upgrade version

.github/workflows/build-push.yml

@@ -5,6 +5,7 @@ on:
     branches:
       - "main"
       - "deploy/dev"
+      - "feat/upgrade-unstructured-version-10.2"
   release:
     types: [published]
 

api/Dockerfile

@@ -49,25 +49,25 @@ ENV TZ=UTC
 WORKDIR /app/api
 
 RUN apt-get update \
-    && apt-get install -y --no-install-recommends curl nodejs libgmp-dev libmpfr-dev libmpc-dev \
+    # Install dependencies
-    # if you located in China, you can use aliyun mirror to speed up
+    && apt-get install -y --no-install-recommends \
-    # && echo "deb http://mirrors.aliyun.com/debian testing main" > /etc/apt/sources.list \
+        # basic environment
-    && echo "deb http://deb.debian.org/debian testing main" > /etc/apt/sources.list \
+        curl nodejs libgmp-dev libmpfr-dev libmpc-dev \
-    && apt-get update \
         # For Security
-    && apt-get install -y --no-install-recommends zlib1g=1:1.3.dfsg+really1.3.1-1 expat=2.6.3-1 libldap-2.5-0=2.5.18+dfsg-3+b1 perl=5.40.0-6 libsqlite3-0=3.46.1-1 \
+        expat libldap-2.5-0 perl libsqlite3-0 zlib1g \
         # install a chinese font to support the use of tools like matplotlib
-    && apt-get install -y fonts-noto-cjk \
+        fonts-noto-cjk \
+        # install libmagic to support the use of python-magic guess MIMETYPE
+        libmagic1 \
     && apt-get autoremove -y \
     && rm -rf /var/lib/apt/lists/*
-
 # Copy Python environment and packages
 ENV VIRTUAL_ENV=/app/api/.venv
 COPY --from=packages ${VIRTUAL_ENV} ${VIRTUAL_ENV}
 ENV PATH="${VIRTUAL_ENV}/bin:${PATH}"
 
 # Download nltk data
-RUN python -c "import nltk; nltk.download('punkt'); nltk.download('averaged_perceptron_tagger')"
+RUN python -c "import nltk; nltk.download('punkt'); nltk.download('punkt_tab'); nltk.download('averaged_perceptron_tagger')"
 
 # Copy source code
 COPY . /app/api/

api/pyproject.toml

@@ -177,7 +177,7 @@ tencentcloud-sdk-python-hunyuan = "~3.0.1158"
 tiktoken = "~0.8.0"
 tokenizers = "~0.15.0"
 transformers = "~4.35.0"
-unstructured = { version = "~0.16.1", extras = ["docx", "epub", "md", "msg", "ppt", "pptx"] }
+unstructured = { version = "~0.16.13", extras = ["docx", "epub", "md", "msg", "ppt", "pptx"] }
 validators = "0.21.0"
 volcengine-python-sdk = {extras = ["ark"], version = "~1.0.98"}
 websocket-client = "~1.7.0"