From cd91d8a987518ac1a050f24489ee9fc7c4e3c9a7 Mon Sep 17 00:00:00 2001
From: Jun Siang Cheah <git@jscheah.me>
Date: Wed, 10 Apr 2024 13:39:46 +0100
Subject: [PATCH] run apt install first for better potential layer caching

---
 Dockerfile | 64 +++++++++++++++++++++++++++---------------------------
 1 file changed, 32 insertions(+), 32 deletions(-)

diff --git a/Dockerfile b/Dockerfile
index 6b44afd3f..6cf8ded28 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -67,43 +67,43 @@ ENV RAG_EMBEDDING_MODEL="$USE_EMBEDDING_MODEL_DOCKER" \
 #### Other models ##########################################################
 
 WORKDIR /app/backend
+
+RUN if [ "$USE_OLLAMA" = "true" ]; then \
+        apt-get update && \
+        # Install pandoc and netcat
+        apt-get install -y --no-install-recommends pandoc netcat-openbsd && \
+        # for RAG OCR
+        apt-get install -y --no-install-recommends ffmpeg libsm6 libxext6 && \
+        # install helper tools
+        apt-get install -y --no-install-recommends curl && \
+        # install ollama
+        curl -fsSL https://ollama.com/install.sh | sh && \
+        # cleanup
+        rm -rf /var/lib/apt/lists/*; \
+    else \
+        apt-get update && \
+        # Install pandoc and netcat
+        apt-get install -y --no-install-recommends pandoc netcat-openbsd && \
+        # for RAG OCR
+        apt-get install -y --no-install-recommends ffmpeg libsm6 libxext6 && \
+        # cleanup
+        rm -rf /var/lib/apt/lists/*; \
+    fi
+
 # install python dependencies
 COPY ./backend/requirements.txt ./requirements.txt
 
 RUN if [ "$USE_CUDA" = "true" ]; then \
-    # If you use CUDA the whisper and embedding modell will be downloaded on first use
-    pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/$USE_CUDA_DOCKER_VER --no-cache-dir && \
-    pip3 install -r requirements.txt --no-cache-dir && \
-    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; from chromadb.utils import embedding_functions; sentence_transformer_ef = embedding_functions.SentenceTransformerEmbeddingFunction(model_name=os.environ['RAG_EMBEDDING_MODEL'], device='cpu')"; \
+        # 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/$USE_CUDA_DOCKER_VER --no-cache-dir && \
+        pip3 install -r requirements.txt --no-cache-dir && \
+        python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])" && \
+        python -c "import os; from chromadb.utils import embedding_functions; sentence_transformer_ef = embedding_functions.SentenceTransformerEmbeddingFunction(model_name=os.environ['RAG_EMBEDDING_MODEL'], device='cpu')"; \
     else \
-    pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu --no-cache-dir && \
-    pip3 install -r requirements.txt --no-cache-dir && \
-    python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])" && \
-    python -c "import os; from chromadb.utils import embedding_functions; sentence_transformer_ef = embedding_functions.SentenceTransformerEmbeddingFunction(model_name=os.environ['RAG_EMBEDDING_MODEL'], device='cpu')"; \
-    fi
-
-
-RUN if [ "$USE_OLLAMA" = "true" ]; then \
-    apt-get update && \
-    # Install pandoc and netcat
-    apt-get install -y --no-install-recommends pandoc netcat-openbsd && \
-    # for RAG OCR
-    apt-get install -y --no-install-recommends ffmpeg libsm6 libxext6 && \
-    # install helper tools
-    apt-get install -y --no-install-recommends curl && \
-    # install ollama
-    curl -fsSL https://ollama.com/install.sh | sh && \
-    # cleanup
-    rm -rf /var/lib/apt/lists/*; \
-    else \
-    apt-get update && \
-    # Install pandoc and netcat
-    apt-get install -y --no-install-recommends pandoc netcat-openbsd && \
-    # for RAG OCR
-    apt-get install -y --no-install-recommends ffmpeg libsm6 libxext6 && \
-    # cleanup
-    rm -rf /var/lib/apt/lists/*; \
+        pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu --no-cache-dir && \
+        pip3 install -r requirements.txt --no-cache-dir && \
+        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; from chromadb.utils import embedding_functions; sentence_transformer_ef = embedding_functions.SentenceTransformerEmbeddingFunction(model_name=os.environ['RAG_EMBEDDING_MODEL'], device='cpu')"; \
     fi