change sdk

Dockerfile

@@ -1,34 +1,58 @@
 FROM nvidia/cuda:12.3.2-cudnn9-devel-ubuntu22.04
-
-# Set environment variables
 ENV DEBIAN_FRONTEND=noninteractive
-ENV PYTHONUNBUFFERED=1
-ENV FLASH_ATTENTION_SKIP_CUDA_BUILD=TRUE
-
-# Install system dependencies
-RUN apt-get update && apt-get install -y \
-    python3.10 \
-    python3-pip \
-    python3.10-dev \
-    build-essential \
-    ninja-build \
+RUN apt-get update && \
+    apt-get upgrade -y && \
+    apt-get install -y --no-install-recommends \
     git \
+    git-lfs \
+    wget \
+    curl \
+    # python build dependencies \
+    build-essential \
+    libssl-dev \
+    zlib1g-dev \
+    libbz2-dev \
+    libreadline-dev \
+    libsqlite3-dev \
+    libncursesw5-dev \
+    xz-utils \
+    tk-dev \
+    libxml2-dev \
+    libxmlsec1-dev \
+    libffi-dev \
+    liblzma-dev \
+    # gradio dependencies \
+    ffmpeg \
+    && apt-get clean \
     && rm -rf /var/lib/apt/lists/*
 
-# Create and set working directory
-WORKDIR /app
-
-# Copy requirements first to leverage Docker cache
-COPY requirements.txt .
-
-# Install Python dependencies
-RUN pip3 install --no-cache-dir -r requirements.txt
-
-# Install flash-attention
-RUN pip3 install --no-cache-dir flash-attn --no-build-isolation
-
-# Copy the rest of the application
-COPY . .
-
-# Set the default command
-CMD ["python3", "-m", "src.video_processor.processor"] 
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:${PATH}
+WORKDIR ${HOME}/app
+
+RUN curl https://pyenv.run | bash
+ENV PATH=${HOME}/.pyenv/shims:${HOME}/.pyenv/bin:${PATH}
+ARG PYTHON_VERSION=3.10.12
+RUN pyenv install ${PYTHON_VERSION} && \
+    pyenv global ${PYTHON_VERSION} && \
+    pyenv rehash && \
+    pip install --no-cache-dir -U pip setuptools wheel && \
+    pip install packaging ninja
+
+COPY --chown=1000 ./requirements.txt /tmp/requirements.txt
+RUN pip install --no-cache-dir --upgrade -r /tmp/requirements.txt && \
+    pip install flash-attn --no-build-isolation
+
+COPY --chown=1000 . ${HOME}/app
+ENV PYTHONPATH=${HOME}/app \
+    PYTHONUNBUFFERED=1 \
+    GRADIO_ALLOW_FLAGGING=never \
+    GRADIO_NUM_PORTS=1 \
+    GRADIO_SERVER_NAME=0.0.0.0 \
+    GRADIO_THEME=huggingface \
+    SYSTEM=spaces \
+    FLASH_ATTENTION_SKIP_CUDA_BUILD=TRUE
+
+CMD ["python", "app.py"] 

README.md

@@ -3,8 +3,7 @@ title: Smollvm
 emoji: 🌍
 colorFrom: pink
 colorTo: gray
-sdk: gradio
-sdk_version: 5.17.1
+sdk: docker
 app_file: src/app.py
 pinned: false
 short_description: test

app.py

@@ -0,0 +1,29 @@
+import gradio as gr
+from src.video_processor.processor import VideoAnalyzer
+import logging
+
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+def process_video(video_path):
+    try:
+        analyzer = VideoAnalyzer()
+        result = analyzer.process_video(video_path)
+        return result[0]["description"]
+    except Exception as e:
+        logger.error(f"Error processing video: {str(e)}", exc_info=True)
+        return f"Error processing video: {str(e)}"
+
+# Create Gradio interface
+demo = gr.Interface(
+    fn=process_video,
+    inputs=gr.Video(label="Upload your video"),
+    outputs=gr.Textbox(label="Video Analysis", lines=10),
+    title="Video Analysis with SmolVLM",
+    description="Upload a video to get a detailed analysis of its content, including actions, events, timestamps, and important details.",
+    examples=[],  # You can add example videos here
+    cache_examples=False
+)
+
+if __name__ == "__main__":
+    demo.launch() 

src/video_processor/processor.py

@@ -5,7 +5,15 @@ import logging
 
 logger = logging.getLogger(__name__)
 
-DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+def _grab_best_device(use_gpu=True):
+    if torch.cuda.device_count() > 0 and use_gpu:
+        device = "cuda"
+    else:
+        device = "cpu"
+    return device
+
+DEVICE = _grab_best_device()
+
 logger.info(f"Using device: {DEVICE}")
 
 class VideoAnalyzer: