Update app.py

app.py

@@ -1,14 +1,13 @@
 import os
 import json
 import pickle
+import random
 import tempfile
 import asyncio
-import io
 import numpy as np
 import redis
 import uvicorn
 import nltk
-from datetime import datetime
 from nltk.stem import WordNetLemmatizer
 from tensorflow.keras import Sequential
 from tensorflow.keras.layers import Dense, Dropout, Input
@@ -18,6 +17,7 @@ from fastapi import FastAPI
 from fastapi.responses import HTMLResponse
 from pydantic import BaseModel
 from dotenv import load_dotenv
+from datetime import datetime
 from faker import Faker
 import logging
 
@@ -32,12 +32,6 @@ lemmatizer = WordNetLemmatizer()
 redis_password = os.getenv("REDIS_PASSWORD")
 r = redis.Redis(host=os.getenv("REDIS_HOST"), port=int(os.getenv("REDIS_PORT")), password=redis_password)
 
-nltk.download('punkt')
-nltk.download('wordnet')
-nltk.download('omw-1.4')
-nltk.download('averaged_perceptron_tagger')
-nltk.download('punkt_tab')
-
 def create_intents_json():
     intents = {
         "intents": [
@@ -111,10 +105,10 @@ async def train_and_save_model():
         training = []
         output_empty = [0] * len(classes)
         for doc in documents:
-            bag = []
+            bag = [0] * len(words)
             pattern_words = [lemmatizer.lemmatize(word.lower()) for word in doc[0]]
             for w in words:
-                bag.append(1 if w in pattern_words else 0)
+                bag[words.index(w)] = 1 if w in pattern_words else 0
 
             output_row = list(output_empty)
             output_row[classes.index(doc[1])] = 1
@@ -127,6 +121,11 @@ async def train_and_save_model():
         train_x = np.array([row[0] for row in training])
         train_y = np.array([row[1] for row in training])
 
+        if train_x.shape[1] != len(words):
+            logger.error("Error: Las dimensiones de entrada no coinciden.")
+            await asyncio.sleep(60)
+            continue
+
         if r.exists('chatbot_model'):
             with tempfile.NamedTemporaryFile(delete=False, suffix='.h5') as temp_file:
                 temp_file.write(r.get('chatbot_model'))
@@ -134,7 +133,7 @@ async def train_and_save_model():
             model = load_model(temp_file_name)
             os.remove(temp_file.name)
         else:
-            input_layer = Input(shape=(len(train_x[0]),))
+            input_layer = Input(shape=(len(words),))
             layer1 = Dense(128, activation='relu')(input_layer)
             layer2 = Dropout(0.5)(layer1)
             layer3 = Dense(64, activation='relu')(layer2)
@@ -156,17 +155,6 @@ async def train_and_save_model():
                 r.set('chatbot_model', f.read())
             os.remove(temp_file.name)
 
-def generate_synonyms(pattern):
-    synonyms = []
-    words = nltk.word_tokenize(pattern)
-    for word in words:
-        synsets = nltk.corpus.wordnet.synsets(word)
-        if synsets:
-            for syn in synsets:
-                for lemma in syn.lemmas():
-                    synonyms.append(lemma.name())
-    return list(set(synonyms))
-
 async def handle_new_message(message: str):
     r.rpush('user_questions', message)
     await train_and_save_model()
@@ -277,32 +265,38 @@ html_code = """
     <script>
     function sendMessage() {
         let userInput = document.getElementById('user_input').value;
+        document.getElementById('chatbox').innerHTML += '<p><strong>Tú:</strong> ' + userInput + '</p>';
         document.getElementById('user_input').value = '';
+
         fetch('/chat', {
             method: 'POST',
-            headers: {'Content-Type': 'application/json'},
-            body: JSON.stringify({"message": userInput})
+            headers: {
+                'Content-Type': 'application/json'
+            },
+            body: JSON.stringify({ message: userInput })
         })
         .then(response => response.json())
         .then(data => {
-            let chatbox = document.getElementById('chatbox');
-            chatbox.innerHTML += '<p><b>Tú:</b> ' + userInput + '</p>';
             data.forEach(item => {
-              chatbox.innerHTML += '<p><b>Bot:</b> ' + item.intent + ' (Probabilidad: ' + item.probability + ')</p>';
+                document.getElementById('chatbox').innerHTML += '<p><strong>' + item.intent + ':</strong> ' + item.probability + '</p>';
             });
         });
-      }
+    }
     </script>
 </body>
 </html>
 """
 
 @app.get("/", response_class=HTMLResponse)
-async def root():
+async def get_chat():
     return html_code
 
 if __name__ == "__main__":
-    logger.info(f"Application Startup at {datetime.now()}")
-    create_intents_json()
-    asyncio.run(train_and_save_model())
-    uvicorn.run(app, host="0.0.0.0", port=7860)
+    nltk.download('punkt')
+    nltk.download('wordnet')
+    nltk.download('omw-1.4')
+    nltk.download('averaged_perceptron_tagger')
+    nltk.download('punkt_tab')
+    loop = asyncio.get_event_loop()
+    loop.run_until_complete(train_and_save_model())
+    uvicorn.run(app, host="0.0.0.0", port=8000)