perf: replace --no-cache-dir with BuildKit cache mounts for pip and uv

Author: Algorithm5838

Dockerfile

@@ -135,21 +135,23 @@ RUN apt-get update && \
 # install python dependencies
 COPY --chown=$UID:$GID ./backend/requirements.txt ./requirements.txt
 
-RUN set -e; \
-    pip3 install --no-cache-dir uv; \
+RUN --mount=type=cache,target=/root/.cache/pip \
+    --mount=type=cache,target=/root/.cache/uv \
+    set -e; \
+    pip3 install uv; \
     if [ "$USE_CUDA" = "true" ]; then \
     # If you use CUDA the whisper and embedding model will be downloaded on first use
     # fix: pin torch<=2.9.1 - torch 2.10.0 aarch64 wheels cause SIGILL on ARM devices (RPi 4 Cortex-A72) #21349
-    pip3 install 'torch<=2.9.1' torchvision torchaudio --index-url https://download.pytorch.org/whl/$USE_CUDA_DOCKER_VER --no-cache-dir; \
-    uv pip install --system -r requirements.txt --no-cache-dir; \
+    pip3 install 'torch<=2.9.1' torchvision torchaudio --index-url https://download.pytorch.org/whl/$USE_CUDA_DOCKER_VER; \
+    uv pip install --system -r requirements.txt; \
     python -c "import os; from sentence_transformers import SentenceTransformer; SentenceTransformer(os.environ['RAG_EMBEDDING_MODEL'], device='cpu')"; \
     python -c "import os; from sentence_transformers import SentenceTransformer; SentenceTransformer(os.environ.get('AUXILIARY_EMBEDDING_MODEL', 'TaylorAI/bge-micro-v2'), device='cpu')"; \
     python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])"; \
     python -c "import os; import tiktoken; tiktoken.get_encoding(os.environ['TIKTOKEN_ENCODING_NAME'])"; \
     python -c "import nltk; nltk.download('punkt_tab')"; \
     else \
-    pip3 install 'torch<=2.9.1' torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu --no-cache-dir; \
-    uv pip install --system -r requirements.txt --no-cache-dir; \
+    pip3 install 'torch<=2.9.1' torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu; \
+    uv pip install --system -r requirements.txt; \
     if [ "$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 sentence_transformers import SentenceTransformer; SentenceTransformer(os.environ.get('AUXILIARY_EMBEDDING_MODEL', 'TaylorAI/bge-micro-v2'), device='cpu')"; \