Skip to content

Commit

Permalink
fix: UI tab name and reranking process for TeiFastReranking (#576)
Browse files Browse the repository at this point in the history
* 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>
  • Loading branch information
3 people authored Dec 17, 2024
1 parent 9039b4f commit cd87a7e
Show file tree
Hide file tree
Showing 3 changed files with 23 additions and 18 deletions.
32 changes: 16 additions & 16 deletions Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -4,15 +4,15 @@ FROM python:3.10-slim AS lite
# Common dependencies
RUN apt-get update -qqy && \
apt-get install -y --no-install-recommends \
ssh \
git \
gcc \
g++ \
poppler-utils \
libpoppler-dev \
unzip \
curl \
cargo
ssh \
git \
gcc \
g++ \
poppler-utils \
libpoppler-dev \
unzip \
curl \
cargo

# Setup args
ARG TARGETPLATFORM
Expand Down Expand Up @@ -62,13 +62,13 @@ FROM lite AS full
# Additional dependencies for full version
RUN apt-get update -qqy && \
apt-get install -y --no-install-recommends \
tesseract-ocr \
tesseract-ocr-jpn \
libsm6 \
libxext6 \
libreoffice \
ffmpeg \
libmagic-dev
tesseract-ocr \
tesseract-ocr-jpn \
libsm6 \
libxext6 \
libreoffice \
ffmpeg \
libmagic-dev

# Install torch and torchvision for unstructured
RUN --mount=type=ssh \
Expand Down
2 changes: 1 addition & 1 deletion docs/pages/app/ext/user-management.md
Original file line number Diff line number Diff line change
Expand Up @@ -11,4 +11,4 @@ Once enabled, you have access to the following features:

- User login/logout (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 changes: 6 additions & 1 deletion libs/kotaemon/kotaemon/rerankings/tei_fast_rerank.py
Original file line number Diff line number Diff line change
Expand Up @@ -29,13 +29,18 @@ class TeiFastReranking(BaseReranking):
),
)
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):
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(
url=self.endpoint_url,
json={
"query": query,
"texts": texts,
"texts": truncated_texts,
"is_truncated": self.is_truncated, # default is True
},
).json()
Expand Down

0 comments on commit cd87a7e

Please sign in to comment.