Docker reproducibility

Author: RonaldRonnie

Dockerfile

@@ -1,69 +1,35 @@
-# BioAnalyzer Backend Dockerfile
 FROM python:3.11-slim
 
 WORKDIR /app
-
-# FIX: Make Python recognize the application as a package
 ENV PYTHONPATH="/app:/app/app"
 
-# Install system dependencies
 RUN apt-get update && apt-get install -y \
-    gcc \
-    g++ \
-    curl \
-    git \
+    gcc g++ curl git \
     && rm -rf /var/lib/apt/lists/*
 
-# Copy pyproject.toml and README.md first for better caching
 COPY pyproject.toml README.md ./
 
-# Upgrade pip and setuptools first
 RUN pip install --upgrade pip setuptools wheel build
 
-# ------------------------------------------------------------
-# Step 1: Install PyTorch CPU versions (fixed +cpu issue)
-# Note: PyTorch CPU versions require special index URL, so we install them separately
-# before installing the package from pyproject.toml
-# ------------------------------------------------------------
-RUN pip install --no-cache-dir --default-timeout=600 --retries=10 \
-    --extra-index-url https://download.pytorch.org/whl/cpu \
-    torch==2.1.0+cpu \
-    torchvision==0.16.0+cpu \
-    torchaudio==2.1.0+cpu
+# Install PyTorch CPU wheels
+RUN pip install --no-cache-dir --extra-index-url https://download.pytorch.org/whl/cpu \
+    torch==2.1.0+cpu torchvision==0.16.0+cpu torchaudio==2.1.0+cpu
 
-# ------------------------------------------------------------
-# Step 2: Copy application code
-# ------------------------------------------------------------
 COPY . .
 
-# ------------------------------------------------------------
-# Step 3: Install the package from pyproject.toml
-# This installs the package and all its dependencies from pyproject.toml
-# PyTorch is already installed above, so pip will skip it
-# Installing in editable mode (-e) ensures entry points are properly installed
-# ------------------------------------------------------------
-RUN pip install --no-cache-dir --default-timeout=300 --retries=5 -e .
+# Install package + dependencies
+RUN pip install --no-cache-dir -e .
 
-# ------------------------------------------------------------
-# Step 4: Install testing dependencies (optional, for development)
-# ------------------------------------------------------------
-RUN pip install --no-cache-dir pytest>=7.4.0 pytest-cov>=4.1.0
+# Explicit analysis deps (defensive)
+RUN pip install --no-cache-dir pandas scikit-learn matplotlib seaborn
 
-# Create necessary directories
 RUN mkdir -p cache logs results
 
-# Make CLI executable
-RUN chmod +x cli.py
+RUN chmod +x cli.py || true
+RUN chmod +x scripts/*.py || true
 
-# Expose port
 EXPOSE 8000
 
-# Health check
-HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 \
-    CMD curl -f http://localhost:8000/health || exit 1
-
-# Set PYTHONPATH for app module imports (fixed nested /app/app issue)
-# ENV PYTHONPATH=/app:/app/app
+HEALTHCHECK CMD curl -f http://localhost:8000/health || exit 1
 
-# Default command (can be overridden)
 CMD ["python", "main.py", "--host", "0.0.0.0", "--port", "8000"]

config/requirements.txt

@@ -10,8 +10,8 @@ torchaudio>=2.1.0+cpu
 numpy>=1.26.0
 pandas>=2.1.1
 scikit-learn>=1.3.0
-matplotlib>=3.7
-seaborn>=0.12
+matplotlib>=3.7.0
+seaborn>=0.12.0
 biopython>=1.81
 pytz>=2023.3
 
@@ -29,7 +29,7 @@ paper-qa>=5.0.0
 # --- Vector Database ---
 qdrant-client>=1.7.0
 
-# --- Web Framework & API (FastAPI/Uvicorn) ---
+# --- Web Framework & API ---
 fastapi>=0.104.0
 uvicorn[standard]>=0.23.2
 starlette>=0.31.1
@@ -47,19 +47,15 @@ wsproto>=1.0.0
 h11>=0.12.0
 httptools>=0.3.0
 
-# --- File Processing (Excel/Env) ---
+# --- File Processing ---
 openpyxl>=3.1.0
 xlrd>=2.0.1
 python-dotenv>=1.0.0
 PyYAML>=5.4.1
 aiofiles>=0.7.0
 
-# --- Utilities & System ---
-tqdm>=4.65.0`
+# --- Utilities ---
+tqdm>=4.65.0
 psutil>=5.9.0
 click>=8.0.1
 watchfiles[watchdog]>=1.0.0
-
-# --- Development (Uncomment to install) ---
-# pytest>=7.4.0
-# pytest-cov>=4.1.0