fix DockerFile

Dockerfile

@@ -133,27 +133,35 @@ RUN if [ "$USE_OLLAMA" = "true" ]; then \
 # install python dependencies
 COPY --chown=$UID:$GID ./backend/requirements.txt ./requirements.txt
 
-RUN pip3 install --no-cache-dir uv && \
-RUN pip3 install huggingface_hub
-RUN pip3 install uv && \
-    if [ "$USE_CUDA" = "true" ]; then \
+RUN pip3 install --no-cache-dir uv huggingface_hub
+
+RUN if [ "$USE_CUDA" = "true" ]; then \
     # If you use CUDA the whisper and embedding model will be downloaded on first use
+    echo "Installing PyTorch with CUDA support ($USE_CUDA_DOCKER_VER)..." && \
     pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/$USE_CUDA_DOCKER_VER --no-cache-dir && \
+    echo "Installing requirements using uv..." && \
     uv pip install --system -r requirements.txt --no-cache-dir && \
+    echo "Pre-downloading embedding model..." && \
     python -c "import os; from sentence_transformers import SentenceTransformer; SentenceTransformer(os.environ['RAG_EMBEDDING_MODEL'], device='cpu')" && \
-    python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])"; \
+    echo "Pre-downloading whisper model..." && \
+    python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])" && \
+    echo "Pre-downloading tiktoken encoding..." && \
     python -c "import os; import tiktoken; tiktoken.get_encoding(os.environ['TIKTOKEN_ENCODING_NAME'])"; \
     else \
+    echo "Installing PyTorch with CPU support..." && \
     pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu --no-cache-dir && \
+    echo "Installing requirements using uv..." && \
     uv pip install --system -r requirements.txt --no-cache-dir && \
+    echo "Pre-downloading embedding model..." && \
     python -c "import os; from sentence_transformers import SentenceTransformer; SentenceTransformer(os.environ['RAG_EMBEDDING_MODEL'], device='cpu')" && \
-    python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])"; \
+    echo "Pre-downloading whisper model..." && \
+    python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])" && \
+    echo "Pre-downloading tiktoken encoding..." && \
     python -c "import os; import tiktoken; tiktoken.get_encoding(os.environ['TIKTOKEN_ENCODING_NAME'])"; \
-    fi; \
+    fi && \
+    echo "Setting final ownership..." && \
     chown -R $UID:$GID /app/backend/data/
 
-
-
 # copy embedding weight from build
 # RUN mkdir -p /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2
 # COPY --from=build /app/onnx /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2/onnx