serve file added

app.py

@@ -165,7 +165,7 @@ def create_chat_interface():
 if __name__ == "__main__":
     demo = create_chat_interface()
     demo.launch(
-        share=True,
+        share=False,
         server_name="0.0.0.0",  # Makes the server accessible from other machines
         server_port=7860,  # Specify the port
         debug=True

dockerfile

@@ -1,30 +1,69 @@
-# Use Python 3.10 slim as base image
-FROM python:3.10-slim
+# # Use Python 3.10 slim as base image
+# FROM python:3.10-slim
 
-# Set the working directory
-WORKDIR /app
+# # Set the working directory
+# WORKDIR /app
 
-# Copy the current directory contents into the container at /app
-COPY . /app
+# # Copy the current directory contents into the container at /app
+# COPY . /app
 
-# Install dependencies
-RUN apt-get update && apt-get install -y \
+# # Install dependencies
+# RUN apt-get update && apt-get install -y \
+#     python3-pip \
+#     git
+
+# # Install pip packages without caching
+# RUN pip install --no-cache-dir --upgrade pip
+# RUN pip install --no-cache-dir torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/cu121
+# RUN pip install --no-cache-dir -r requirements.txt
+
+# # # Copy .env file to the working directory
+# # COPY .env /app/.env
+
+# # # Set environment variables from .env file
+# # ENV $(cat /app/.env | xargs)
+
+# # Expose port 7860
+# EXPOSE 7860
+
+
+
+# # Run the application
+# CMD ["python", "app.py"]
+
+# Use NVIDIA CUDA base image
+FROM nvidia/cuda:11.8.0-runtime-ubuntu20.04
+
+# Set environment variables
+ENV PYTHONUNBUFFERED=TRUE
+ENV PYTHONDONTWRITEBYTECODE=TRUE
+ENV PATH="/opt/conda/bin:${PATH}"
+
+# Install system dependencies
+RUN apt-get update && \
+    DEBIAN_FRONTEND=noninteractive apt-get install -y \
     python3-pip \
-    git
+    python3-dev \
+    git \
+    && rm -rf /var/lib/apt/lists/*
+
+# Set up working directory
+WORKDIR /opt/ml/code
 
-# Install pip packages without caching
-RUN pip install --no-cache-dir --upgrade pip
+# Copy requirements and install dependencies
+COPY requirements.txt .
 RUN pip install --no-cache-dir torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/cu121
 RUN pip install --no-cache-dir -r requirements.txt
 
-# # Copy .env file to the working directory
-# COPY .env /app/.env
+# Copy the application code and serve script
+COPY app.py .
+COPY serve .
 
-# # Set environment variables from .env file
-# ENV $(cat /app/.env | xargs)
+# Make the serve script executable
+RUN chmod +x serve
 
-# Expose port 7860
+# Expose the Gradio port
 EXPOSE 7860
 
-# Run the application
-CMD ["python", "app.py"]
+# Set entry point to the serve script
+ENTRYPOINT ["./serve"]

serve.sh

@@ -0,0 +1,13 @@
+#!/bin/bash
+
+# Set environment variables for SageMaker
+if [ "${SM_MODEL_DIR}" = "" ]; then
+    export SM_MODEL_DIR=/opt/ml/model
+fi
+
+if [ "${SM_CHANNEL_TRAINING}" = "" ]; then
+    export SM_CHANNEL_TRAINING=/opt/ml/input/data/training
+fi
+
+# Start the Gradio app
+exec python3 app.py