debug

Dockerfile

@@ -1,80 +1,41 @@
-# Stage 1: Build dependencies
-FROM debian:latest as builder
+# Start with NVIDIA CUDA 12.6 base image
+FROM nvidia/cuda:12.6.0-base-ubuntu22.04 AS base
 
+# Install necessary dependencies and musl
 RUN apt-get update && apt-get install -y \
-    musl \
-    python3 \
-    python3.11 \
-    python3-pip \
-    cmake \
+    software-properties-common \
     wget \
+    musl \
+    musl-dev \
+    musl-tools \
     && rm -rf /var/lib/apt/lists/*
 
-WORKDIR /app
-
-COPY ./requirements.txt /app/requirements.txt
-RUN pip3 install --break-system-packages --no-cache-dir --upgrade -r /app/requirements.txt
-RUN pip3 install --break-system-packages https://files.pythonhosted.org/packages/13/87/e0cb08c2d4bd7d38ab63816b306c8b1e7cfdc0e59bd54462e8b0df069078/semantic_text_splitter-0.6.3-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
-RUN pip3 install --break-system-packages llama_cpp_python
-RUN FORCE_CMAKE=1 CMAKE_SYSTEM_PROCESSOR=AMD64 pip3 install --break-system-packages --verbose --no-cache-dir llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
-
-# Install text2vec-transformers
-WORKDIR /app/text2vec-transformers
-COPY --from=semitechnologies/transformers-inference:sentence-transformers-multi-qa-MiniLM-L6-cos-v1 /app /app/text2vec-transformers
-COPY --from=semitechnologies/transformers-inference:sentence-transformers-multi-qa-MiniLM-L6-cos-v1 /usr/local/bin /app/text2vec-transformers/bin
-COPY ./multi-qa-MiniLM-L6-cos-v1 /app/text2vec-transformers
-RUN ./custom_prerequisites.py
-
-# Stage 2: Final image
-FROM nvidia/cuda:12.6.0-cudnn-runtime-ubuntu24.04 as final
-
-RUN apt-get update && apt-get install -y \
-    wget \
-    curl \
-    unzip \
+# Install Python 3.11
+RUN add-apt-repository ppa:deadsnakes/ppa && \
+    apt-get update && \
+    apt-get install -y \
+    python3.11 \
+    python3.11-venv \
+    python3.11-dev \
+    python3-pip \
     && rm -rf /var/lib/apt/lists/*
 
-# Copy Python environment from builder stage
-COPY --from=builder /usr/local /usr/local
-COPY --from=builder /app /app
-
-# Set up environment variables
-ENV LD_LIBRARY_PATH="/usr/lib/x86_64-linux-gnu:/usr/local/cuda/lib64:$LD_LIBRARY_PATH"
-ENV PATH="/app:/app/text2vec-transformers:/app/text2vec-transformers/bin:/usr/local/bin:$PATH"
-
-WORKDIR /app
-
-# Copy application files
-COPY ./semsearch.py /app/semsearch.py
-COPY ./startup.sh /app/startup.sh
-COPY ./.streamlit/main.css /app/.streamlit/main.css
-COPY ./app.py /app/app.py
-RUN chmod 755 /app/startup.sh
-
-# Copy input documents
-RUN mkdir -p /app/inputDocs
-COPY ./inputDocs/* /app/inputDocs/
+# Set Python 3.11 as the default python version
+RUN update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.11 1
+RUN update-alternatives --set python3 /usr/bin/python3.11
 
-# Install Weaviate
-WORKDIR /app/weaviate
-RUN wget -qO- https://github.com/weaviate/weaviate/releases/download/v1.24.10/weaviate-v1.24.10-linux-amd64.tar.gz | tar -xzf -
+# Verify Python and musl installations
+RUN python3 --version && \
+    ldd --version | grep musl
 
-# Download Llama model
+# Set up a working directory
 WORKDIR /app
-RUN wget -v https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/resolve/main/llama-2-7b-chat.Q4_0.gguf
-
-# Create a non-root user
-RUN groupadd -g 2222 user && useradd -m -u 2222 -g user user
-
-# Set permissions
-RUN chown -R user:user /app
-RUN chmod -R 755 /app
-
-# Switch to non-root user
-USER user
 
-EXPOSE 8080 8501
+# Copy your application files
+COPY . /app
 
+# Install any needed packages specified in requirements.txt
+RUN pip3 install --no-cache-dir -r requirements.txt
 
-#CMD ["streamlit", "run", "/app/app.py", "--server.headless", "true", "--server.enableCORS", "false", "--server.enableXsrfProtection", "false", "--server.fileWatcherType", "none"]
-CMD ["/app/delay.sh", "1200"]
+# Command to run the application
+CMD ["python3xxx", "app.py"]