Update Dockerfile

Dockerfile

@@ -1,320 +1,30 @@
-FROM python:3.8
-
-# Install required system dependencies
-RUN apt-get update && apt-get install -y libopenblas-dev git curl && rm -rf /var/lib/apt/lists/*
-
-# Set the working directory inside the container
-WORKDIR /app
-
-# Copy the requirements file into the container
-COPY requirements.txt .
-
-# Install dependencies
-RUN pip install --no-cache-dir -r requirements.txt
-
-# Create necessary directories (but don't download models here!)
-RUN mkdir -p /app/modelsBioembed /app/models_folder /app/Samples /app/numba_cache /app/hf_cache
-
-# Copy the entire project to the container
-COPY . .
-
-# Expose the port for Flask
-EXPOSE 7860
-
-# Run the app with Gunicorn
-CMD ["gunicorn", "-b", "0.0.0.0:7860", "app:app"]
-
-
-# # Use Python 3.8 as the base image
-# FROM python:3.8
-
-# # Install required system dependencies
-# RUN apt-get update && apt-get install -y libopenblas-dev git wget && rm -rf /var/lib/apt/lists/*
-
-# # Set the working directory inside the container
-# WORKDIR /app
-
-# # Copy the requirements file into the container
-# COPY requirements.txt .
-
-# # Install dependencies
-# RUN pip install --no-cache-dir -r requirements.txt
-
-# # Create necessary directories inside the container
-# RUN mkdir -p /app/modelsBioembed /app/models_folder /app/Samples
-
-# # Download model files from Dropbox using wget
-# RUN wget -O /app/modelsBioembed/pytorch_model.bin "https://www.dropbox.com/scl/fi/b41t8c6ji7j6uk5y2jj8g/pytorch_model.bin?rlkey=kuuwkid36ugml560c4a465ilr&st=t60bfemx&dl=1" && \
-#     wget -O /app/modelsBioembed/config.json "https://www.dropbox.com/scl/fi/js6czj3kfc4a5kshfkzie/config.json?rlkey=5oysq4ecilnan5tviuqe86v93&st=75zpce8h&dl=1" && \
-#     wget -O /app/modelsBioembed/special_tokens_map.json "https://www.dropbox.com/scl/fi/t3lvmp5x28d1zjac3j7ec/special_tokens_map.json?rlkey=z2xbompa54iu4y9qgb5bvmfc9&st=zrxlpjdt&dl=1" && \
-#     wget -O /app/modelsBioembed/tokenizer_config.json "https://www.dropbox.com/scl/fi/x11poym6mueoxod7xb6f1/tokenizer_config.json?rlkey=s51pik2rkmqp1fu99qj9qaria&st=z9kkcxp7&dl=1" && \
-#     wget -O /app/modelsBioembed/vocab.txt "https://www.dropbox.com/scl/fi/v6e2gn10ck4lpx4iv9kpe/vocab.txt?rlkey=dcu29g5ns4wtqdv0pkks0ehx1&st=qt187rhq&dl=1"
-
-# # Copy the entire project to the container
-# COPY . .
-
-# # Expose the port for Flask
-# EXPOSE 8000
-
-# # Run the app with Gunicorn
-# CMD ["gunicorn", "-b", "0.0.0.0:8000", "app:app"]
-
-
-
-
-# # Use Python 3.8 as the base image
-# FROM python:3.8
-
-# # Install required system dependencies
-# RUN apt-get update && apt-get install -y libopenblas-dev git wget && rm -rf /var/lib/apt/lists/*
-
-# # Set the working directory inside the container
-# WORKDIR /app
-
-# # Copy the requirements file into the container
-# COPY requirements.txt .
-
-# # Install dependencies
-# RUN pip install --no-cache-dir -r requirements.txt
-
-# # Create necessary directories inside the container
-# RUN mkdir -p /app/modelsBioembed /app/models_folder /app/Samples
-
-# # Download model files from Dropbox using wget
-# RUN wget -O /app/modelsBioembed/pytorch_model.bin "https://www.dropbox.com/s/example/pytorch_model.bin?dl=1" && \
-#     wget -O /app/modelsBioembed/config.json "https://www.dropbox.com/s/example/config.json?dl=1" && \
-#     wget -O /app/modelsBioembed/tokenizer_config.json "https://www.dropbox.com/s/example/tokenizer_config.json?dl=1" && \
-#     wget -O /app/modelsBioembed/vocab.txt "https://www.dropbox.com/s/example/vocab.txt?dl=1" && \
-#     wget -O /app/modelsBioembed/special_tokens_map.json "https://www.dropbox.com/s/example/special_tokens_map.json?dl=1"
-
-# # Copy the entire project to the container
-# COPY . .
-
-# # Expose the port for Flask
-# EXPOSE 8000
-
-# # Run the app with Gunicorn
-# CMD ["gunicorn", "-b", "0.0.0.0:8000", "app:app"]
-
-
-
-
-
-
-
-
-
-
-
-
-
-# # Use Python 3.8 as the base image
-# FROM python:3.8
-
-# # Install required system dependencies
-# RUN apt-get update && apt-get install -y libopenblas-dev git curl && rm -rf /var/lib/apt/lists/*
-
-# # Set the working directory inside the container
-# WORKDIR /app
-
-# # Copy the requirements file into the container
-# COPY requirements.txt .
-
-# # Install dependencies
-# RUN pip install --no-cache-dir -r requirements.txt
-
-# # Install gdown for Google Drive downloads
-# RUN pip install --no-cache-dir gdown
-
-# # Create necessary directories inside the container
-# RUN mkdir -p /app/modelsBioembed /app/models_folder /app/Samples
-
-# # Download model files from Google Drive using gdown
-# RUN gdown --id 1aDirthtWAu-oyVjcWZ6linrddN-dmLMI -O /app/modelsBioembed/pytorch_model.bin && \
-#     gdown --id 1bwk1fSwqQE5mN9AhsOBlQkvFjHCGQtJ3 -O /app/modelsBioembed/config.json && \
-#     gdown --id 1ne-xJcySd8PcGTA4SdpTA6F869xsPiTf -O /app/modelsBioembed/tokenizer_config.json && \
-#     gdown --id 1tWjWsoeyPvTdW5sYZMSWpvISlN7tDoZ -O /app/modelsBioembed/vocab.txt && \
-#     gdown --id 1M8Qg9fSQ2A7CZpVFMCrZMIwam2j6Cc6P -O /app/modelsBioembed/special_tokens_map.json
-
-# # Copy the entire project to the container
-# COPY . .
-
-# # Expose the port for Flask
-# EXPOSE 8000
-
-# # Run the app with Gunicorn
-# CMD ["gunicorn", "-b", "0.0.0.0:8000", "app:app"]
-# #Use Python 3.8 as the base image
-# FROM python:3.8
-
-# # Install required system dependencies
-# RUN apt-get update && apt-get install -y libopenblas-dev git curl && rm -rf /var/lib/apt/lists/*
-
-# # Set the working directory inside the container
-# WORKDIR /app
-
-# # Copy the requirements file into the container
-# COPY requirements.txt .
-
-# # Install dependencies
-# RUN pip install --no-cache-dir -r requirements.txt
-
-# # Install gdown for Google Drive downloads
-# RUN pip install --no-cache-dir gdown
-
-# # Create necessary directories inside the container
-# RUN mkdir -p /app/modelsBioembed /app/models_folder /app/Samples
-
-# # Download model files from Google Drive using alternative methods
-# RUN curl -L -o /app/modelsBioembed/pytorch_model.bin "https://drive.google.com/uc?export=download&id=11g7bAXYNxlPsnwC8_qsUIZITAjG85JXb" && \
-#     curl -L -o /app/modelsBioembed/config.json "https://drive.google.com/uc?export=download&id=1ZfuhTnEuKAI1Z92m1QnDTOEQYNe9y24E" && \
-#     curl -L -o /app/modelsBioembed/tokenizer_config.json "https://drive.google.com/uc?export=download&id=1r4ncUsWBNQZVKp4zw97DLTf0AgRUiuFc" && \
-#     curl -L -o /app/modelsBioembed/vocab.txt "https://drive.google.com/uc?export=download&id=1G1UQIGMHvCC3OokCG1tl-cTxjIVqw04w" && \
-#     curl -L -o /app/modelsBioembed/special_tokens_map.json "https://drive.google.com/uc?export=download&id=1pINnV2P1eBmaC7X0A52UhjrmlJgzxqbl"
-
-# # Copy the entire project to the container
-# COPY . .
-
-# # Expose the port for Flask
-# EXPOSE 8000
-
-# # Run the app with Gunicorn
-# CMD ["gunicorn", "-b", "0.0.0.0:8000", "app:app"]
-
-
-
-
-# # Use Python 3.8 as the base image
-# FROM python:3.8
-
-# # Install required system dependencies
-# RUN apt-get update && apt-get install -y libopenblas-dev git curl wget && rm -rf /var/lib/apt/lists/*
-
-# # Set the working directory inside the container
-# WORKDIR /app
-
-# # Copy the requirements file into the container
-# COPY requirements.txt .
-
-# # Install dependencies
-# RUN pip install --no-cache-dir -r requirements.txt
-
-# # Create necessary directories inside the container
-# RUN mkdir -p /app/modelsBioembed /app/models_folder /app/Samples
-
-# # Function to download file from Google Drive using wget
-# RUN wget --no-check-certificate 'https://drive.google.com/uc?export=download&id=11g7bAXYNxlPsnwC8_qsUIZITAjG85JXb' -O /app/modelsBioembed/pytorch_model.bin && \
-#     wget --no-check-certificate 'https://drive.google.com/uc?export=download&id=1ZfuhTnEuKAI1Z92m1QnDTOEQYNe9y24E' -O /app/modelsBioembed/config.json && \
-#     wget --no-check-certificate 'https://drive.google.com/uc?export=download&id=1r4ncUsWBNQZVKp4zw97DLTf0AgRUiuFc' -O /app/modelsBioembed/tokenizer_config.json && \
-#     wget --no-check-certificate 'https://drive.google.com/uc?export=download&id=1G1UQIGMHvCC3OokCG1tl-cTxjIVqw04w' -O /app/modelsBioembed/vocab.txt && \
-#     wget --no-check-certificate 'https://drive.google.com/uc?export=download&id=1pINnV2P1eBmaC7X0A52UhjrmlJgzxqbl' -O /app/modelsBioembed/special_tokens_map.json
-
-# # Copy the entire project to the container
-# COPY . .
-
-# # Expose the port for Flask
-# EXPOSE 8000
-
-# # Run the app with Gunicorn
-# CMD ["gunicorn", "-b", "0.0.0.0:8000", "app:app"]
-
-
-# # Use Python 3.8 as the base image
-# FROM python:3.8
-
-# # Install required system dependencies
-# RUN apt-get update && apt-get install -y libopenblas-dev git curl && rm -rf /var/lib/apt/lists/*
-
-# # Set the working directory inside the container
-# WORKDIR /app
-
-# # Copy the requirements file into the container
-# COPY requirements.txt .
-
-# # Install dependencies
-# RUN pip install --no-cache-dir -r requirements.txt
-
-# # Install gdown for Google Drive downloads
-# RUN pip install --no-cache-dir gdown
-
-# # Create necessary directories inside the container
-# RUN mkdir -p /app/modelsBioembed /app/models_folder /app/Samples
-
-# # Download model files using gdown with file IDs
-# RUN gdown --id 1aDirthtWAu-oyVjcWZ6linrddN-dmLMI -O /app/modelsBioembed/pytorch_model.bin && \
-#     gdown --id 1bwk1fSwqQE5mN9AhsOBlQkvFjHCGQtJ3 -O /app/modelsBioembed/config.json && \
-#     gdown --id 1ne-xJcySd8PcGTA4SdpTA6F869xsPiTf -O /app/modelsBioembed/tokenizer_config.json && \
-#     gdown --id 1tWjWsoeyPvTdW5sYZMSWpvISlN7tDoZ -O /app/modelsBioembed/vocab.txt && \
-#     gdown --id 1M8Qg9fSQ2A7CZpVFMCrZMIwam2j6Cc6P -O /app/modelsBioembed/special_tokens_map.json
-
-# # Copy the entire project to the container
-# COPY . .
-
-# # Expose the port for Flask
-# EXPOSE 8000
-
-# # Run the app with Gunicorn
-# CMD ["gunicorn", "-b", "0.0.0.0:8000", "app:app"]
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-# # Use Python 3.8 as the base image
-# FROM python:3.8
-
-# # Install required system dependencies
-# RUN apt-get update && apt-get install -y libopenblas-dev git curl && rm -rf /var/lib/apt/lists/*
-
-# # Set the working directory inside the container
-# WORKDIR /app
-
-# # Copy the requirements file into the container
-# COPY requirements.txt .
-
-# # Install dependencies
-# RUN pip install --no-cache-dir -r requirements.txt
-
-# # Create necessary directories inside the container
-# RUN mkdir -p /app/modelsBioembed /app/models_folder /app/Samples
-
-# # Set the OAuth 2.0 Access Token (Replace with your actual token)
-# ENV ACCESS_TOKEN="ya29.a0AeXRPp6PRilVeuzghPDbZQE7DxYHHWv4TARoaumWuo4gX9bIcEtMzp3PGi1Ak36YIbvKk32V7Cwb6bEjGfJuOWp0ZDW5rdog1c5uf9PJH7b-zgPxIeGa0kmZhGlk79gc7WfoSAl-GUopljJfOmKsyVn628CGB10RRHBtMQiHaCgYKARQSARESFQHGX2MiRd-59J4_XHWekXXqwK-jsw0175"
-
-# # Define Google Drive File IDs
-# ENV FILE_ID1="1aDirthtWAu-oyVjcWZ6linrddN-dmLMI"
-# ENV FILE_ID2="1bwk1fSwqQE5mN9AhsOBlQkvFjHCGQtJ3"
-# ENV FILE_ID3="1ne-xJcySd8PcGTA4SdpTA6F869xsPiTf"
-# ENV FILE_ID4="1tWjWsoeyPvTdW5sYZMSWpvISlN7tDoZ"
-# ENV FILE_ID5="1M8Qg9fSQ2A7CZpVFMCrZMIwam2j6Cc6P"
-
-# # Download model files using curl with OAuth token
-# RUN curl -H "Authorization: Bearer $ACCESS_TOKEN" "https://www.googleapis.com/drive/v3/files/$FILE_ID1?alt=media" -o /app/modelsBioembed/pytorch_model.bin && \
-#     curl -H "Authorization: Bearer $ACCESS_TOKEN" "https://www.googleapis.com/drive/v3/files/$FILE_ID2?alt=media" -o /app/modelsBioembed/config.json && \
-#     curl -H "Authorization: Bearer $ACCESS_TOKEN" "https://www.googleapis.com/drive/v3/files/$FILE_ID3?alt=media" -o /app/modelsBioembed/tokenizer_config.json && \
-#     curl -H "Authorization: Bearer $ACCESS_TOKEN" "https://www.googleapis.com/drive/v3/files/$FILE_ID4?alt=media" -o /app/modelsBioembed/vocab.txt && \
-#     curl -H "Authorization: Bearer $ACCESS_TOKEN" "https://www.googleapis.com/drive/v3/files/$FILE_ID5?alt=media" -o /app/modelsBioembed/special_tokens_map.json
-
-# # Copy the entire project to the container
-# COPY . .
-
-# # Expose the port for Flask
-# EXPOSE 8000
-
-# # Run the app with Gunicorn
-# CMD ["gunicorn", "-b", "0.0.0.0:8000", "app:app"]
-
+FROM python:3.8
+
+# Install required system dependencies
+RUN apt-get update && apt-get install -y libopenblas-dev git curl && rm -rf /var/lib/apt/lists/*
+
+# Set environment variables to avoid cache write errors
+ENV TRANSFORMERS_CACHE=/app/hf_cache
+ENV NUMBA_CACHE_DIR=/app/numba_cache
+ENV NUMBA_DISABLE_CACHING=1
+
+# Set the working directory inside the container
+WORKDIR /app
+
+# Copy the requirements file into the container
+COPY requirements.txt .
+
+# Install dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Create necessary directories
+RUN mkdir -p /app/modelsBioembed /app/models_folder /app/Samples /app/numba_cache /app/hf_cache
+
+# Copy the entire project to the container
+COPY . .
+
+# Expose the port for Gunicorn
+EXPOSE 7860
+
+# Run the app with Gunicorn
+CMD ["gunicorn", "-b", "0.0.0.0:7860", "app:app"]