文档**： ```bash curl --location --request POST 'https://api.dify.ai/v1/datasets/<uuid:dataset_id>/document/create_by_text>' \ --header 'Authorization: Bearer {api_key}' \ --header 'Content-Type: application/json' \ --data-raw '{ "name": "Dify", "text": "Dify means Do it for you...", "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" } }' ``` - **通过文件创建文档**： ```bash curl --location POST 'https://api.dify.ai/v1/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"' ``` - **获取文档嵌入状态**： ```bash curl --location --request GET 'https://api.dify.ai/v1/datasets/{dataset_id}/documents/{batch}/indexing-status' \ --header 'Authorization: Bearer {api_key}' ``` - **删除文档**： ```bash curl --location --request DELETE 'https://api.dify.ai/v1/datasets/{dataset_id}/documents/{document_id}' \ --header 'Authorization: Bearer {api_key}' ``` - **获取文档列表**： ```bash curl --location --request GET 'https://api.dify.ai/v1/datasets/{dataset_id}/documents' \ --header 'Authorization: Bearer {api_key}' ``` - **添加新段落**： ```bash curl 'https://api.dify.ai/v1/datasets/aac47674-31a8-4f12-aab2-9603964c4789/documents/2034e0c1-1b75-4532-849e-24e72666595b/segment' \ --header 'Authorization: Bearer {api_key}' \ --header 'Content-Type: application/json' \ --data-raw $'"segments":[ {"content":"Dify means Do it for you", "keywords":["Dify","Do"] } ]' --compressed ``` 这些 API 端点允许创建数据集和添加文档，并进行向量化和存储。 更多详细信息可以参考 [Dify 文档](https://docs.dify.ai) <sup>[[1]](https://github.com/langgenius/dify-docs/blob/main/zh_CN/guides/knowledge-base/maintain-dataset-via-api.md)</sup><sup>[[2]](https://github.com/langgenius/dify-docs/blob/main/en/features/datasets/maintain-dataset-via-api.md)</sup><sup>[[3]](https://github.com/langgenius/dify-docs/blob/main/zh_CN/guides/knowledge-base/knowledge_and_documents_maintenance.md)</sup><sup>[[4]](https://github.com/langgenius/dify-docs/blob/main/zh_CN/guides/knowledge-base/create_knowledge_and_upload_documents.md)</sup><sup>[[5]](https://github.com/langgenius/dify-docs/blob/main/zh_CN/features/datasets/maintain-dataset-via-api.md)</sup>. <!-- Dosu Comment Footer --> *To continue talking to [Dosu](https://dosu.dev), mention @dosu.*
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Knowledge Pipeline
Proposal
WIP
cloud
dependencies
feat:webapp
good first issue
outdated
performance
pull-request
Mirrored from GitHub Pull Request
 python:uv
refactor
size:L
stale
status: accepting prs
status: blocked
status: in discussion
stt & tts
vulnerablity
web
wont-fix
🌊 feat:workflow
🌚 invalid
🐞 bug
👻 feat:rag
💪 enhancement
📚 documentation
🔨 feat:tools
🙋‍♂️ question
🙏 help wanted
🤔 cant-reproduce
🤖 feat:agent
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify#3985
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?