new

Dockerfile

@@ -1,14 +1,25 @@
 FROM python:3.9
 
+# Create user
 RUN useradd -m -u 1000 user
 USER user
 ENV PATH="/home/user/.local/bin:$PATH"
+ENV NLTK_DATA="/home/user/nltk_data"
 
+# Set working directory
 WORKDIR /app
 
+# Copy requirements and install
 COPY --chown=user requirements.txt .
 RUN pip install --no-cache-dir --upgrade -r requirements.txt
 
+# Create nltk_data directory and download punkt
+RUN mkdir -p $NLTK_DATA
+COPY --chown=user download_nltk_data.py .
+RUN python download_nltk_data.py && rm download_nltk_data.py
+
+# Copy the rest of the app
 COPY --chown=user . /app
 
+# Start the app
 CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

download_nltk_data.py

@@ -0,0 +1,5 @@
+import nltk
+import os
+
+nltk_data_path = os.getenv("NLTK_DATA", "/home/user/nltk_data")
+nltk.download("punkt", download_dir=nltk_data_path)

requirements.txt

@@ -2,4 +2,5 @@ fastapi
 uvicorn[standard]
 transformers
 torch
+nltk
 pydantic