Upload ChatBot.py

ChatBot.py

@@ -0,0 +1,81 @@
+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
+
+tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
+model = GPT2LMHeadModel.from_pretrained('gpt2')
+
+json_file_path = 'interview-workspace\src\data\short_let_room.json'
+
+app = Flask(__name__)
+
+
+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,
+                                      pad_token_id=model.config.eos_token_id)
+    generated_response = tokenizer.decode(generated_output[0], skip_special_tokens=True)
+    return generated_response
+
+def find_question_and_answer(json_file, question, input_ids):
+    with open(json_file, "r") as json_file:
+        data = json.load(json_file)
+
+    quest = question.lower()
+
+    all_questions = data.get("questions", [])
+    all_response = data.get("responses", [])
+    for dataset_question in all_questions:
+        if 'question' in dataset_question and dataset_question['question'].lower() == quest:
+            for dataset_response in all_response:
+                if dataset_question['response_id'] == dataset_response['id']:
+                    response = {
+                        "Chat Bot ": dataset_response["response_message"],
+                        "Apartment ": dataset_response["response_message1"],
+                        "Address ": dataset_response["shortlet_Address"],
+                        "Price ": dataset_response["shortlet_Price"],
+                        "URL ": dataset_response.get("shortlet_url")
+                    }
+                    return response
+                
+    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,
+                                    pad_token_id=model.config.eos_token_id)
+    generated_response = tokenizer.decode(generated_output[0], skip_special_tokens=True)
+    return generated_response
+
+@app.route("/")
+def index():
+    return render_template('index.html')
+
+@app.route('/ask', methods=['POST'])
+def ask():
+    user_input = request.form['user_input']
+    if not user_input:
+        response = ""
+    else:
+        input_ids = tokenizer.encode(user_input, return_tensors='pt')
+        response = find_question_and_answer(json_file_path, user_input, input_ids)
+
+    if isinstance(response, dict):
+        response_type = "mapping"
+    else:
+        response_type = "string"
+
+    return render_template('index.html', user_input=user_input, response=response, response_type=response_type)
+
+
+if __name__ == '__main__':
+    app.run(debug=True)