Modified download_deps.py (#2747)

### What problem does this PR solve?

Modified download_deps.py

### Type of change

- [ ] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [x] Other (please describe): CI

.github/workflows/tests.yml

@@ -48,7 +48,7 @@ jobs:
       - name: Build ragflow:dev-slim
         run: |
           RUNNER_WORKSPACE_PREFIX=${RUNNER_WORKSPACE_PREFIX:-$HOME}
-          cp -r ${RUNNER_WORKSPACE_PREFIX}/huggingface.co ${RUNNER_WORKSPACE_PREFIX}/nltk_data .
+          cp -r ${RUNNER_WORKSPACE_PREFIX}/huggingface.co ${RUNNER_WORKSPACE_PREFIX}/nltk_data ${RUNNER_WORKSPACE_PREFIX}/libssl*.deb .
           sudo docker pull ubuntu:24.04
           sudo docker build -f Dockerfile.slim -t infiniflow/ragflow:dev-slim .
 

Dockerfile

@@ -24,8 +24,9 @@ RUN --mount=type=cache,id=ragflow_base_apt,target=/var/cache/apt,sharing=locked
 
 # https://forum.aspose.com/t/aspose-slides-for-net-no-usable-version-of-libssl-found-with-linux-server/271344/13
 # aspose-slides on linux/arm64 is unavailable
-RUN if [ "${ARCH}" = "amd64" ]; then \
-        curl -o libssl1.deb http://archive.ubuntu.com/ubuntu/pool/main/o/openssl/libssl1.1_1.1.1f-1ubuntu2_amd64.deb && dpkg -i libssl1.deb && rm -f libssl1.deb; \
+RUN --mount=type=bind,source=libssl1.1_1.1.1f-1ubuntu2_amd64.deb,target=/root/libssl1.1_1.1.1f-1ubuntu2_amd64.deb \
+    if [ "${ARCH}" = "amd64" ]; then \
+        dpkg -i /root/libssl1.1_1.1.1f-1ubuntu2_amd64.deb; \
     fi
 
 ENV PYTHONDONTWRITEBYTECODE=1 DOTNET_SYSTEM_GLOBALIZATION_INVARIANT=1

download_deps.py

@@ -3,6 +3,11 @@
 from huggingface_hub import snapshot_download
 import nltk
 import os
+import urllib.request
+
+urls = [
+    "http://archive.ubuntu.com/ubuntu/pool/main/o/openssl/libssl1.1_1.1.1f-1ubuntu2_amd64.deb",
+]
 
 repos = [
     "InfiniFlow/text_concat_xgb_v1.0",
@@ -20,6 +25,12 @@ def download_model(repo_id):
 
 
 if __name__ == "__main__":
+    for url in urls:
+        filename = url.split("/")[-1]
+        print(f"Downloading {url}...")
+        if not os.path.exists(filename):
+            urllib.request.urlretrieve(url, filename)
+
     local_dir = os.path.abspath('nltk_data')
     for data in ['wordnet', 'punkt', 'punkt_tab']:
         print(f"Downloading nltk {data}...")