nltk error

Dockerfile

@@ -22,8 +22,14 @@ RUN mkdir -p app/models && chmod 777 app/models
 COPY app ./app
 COPY app.py .
 
-# Download NLTK data
-RUN python -c "import nltk; nltk.download('punkt')"
+# Create NLTK data directory with proper permissions
+RUN mkdir -p /usr/local/share/nltk_data && chmod 777 /usr/local/share/nltk_data
+
+# Set NLTK_DATA environment variable
+ENV NLTK_DATA=/usr/local/share/nltk_data
+
+# Download NLTK data with explicit directory
+RUN python -c "import nltk; nltk.download('punkt', download_dir='/usr/local/share/nltk_data')"
 
 # Download model files during build
 RUN python -m app.download_model

app.py

@@ -2,7 +2,9 @@
 Main application entry point for Image Captioning API
 """
 import os
+import sys
 import logging
+import nltk
 
 # Configure logging
 logging.basicConfig(
@@ -11,6 +13,45 @@ logging.basicConfig(
 )
 logger = logging.getLogger(__name__)
 
+# Setup NLTK data path
+def setup_nltk():
+    """Set up NLTK data directory and ensure punkt tokenizer is available"""
+    logger.info("Setting up NLTK...")
+    
+    # Create potential NLTK data directories with proper permissions
+    nltk_dirs = [
+        os.path.expanduser('~/.nltk_data'),
+        './nltk_data',
+        '/usr/local/share/nltk_data'
+    ]
+    
+    for directory in nltk_dirs:
+        try:
+            os.makedirs(directory, exist_ok=True)
+            logger.info(f"Created NLTK data directory: {directory}")
+        except Exception as e:
+            logger.warning(f"Could not create NLTK directory {directory}: {e}")
+    
+    # Try to find punkt tokenizer
+    try:
+        nltk.data.find('tokenizers/punkt')
+        logger.info("NLTK punkt tokenizer found!")
+        return
+    except LookupError:
+        # Not found, try to download to different locations
+        for directory in nltk_dirs:
+            try:
+                logger.info(f"Attempting to download punkt tokenizer to {directory}")
+                nltk.download('punkt', download_dir=directory)
+                logger.info(f"Successfully downloaded punkt tokenizer to {directory}")
+                return
+            except Exception as e:
+                logger.warning(f"Failed to download punkt to {directory}: {e}")
+        
+        # If we get here, we couldn't download punkt anywhere
+        logger.error("Could not download NLTK punkt tokenizer to any location")
+        logger.error("The application may not function correctly")
+
 # Check if model files exist and download if needed
 def ensure_models_exist():
     model_path = "app/models/image_captioning_model.pth"
@@ -24,6 +65,9 @@ def ensure_models_exist():
         logger.info("Model files found.")
 
 if __name__ == "__main__":
+    # Setup NLTK
+    setup_nltk()
+    
     # Ensure model files exist
     ensure_models_exist()
     

app/fix_vocab_pickle.py

@@ -17,7 +17,20 @@ logger = logging.getLogger(__name__)
 try:
     nltk.data.find('tokenizers/punkt')
 except LookupError:
-    nltk.download('punkt')
+    # Try to download to a directory where we have write permissions
+    try:
+        # Try user home directory first
+        nltk.download('punkt', download_dir=os.path.expanduser('~/.nltk_data'))
+        logger.info("Downloaded NLTK punkt to user home directory")
+    except:
+        # Then try current directory
+        try:
+            os.makedirs('./nltk_data', exist_ok=True)
+            nltk.download('punkt', download_dir='./nltk_data')
+            logger.info("Downloaded NLTK punkt to current directory")
+        except Exception as e:
+            logger.error(f"Failed to download NLTK punkt: {str(e)}")
+            # Continue anyway, as we might have the data elsewhere
 
 # Vocabulary class for loading the vocabulary
 class Vocabulary:

app/image_captioning_service.py

@@ -16,7 +16,20 @@ logger = logging.getLogger(__name__)
 try:
     nltk.data.find('tokenizers/punkt')
 except LookupError:
-    nltk.download('punkt')
+    # Try to download to a directory where we have write permissions
+    try:
+        # Try user home directory first
+        nltk.download('punkt', download_dir=os.path.expanduser('~/.nltk_data'))
+        logger.info("Downloaded NLTK punkt to user home directory")
+    except:
+        # Then try current directory
+        try:
+            os.makedirs('./nltk_data', exist_ok=True)
+            nltk.download('punkt', download_dir='./nltk_data')
+            logger.info("Downloaded NLTK punkt to current directory")
+        except Exception as e:
+            logger.error(f"Failed to download NLTK punkt: {str(e)}")
+            # Continue anyway, as we might have the data elsewhere
 
 # Vocabulary class for loading the vocabulary
 class Vocabulary: