pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

Feat(nlp): add "怎么办" pattern to question word removal (#10284)

Browse Source 
### What problem does this PR solve?

Added "怎么办" to the regex pattern in rmWWW method to improve query
cleaning by removing this common question phrase along with other
question words.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
This commit is contained in:
Liu An
2025-09-25 16:47:56 +08:00
committed by GitHub
parent 7ac95b759b
commit 9e323a9351
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
rag/nlp/query.py
View File

@ -56,7 +56,7 @@ class FulltextQueryer:
def rmWWW(txt): def rmWWW(txt):
patts = [ patts = [
( (
r"是*(什么样的|哪家|一下|那家|请问|啥样|咋样了|什么时候|何时|何地|何人|是否|是不是|多少|哪里|怎么|哪儿|怎么样|如何|哪些|是啥|啥是|啊|吗|呢|吧|咋|什么|有没有|呀|谁|哪位|哪个)是*", r"是*(怎么办|什么样的|哪家|一下|那家|请问|啥样|咋样了|什么时候|何时|何地|何人|是否|是不是|多少|哪里|怎么|哪儿|怎么样|如何|哪些|是啥|啥是|啊|吗|呢|吧|咋|什么|有没有|呀|谁|哪位|哪个)是*",
"", "",
), ),
(r"(^| )(what|who|how|which|where|why)('re|'s)? ", " "), (r"(^| )(what|who|how|which|where|why)('re|'s)? ", " "),