langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-21 12:05:30 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

回答没按训练集中的数据来【bug】 #182

New Issue
Closed
opened 2026-02-21 17:26:17 -05:00 by yindo · 4 comments
yindo commented 2026-02-21 17:26:17 -05:00
Owner
Copy Link
Copy Source

Originally created by @allentofight on GitHub (Jun 18, 2023).

数据传的 text，格式如下

问题:xxx
回答:xxx

问题:xxx
回答:xxx

问题:xxx
回答:xxx

使用自动模式分段后的问答有一段是下面这样的，
image

但在 preview 中提问却是下面这样这样的回答，不是训练数据中的回答
image

Originally created by @allentofight on GitHub (Jun 18, 2023). 数据传的 text，格式如下 ``` 问题:xxx 回答:xxx 问题:xxx 回答:xxx 问题:xxx 回答:xxx ``` 使用自动模式分段后的问答有一段是下面这样的， ![image](https://github.com/langgenius/dify/assets/1235483/b7e4f2b7-bc1d-4575-8aec-d7c01139d3fd) 但在 preview 中提问却是下面这样这样的回答，不是训练数据中的回答 ![image](https://github.com/langgenius/dify/assets/1235483/d76a1c29-c564-484d-9a64-2918abb28d6c)
yindo closed this issue 2026-02-21 17:26:17 -05:00
yindo commented 2026-02-21 17:26:17 -05:00
Author
Owner
Copy Link
Copy Source

@allentofight commented on GitHub (Jun 18, 2023):

发现它命中的是下面这一条
image

@allentofight commented on GitHub (Jun 18, 2023): 发现它命中的是下面这一条 ![image](https://github.com/langgenius/dify/assets/1235483/1a9d6977-e9f0-4077-ab68-acecae9eb622)
yindo commented 2026-02-21 17:26:17 -05:00
Author
Owner
Copy Link
Copy Source

@allentofight commented on GitHub (Jun 18, 2023):

大概知道原因了，回答中最好要增加提问问题中关键词的权重，如在回答中增加几个"机器人掉线"这样的关键词就能命中了

@allentofight commented on GitHub (Jun 18, 2023): 大概知道原因了，回答中最好要增加提问问题中关键词的权重，如在回答中增加几个"机器人掉线"这样的关键词就能命中了
yindo commented 2026-02-21 17:26:17 -05:00
Author
Owner
Copy Link
Copy Source

@rocymp commented on GitHub (Aug 8, 2023):

大概知道原因了，回答中最好要增加提问问题中关键词的权重，如在回答中增加几个"机器人掉线"这样的关键词就能命中了

向量匹配是按回答内容匹配的么？

@rocymp commented on GitHub (Aug 8, 2023): > 大概知道原因了，回答中最好要增加提问问题中关键词的权重，如在回答中增加几个"机器人掉线"这样的关键词就能命中了 向量匹配是按回答内容匹配的么？
yindo commented 2026-02-21 17:26:17 -05:00
Author
Owner
Copy Link
Copy Source

@allentofight commented on GitHub (Aug 15, 2023):

大概知道原因了，回答中最好要增加提问问题中关键词的权重，如在回答中增加几个"机器人掉线"这样的关键词就能命中了

向量匹配是按回答内容匹配的么？

实测是按切片中内容的匹配度来的

@allentofight commented on GitHub (Aug 15, 2023): > > 大概知道原因了，回答中最好要增加提问问题中关键词的权重，如在回答中增加几个"机器人掉线"这样的关键词就能命中了 > > 向量匹配是按回答内容匹配的么？ 实测是按切片中内容的匹配度来的
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outdated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#182
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?