Create Dockerfile_20250617

Dockerfile_20250617

@@ -0,0 +1,154 @@
+Hugging Face's logo
+Hugging Face
+Models
+Datasets
+Spaces
+Community
+Docs
+Enterprise
+Pricing
+
+
+
+Spaces:
+
+MVPilgrim
+/
+SemanticSearchPOC
+
+private
+
+Logs
+App
+Files
+Community
+Settings
+SemanticSearchPOC
+/
+Dockerfile
+
+MVPilgrim
+debug
+7cb1a56
+10 months ago
+raw
+
+Copy download link
+history
+blame
+edit
+delete
+
+4.34 kB
+# Start with NVIDIA CUDA 12.6 base image
+FROM nvidia/cuda:12.2.0-base-ubuntu22.04 AS base
+
+ENV DEBIAN_FRONTEND=noninteractive
+ENV DEBCONF_NOWARNINGS="yes"
+ENV CUDA_VISIBLE_DEVICES=0
+ENV LLAMA_CUBLAS=1
+
+# Install necessary dependencies and musl
+RUN apt-get update && apt-get install -y \
+    software-properties-common \
+    wget \
+    musl \
+    musl-dev \
+    musl-tools \
+	libffi-dev \
+	git \
+	build-essential \
+    pkg-config \
+    cuda-toolkit-12-2 \
+    cuda-nvcc-12-2 \
+    libcublas-12-2 \
+    libcudnn8 \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+
+# 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 \
+	tzdata \
+    && rm -rf /var/lib/apt/lists/*
+
+# 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
+
+# Create softlink so that text2vec-transformer can invoke python3 when using /usr/local/bin/python.
+RUN ln -s /usr/bin/python3.11 /usr/local/bin/python
+
+# Set up environment variables
+ENV LD_LIBRARY_PATH="/usr/lib/x86_64-linux-gnu:/usr/lib64:/usr/local/cuda/lib64:$LD_LIBRARY_PATH"
+ENV PATH="/usr/local/cuda/bin:/app:/app/text2vec-transformers:/app/text2vec-transformers/bin:/usr/local/bin:/usr/bin:$PATH"
+
+# Upgrade pip to support --break-system-packages.
+RUN python3 -m pip install --upgrade pip
+
+# Install requirements packages, semantic text splitter, llama_cpp.
+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
+#RUN FORCE_CMAKE=1 CMAKE_SYSTEM_PROCESSOR=AMD64 pip3 install --break-system-packages --verbose --no-cache-dir llama-cpp-python 
+
+#RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on -DCUDA_PATH=/usr/local/cuda-12.2 -DCUDAToolkit_ROOT=/usr/local/cuda-12.2 -DCUDAToolkit_INCLUDE_DIR=/usr/local/cuda-12/include -DCUDAToolkit_LIBRARY_DIR=/usr/local/cuda-12.2/lib64" FORCE_CMAKE=1 pip install llama-cpp-python - no-cache-dir
+RUN CMAKE_ARGS="GGML_CUDA=on" FORCE_CMAKE=1 pip install --break-system-packages llama-cpp-python --no-cache-dir
+
+RUN pip3 install --break-system-packages cffi
+
+# 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
+RUN ./custom_prerequisites.py
+
+COPY ./multi-qa-MiniLM-L6-cos-v1 /app/multi-qa-MiniLM-L6-cos-v1
+
+# Copy application files
+WORKDIR /app
+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/
+
+# 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 -
+
+# Download Llama model
+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 1000 user && useradd -m -u 1000 -g user user
+
+# Set permissions
+RUN chown -R user:user /app
+RUN chmod -R 755 /app
+
+# Switch to non-root user
+USER user
+
+# Verify Python and musl installations
+#RUN python3 --version && \
+#    ldd --version | grep musl
+
+EXPOSE 8080 8501
+
+CMD ["streamlit", "run", "/app/app.py", "--server.headless", "true", "--server.enableCORS", "false", "--server.enableXsrfProtection", "false", "--server.fileWatcherType", "none"]
+#CMD ["/app/delay.sh", "1200"]
+