Public/kotaemon
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: UI tab name and reranking process for TeiFastReranking (#576)

Browse Source 
* fix: update user-management.md

* fix: reranking process when TeiFastReranking is specified.

---------

Co-authored-by: Ryuichi Takano <45957617+tknrych@users.noreply.github.com>
Co-authored-by: Ryuichi Takano <ryuichi.takano@jp.ricoh.com>
This commit is contained in:
Tuan Anh Nguyen Dang (Tadashi_Cin) 2024-12-17 17:23:54 +07:00 committed by GitHub
parent 9039b4f32b
commit cd87a7e35f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 23 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/pages/app/ext/user-management.md
View File

@ -11,4 +11,4 @@ Once enabled, you have access to the following features:
- User login/logout (located in Settings Tab) - User login/logout (located in Settings Tab)
- User changing password (located in Settings Tab) - User changing password (located in Settings Tab)
- Create / List / Edit / Delete user (located in Admin > User Management Tab) - Create / List / Edit / Delete user (located in Resources > Users Tab)

7
libs/kotaemon/kotaemon/rerankings/tei_fast_rerank.py
View File

@ -29,13 +29,18 @@ class TeiFastReranking(BaseReranking):
), ),
) )
is_truncated: Optional[bool] = Param(True, help="Whether to truncate the inputs") is_truncated: Optional[bool] = Param(True, help="Whether to truncate the inputs")
max_tokens: Optional[int] = Param(512, help="This option is used to specify the maximum number of tokens supported by the reranker model.")
def client(self, query, texts): def client(self, query, texts):
if self.is_truncated == True:
max_tokens = self.max_tokens # default is 512 tokens.
truncated_texts = [text[:max_tokens] for text in texts]
response = session.post( response = session.post(
url=self.endpoint_url, url=self.endpoint_url,
json={ json={
"query": query, "query": query,
"texts": texts, "texts": truncated_texts,
"is_truncated": self.is_truncated, # default is True "is_truncated": self.is_truncated, # default is True
}, },
).json() ).json()