fix: fixed issue with package versions

.gitignore

@@ -172,3 +172,6 @@ cython_debug/
 
 # PyPI configuration file
 .pypirc
+
+# jupyter notebooks
+*.ipynb

Dockerfile

@@ -12,15 +12,22 @@ RUN apt-get update && \
     apt-get install -y --no-install-recommends \
     build-essential \
     ffmpeg \
-    
     # for hnswlib (needed for OpenMP)
     libgomp1 \
+    curl \
+    git \
     && rm -rf /var/lib/apt/lists/*
 
 # Copy and install Python dependencies
 COPY requirements.txt ./
 RUN pip install --no-cache-dir -r requirements.txt
 
+# Install/patch MinerU and download models
+RUN pip uninstall -y magic-pdf && \
+    pip install git+https://github.com/opendatalab/MinerU.git@dev && \
+    curl -L https://github.com/opendatalab/MinerU/raw/dev/scripts/download_models_hf.py -o download_models_hf.py && \
+    python download_models_hf.py
+
 # Copy application code
 COPY src/ ./src/
 COPY tests/ ./tests/

requirements.txt

@@ -1,9 +1,7 @@
 # Core
 streamlit>=1.25.0
-mineru>=0.1.0
 sentence-transformers>=2.2.2
 rank-bm25>=0.2.2
-redis>=4.5.1
 hnswlib>=0.7.0
 transformers>=4.29.2
 torch>=2.0.0