refac: dockerfile

Dockerfile

@@ -123,7 +123,6 @@ RUN apt-get update && \
 COPY --chown=$UID:$GID ./backend/requirements.txt ./requirements.txt
 
 RUN pip3 install --no-cache-dir uv && \
-    if [ "$USE_SLIM" != "true" ]; then \
     if [ "$USE_CUDA" = "true" ]; then \
     # If you use CUDA the whisper and embedding model will be downloaded on first use
     pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/$USE_CUDA_DOCKER_VER --no-cache-dir && \
@@ -134,17 +133,17 @@ RUN pip3 install --no-cache-dir uv && \
     else \
     pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu --no-cache-dir && \
     uv pip install --system -r requirements.txt --no-cache-dir && \
+    if [ "$USE_SLIM" != "true" ]; then \
     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'])"; \
     python -c "import os; import tiktoken; tiktoken.get_encoding(os.environ['TIKTOKEN_ENCODING_NAME'])"; \
     fi; \
-    else \
-    uv pip install --system -r requirements.txt --no-cache-dir; \
     fi; \
-    mkdir -p /app/backend/data && chown -R $UID:$GID /app/backend/data/
+    mkdir -p /app/backend/data && chown -R $UID:$GID /app/backend/data/ && \
+    rm -rf /var/lib/apt/lists/*;
 
 # Install Ollama if requested
-RUN if [ "$USE_OLLAMA" = "true" ] && [ "$USE_SLIM" != "true" ]; then \
+RUN if [ "$USE_OLLAMA" = "true" ]; then \
     date +%s > /tmp/ollama_build_hash && \
     echo "Cache broken at timestamp: `cat /tmp/ollama_build_hash`" && \
     curl -fsSL https://ollama.com/install.sh | sh && \