Create Dockerfile

Dockerfile

@@ -0,0 +1,35 @@
+FROM python:3.10-slim
+
+WORKDIR /app
+
+# 1. Install System Dependencies (The Heavy Lifting)
+# build-essential: for compiling python libs
+# curl/git: standard tools
+# tesseract-ocr: The OCR engine for OCREnhancedPDFLoader
+# poppler-utils: Required by pdf2image to convert PDF pages to images
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    curl \
+    git \
+    tesseract-ocr \
+    poppler-utils \
+    && rm -rf /var/lib/apt/lists/*
+
+# 2. Install Python Libraries
+COPY requirements.txt ./
+RUN pip3 install --no-cache-dir -r requirements.txt
+
+# 3. Download NLP Models (Bake them into the image)
+# Spacy model for your Chunkers
+RUN python -m spacy download en_core_web_sm
+# NLTK data for your TextPreprocessor
+RUN python -m nltk.downloader stopwords wordnet omw-1.4
+
+# 4. Copy Application Code
+COPY src/ ./src/
+
+# 5. Config
+EXPOSE 8501
+HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
+
+ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0", "--server.enableCORS=false", "--server.enableXsrfProtection=false"]