Update app.py

app.py

@@ -18,9 +18,9 @@ from fastapi.responses import HTMLResponse
 from pydantic import BaseModel
 from dotenv import load_dotenv
 from datetime import datetime
-from faker import Faker
 import logging
 
+# Configuración de logging
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 
@@ -90,15 +90,6 @@ async def train_and_save_model():
                 if intent['tag'] not in classes:
                     classes.append(intent['tag'])
 
-        fake = Faker()
-        for _ in range(10):
-            random_pattern = f"{fake.sentence()}"
-            random_tag = fake.word()
-            documents.append((nltk.word_tokenize(random_pattern), random_tag))
-            words.extend(nltk.word_tokenize(random_pattern))
-            if random_tag not in classes:
-                classes.append(random_tag)
-
         words = sorted(set(words))
         classes = sorted(set(classes))
 
@@ -122,7 +113,7 @@ async def train_and_save_model():
         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.")
+            logger.error(f"Error: Las dimensiones de entrada no coinciden. Esperado: {len(words)}, encontrado: {train_x.shape[1]}")
             await asyncio.sleep(60)
             continue
 
@@ -166,12 +157,12 @@ class ChatMessage(BaseModel):
 async def chat(message: ChatMessage):
     words = pickle.loads(r.get('words'))
     classes = pickle.loads(r.get('classes'))
-    with io.BytesIO(r.get('chatbot_model')) as f:
-        with tempfile.NamedTemporaryFile(delete=False, suffix='.h5') as temp_file:
-            temp_file.write(f.read())
-            temp_file_name = temp_file.name
-        model = load_model(temp_file_name)
-        os.remove(temp_file.name)
+    
+    with tempfile.NamedTemporaryFile(delete=False) as temp_file:
+        temp_file.write(r.get('chatbot_model'))
+        temp_file_name = temp_file.name
+
+    model = load_model(temp_file_name)
 
     sentence_words = nltk.word_tokenize(message.message)
     bag = [0] * len(words)
@@ -265,21 +256,20 @@ 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 => {
-            data.forEach(item => {
-                document.getElementById('chatbox').innerHTML += '<p><strong>' + item.intent + ':</strong> ' + item.probability + '</p>';
+            let chatbox = document.getElementById('chatbox');
+            chatbox.innerHTML += '<p><b>Tú:</b> ' + userInput + '</p>';
+            data.forEach(response => {
+                chatbox.innerHTML += '<p><b>Bot:</b> ' + response.intent + ' (' + response.probability + ')</p>';
             });
+            chatbox.scrollTop = chatbox.scrollHeight;
         });
     }
     </script>
@@ -288,7 +278,7 @@ html_code = """
 """
 
 @app.get("/", response_class=HTMLResponse)
-async def get_chat():
+async def read_root():
     return html_code
 
 if __name__ == "__main__":
@@ -297,6 +287,4 @@ if __name__ == "__main__":
     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)