Update app.py

app.py

@@ -1,15 +1,86 @@
-import streamlit as st
-from transformers import pipeline
-from flask import Flask, render_template, request
 from transformers import GPT2LMHeadModel, GPT2Tokenizer
 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 = 'path/to/your/dataset.json'
 
-pipe = pipeline('sentiment-analysis')
-text = st.text_area('Enter your text here: ')
+tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
+model = GPT2LMHeadModel.from_pretrained('gpt2')
 
-if text:
-    out = pipe(text)
-    print(out)
+def compare_sentences(sentence1, sentence2):
+    vectorizer = CountVectorizer().fit_transform([sentence1, sentence2])
+    similarity = cosine_similarity(vectorizer)
+    similarity_score = similarity[0, 1]
+    return similarity_score
+
+def generate_gpt2_response(question):
+    input_ids = tokenizer.encode(question, return_tensors='pt')
+    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:
+        data = json.load(json_file)
+
+    question = question.lower()
+
+    max_similarity = 0
+    selected_response = None
+
+    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["response"]
+
+    # Set a threshold for similarity score to switch to GPT-2
+    similarity_threshold = 0.4  # Adjust this threshold as needed
+    if max_similarity < similarity_threshold:
+        generated_response = generate_gpt2_response(question)
+        selected_response = generated_response
+
+    # Fallback to a default message if no suitable response is found
+    if selected_response is None:
+        selected_response = "CHAT BOT --> I'm sorry, I don't have data about that.\n"
+
+    return selected_response
+
+# Example usage
+user_input = input("Ask a question: ")
+response = find_question_and_answer(dataset_path, user_input)
+print(response)
+
+
+
+
+
+
+
+
+
+
+# import streamlit as st
+# from transformers import pipeline
+# from flask import Flask, render_template, request
+# from transformers import GPT2LMHeadModel, GPT2Tokenizer
+# from sklearn.feature_extraction.text import CountVectorizer
+# from sklearn.metrics.pairwise import cosine_similarity
+# import json
+
+
+# pipe = pipeline('sentiment-analysis')
+# text = st.text_area('Enter your text here: ')
+
+# if text:
+#     out = pipe(text)
+#     print(out)