Create app.py

app.py

@@ -0,0 +1,143 @@
+import json
+import random
+import nltk
+import numpy
+from nltk.stem import LancasterStemmer
+from tensorflow.python.keras.layers import Dense
+from tensorflow.python.keras.models import Sequential
+from flask import Flask, request, jsonify
+
+app = Flask(__name__)
+
+nltk.download('all')
+stemmer = LancasterStemmer()
+
+intents = []
+
+def generar_pregunta():
+    temas = ["hola", "buenos días", "buenas tardes", "adiós", "hasta luego"]
+    plantillas = [
+        '¿Qué es {}?',
+        '¿Cuál es el significado de {}?',
+        '¿Puedes describir {}?',
+        '¿Qué relación hay entre {} y {}?',
+        '¿Cuál es la diferencia entre {} y {}?',
+    ]
+    
+    tema = random.choice(temas)
+    plantilla = random.choice(plantillas)
+    
+    if '{}' in plantilla:
+        palabra1 = random.choice(temas)
+        palabra2 = random.choice(temas)
+        pregunta = plantilla.format(tema, palabra1, palabra2)
+    else:
+        pregunta = plantilla.format(tema)
+    
+    return pregunta
+
+def entrenar_modelo():
+    global intents
+    words = []
+    labels = []
+    docs_x = []
+    docs_y = []
+    
+    for intent in intents:
+        for pattern in intent["patterns"]:
+            wrds = nltk.word_tokenize(pattern)
+            words.extend(wrds)
+            docs_x.append(wrds)
+            docs_y.append(intent["tag"])
+        if intent["tag"] not in labels:
+            labels.append(intent["tag"])
+    
+    words = [stemmer.stem(w.lower()) for w in words if w != "?"]
+    words = sorted(list(set(words)))
+    labels = sorted(labels)
+    
+    training = []
+    output = []
+    output_empty = [0 for _ in range(len(labels))]
+    
+    for x, doc in enumerate(docs_x):
+        bag = []
+        wrds = [stemmer.stem(w.lower()) for w in doc]
+        for w in words:
+            if w in wrds:
+                bag.append(1)
+            else:
+                bag.append(0)
+        output_row = output_empty[:]
+        output_row[labels.index(docs_y[x])] = 1
+        training.append(bag)
+        output.append(output_row)
+    
+    training = numpy.array(training)
+    output = numpy.array(output)
+    
+    modelo = Sequential()
+    modelo.add(Dense(8, input_shape=[len(words)], activation='relu'))
+    modelo.add(Dense(len(labels), activation='softmax'))
+    modelo.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
+    modelo.fit(training, output, epochs=1000, batch_size=8)
+    
+    return modelo
+
+def responder_pregunta(modelo, pregunta):
+    global intents
+    words = []
+    labels = []
+    
+    for intent in intents:
+        for pattern in intent["patterns"]:
+            wrds = nltk.word_tokenize(pattern)
+            words.extend(wrds)
+        if intent["tag"] not in labels:
+            labels.append(intent["tag"])
+    
+    words = [stemmer.stem(w.lower()) for w in words if w != "?"]
+    words = sorted(list(set(words)))
+    labels = sorted(labels)
+    
+    bag = [0 for _ in range(len(words))]
+    s_words = nltk.word_tokenize(pregunta)
+    s_words = [stemmer.stem(word.lower()) for word in s_words]
+    
+    for se in s_words:
+        for i, w in enumerate(words):
+            if w == se:
+                bag[i] = 1
+    
+    result = modelo.predict(numpy.array([bag]))
+    result_index = numpy.argmax(result)
+    tag = labels[result_index]
+    
+    if result[0][result_index] > 0.7:
+        for tg in intents:
+            if tg['tag'] == tag:
+                responses = tg['responses']
+                return random.choice(responses)
+    else:
+        return "I didn't get that, try again"
+
+@app.route('/chat', methods=['GET', 'POST'])
+def chatBot():
+    chatInput = request.form.get('chatInput', '')
+    if not chatInput:
+        return jsonify(chatBotReply="No se proporcionó entrada.")
+    try:
+        intents.append({
+            "tag": chatInput,
+            "patterns": [chatInput],
+            "responses": ["Respuesta a " + chatInput]
+        })
+        
+        modelo = entrenar_modelo()
+        reply = responder_pregunta(modelo, chatInput)
+        return jsonify(chatBotReply=reply)
+    except Exception as e:
+        return jsonify(chatBotReply=f"Error en chatBot: {e}")
+
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=7860, debug=True)