Update app.py

app.py

@@ -1,6 +1,7 @@
 import nltk
 nltk.download('punkt')
 nltk.download('wordnet')
+nltk.download('omw-1.4') # This is important for WordNetLemmatizer
 from nltk.stem import WordNetLemmatizer
 
 import json
@@ -11,6 +12,7 @@ from tensorflow.keras import Sequential
 from tensorflow.keras.layers import Dense, Dropout
 from tensorflow.keras.optimizers import SGD
 
+import redis
 import os
 from dotenv import load_dotenv
 import uvicorn
@@ -22,7 +24,7 @@ app = FastAPI()
 
 @app.on_event("startup")
 async def startup_event():
-    global lemmatizer, words, classes, documents, ignore_words, intents, model, training, train_x, train_y, sgd, hist
+    global lemmatizer, words, classes, documents, ignore_words, intents, model, r, training, train_x, train_y, sgd, hist
     
     lemmatizer = WordNetLemmatizer()
     words = []
@@ -32,6 +34,9 @@ async def startup_event():
 
     with open('intents.json') as file:
         intents = json.load(file)
+    
+    redis_password = os.getenv("REDIS_PASSWORD")
+    r = redis.Redis(host=os.getenv("REDIS_HOST"), port=int(os.getenv("REDIS_PORT")), db=int(os.getenv("REDIS_DB")), password=redis_password)
 
     while True:
         for intent in intents['intents']:
@@ -74,16 +79,15 @@ async def startup_event():
 
         hist = model.fit(np.array(train_x), np.array(train_y), epochs=300, batch_size=5, verbose=1)
 
-        # Save data and model locally
-        with open('words.pkl', 'wb') as f:
-            pickle.dump(words, f)
-        with open('classes.pkl', 'wb') as f:
-            pickle.dump(classes, f)
-        with open('training.pkl', 'wb') as f:  # Save training data
-            pickle.dump(training, f)
-        model.save('chatbot_model.h5') 
+        r.set('words', pickle.dumps(words))
+        r.set('classes', pickle.dumps(classes))
+        r.set('train_x', pickle.dumps(train_x))
+        r.set('train_y', pickle.dumps(train_y))
+        r.set('model', pickle.dumps(model))
+
+        print("Data and model saved to Redis. Re-training...")
+
 
-        print("Data and model saved locally. Re-training...")
 
 if __name__ == "__main__":
     uvicorn.run(app, host="0.0.0.0", port=7860)