refactor: update Dockerfile and requirements for improved dependency management and build efficiency

Dockerfile

@@ -1,32 +1,37 @@
 # Use an official Python runtime as a parent image
-FROM python:3.10-slim
+FROM python:3.10-slim AS base
+ENV PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    PIP_NO_CACHE_DIR=1 \
+    PIP_DISABLE_PIP_VERSION_CHECK=1
 
-# Set the working directory in the container
 WORKDIR /app
 
-# Copy the dependencies file to the working directory
-COPY requirements.txt .
+# Install build essentials only if needed for wheels (kept minimal)
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    && rm -rf /var/lib/apt/lists/*
 
-# Install any needed packages specified in requirements.txt
-RUN pip install --no-cache-dir -r requirements.txt
-# Copy only application source (avoid copying dev files)
-COPY app.py /app/app.py
-COPY templates /app/templates
-COPY static /app/static
-# Copy the application package so `import src` works inside the container
-COPY src /app/src
-# Copy persisted data (e.g., chroma DB) so the container can access it if present
-COPY data /app/data
-# COPY the scripts directory so runtime init scripts (e.g. init_pgvector.py) exist
-COPY scripts /app/scripts
+COPY constraints.txt requirements.txt ./
+RUN python -m pip install --upgrade pip setuptools wheel \
+    && pip install --no-cache-dir -r requirements.txt -c constraints.txt --only-binary=:all: || \
+    pip install --no-cache-dir -r requirements.txt -c constraints.txt
 
-COPY run.sh /app/run.sh
+# Application source
+COPY app.py ./app.py
+COPY templates ./templates
+COPY static ./static
+COPY src ./src
+COPY data ./data
+COPY scripts ./scripts
+COPY run.sh ./run.sh
 
-# Make run.sh (and optionally the init script) executable
-RUN chmod +x /app/run.sh
-RUN chmod +x /app/scripts/init_pgvector.py || true
+RUN chmod +x run.sh && chmod +x scripts/init_pgvector.py || true
 
-# Expose port 10000
 EXPOSE 10000
-# Default entrypoint uses run.sh which starts gunicorn with configurable workers
 CMD ["/app/run.sh"]
+
+# Optional dev stage for local tooling (not used in final image)
+FROM base AS dev
+COPY dev-requirements.txt ./dev-requirements.txt
+RUN pip install --no-cache-dir -r dev-requirements.txt -c constraints.txt || true

constraints.txt

@@ -0,0 +1,17 @@
+# Pinned runtime dependency constraints (generated manually)
+Flask==3.0.3
+Werkzeug==3.0.3
+itsdangerous==2.2.0
+Jinja2==3.1.4
+click==8.1.7
+gunicorn==22.0.0
+numpy==1.26.4
+requests==2.32.3
+urllib3==2.2.2
+idna==3.7
+certifi==2024.7.4
+charset-normalizer==3.3.2
+psycopg2-binary==2.9.7
+optimum==1.22.0
+onnxruntime==1.18.1
+psutil==5.9.0

dev-requirements.txt

@@ -1,6 +1,15 @@
-pre-commit==3.5.0
-black>=25.0.0
-isort==5.13.0
-flake8==6.1.0
-psutil
-psycopg2-binary==2.9.7
+-r requirements.txt
+
+# Core dev tooling
+pre-commit==3.7.1
+black==24.8.0
+isort==5.13.2
+flake8==7.1.0
+pytest==8.2.2
+
+# Optional heavy packages used only for experimentation or legacy paths
+chromadb==0.4.24
+sentence-transformers==2.7.0
+
+# Keep psutil available for local diagnostics even if disabled in production
+psutil==5.9.0

requirements.txt

@@ -1,20 +1,10 @@
-# Core web framework
 Flask==3.0.3
 gunicorn==22.0.0
-
-# Vector database and embeddings
-chromadb==0.4.24
-sentence-transformers==2.7.0
-optimum[onnxruntime]
 psycopg2-binary==2.9.7
-
-# Core dependencies (pinned for reproducibility, Python 3.12 compatible)
 numpy==1.26.4
 requests==2.32.3
+optimum[onnxruntime]==1.22.0
+onnxruntime==1.18.1
+psutil==5.9.0
 
-# Optional: Add psutil for better memory monitoring in production
-# Uncomment if you want detailed memory metrics
-# psutil==5.9.0
-
-psutil
-pytest
+# Runtime-only requirements. Development and test tools are in dev-requirements.txt