Update Dockerfile and .dockerignore; modify download_assets.py to use specific ChromaDB path

.dockerignore

@@ -26,4 +26,5 @@ data/
 .chroma/
 embeddings/
 data/
-models/
+models/
+chromadb.tar.gz

Dockerfile

@@ -1,28 +1,27 @@
 FROM python:3.11-slim
 
-WORKDIR /
+WORKDIR /app
 
-# Install curl for healthcheck
-RUN apt-get update && apt-get install -y \
-    curl \
-    && rm -rf /var/lib/apt/lists/*
+# Install only curl for healthcheck
+RUN apt-get update && apt-get install -y curl && rm -rf /var/lib/apt/lists/*
 
-# RUN git clone https://github.com/mujeeb-gh/rag-chatbot-final.git .
+# Copy and install dependencies FIRST (this layer only rebuilds when requirements.txt changes)
+COPY requirements.txt .
+RUN pip install --no-cache-dir --upgrade pip && \
+    pip install --no-cache-dir -r requirements.txt
 
+# Copy application code LAST (changes here won't invalidate pip install)
 COPY . .
 
-RUN pip3 install -r requirements.txt
+ENV PYTHONPATH=/app/app
 
-EXPOSE 8501
+# Create entrypoint script
+RUN echo '#!/bin/bash\n\
+python3 -m app.scripts.download_assets\n\
+exec streamlit run app/main.py --server.port=8501 --server.address=0.0.0.0\n\
+' > /entrypoint.sh && chmod +x /entrypoint.sh
 
+EXPOSE 8501
 HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
 
-WORKDIR /app
-
-# Create entrypoint script that downloads assets before starting Streamlit
-RUN echo '#!/bin/bash\n\
-python3 /app/scripts/download_assets.py\n\
-exec streamlit run main.py --server.port=8501 --server.address=0.0.0.0\n\
-' > /app/entrypoint.sh && chmod +x /app/entrypoint.sh
-
-ENTRYPOINT ["/app/entrypoint.sh"]
+ENTRYPOINT ["/entrypoint.sh"]

app/scripts/download_assets.py

@@ -85,7 +85,7 @@ def download_chromadb(chromadb_repo: str, chromadb_dir: Path, hf_token: str | No
     print(f"Checking ChromaDB in {chromadb_dir}...")
     
     # Check if ChromaDB directory already has content
-    expected_chroma_path = chromadb_dir / settings.chroma_db
+    expected_chroma_path = chromadb_dir / "bge-small-finetuned-chroma" # should be settings.chroma_db
     if expected_chroma_path.exists() and any(expected_chroma_path.iterdir()):
         print(f"ChromaDB directory already contains files. Skipping download.")
         print(f"To force re-download, delete {chromadb_dir} and restart.")