Update app.py

app.py

@@ -4,12 +4,11 @@ from sklearn.feature_extraction.text import CountVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
 import json
 
-# Set the path to your dataset file
-dataset_path = 'Q_and_A_Lagos.json'
-
 tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
 model = GPT2LMHeadModel.from_pretrained('gpt2')
 
+json_file_path = 'Q_and_A_Lagos.json'
+
 def compare_sentences(sentence1, sentence2):
     vectorizer = CountVectorizer().fit_transform([sentence1, sentence2])
     similarity = cosine_similarity(vectorizer)
@@ -18,25 +17,17 @@ def compare_sentences(sentence1, sentence2):
 
 def generate_gpt2_response(question):
     input_ids = tokenizer.encode(question, return_tensors='pt')
-
-    # Remove padding tokens if present
-    input_ids = input_ids[:, :model.config.max_position_embeddings]
-
-    generated_output = model.generate(
-        input_ids,
-        max_length=len(input_ids[0]) + 100,
-        num_beams=5,
-        no_repeat_ngram_size=2,
-        top_k=10,
-        top_p=1,
-        temperature=0.9
-    )
-
+    generated_output = model.generate(input_ids, max_length=len(input_ids[0]) + 100,
+                                      num_beams=5,
+                                      no_repeat_ngram_size=2,
+                                      top_k=10,
+                                      top_p=1,
+                                      temperature=0.9)
     generated_response = tokenizer.decode(generated_output[0], skip_special_tokens=True)
     return generated_response
 
-def find_question_and_answer(dataset_file, question):
-    with open(dataset_file, "r") as json_file:
+def find_question_and_answer(json_file, question):
+    with open(json_file, "r") as json_file:
         data = json.load(json_file)
 
     question = question.lower()
@@ -44,13 +35,13 @@ def find_question_and_answer(dataset_file, question):
     max_similarity = 0
     selected_response = None
 
-    for q_and_a in data.get("questions", []):
-        response_message = q_and_a.get("response", "").lower()
+    for q_and_a in data["questions"]:
+        response_message = q_and_a["response"].lower()
         similarity_score = compare_sentences(question, response_message)
 
         if similarity_score > max_similarity:
             max_similarity = similarity_score
-            selected_response = q_and_a.get("response", "")
+            selected_response = q_and_a["response"]
 
     # Set a threshold for similarity score to switch to GPT-2
     similarity_threshold = 0.4  # Adjust this threshold as needed
@@ -64,13 +55,14 @@ def find_question_and_answer(dataset_file, question):
 
     return selected_response
 
-# Streamlit UI
-st.title("Chatbot App")
-user_input = st.text_input("Ask a question:")
-response = find_question_and_answer(dataset_path, user_input)
-st.text(response)
-estion_and_answer(dataset_path, user_input)
-st.text(response)
+if __name__ == '__main__':
+    while True:
+        user_input = input("Enter your question: ")
+        if user_input.lower() == 'exit':
+            break
+        response = find_question_and_answer(json_file_path, user_input)
+        print(response)
+