Update app.py

app.py

@@ -2,40 +2,46 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 import gradio as gr
 import torch
 
-
-title = "🤖AI ChatBot"
+# Title and description
+title = "🤖 AI ChatBot"
 description = "Building open-domain chatbots is a challenging area for machine learning research."
 examples = [["How are you?"]]
 
-
+# Load model and tokenizer
 tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-large")
 model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-large")
 
+def predict(input_text, history=None):
+    if history is None:
+        history = []
+
+    # Tokenize new user input
+    new_user_input_ids = tokenizer.encode(input_text + tokenizer.eos_token, return_tensors="pt")
 
-def predict(input, history=[]):
-    # tokenize the new input sentence
-    new_user_input_ids = tokenizer.encode(
-        input + tokenizer.eos_token, return_tensors="pt"
-    )
+    # Prepare chat history
+    if history:
+        past_ids = torch.LongTensor(history)
+        bot_input_ids = torch.cat([past_ids, new_user_input_ids], dim=-1)
+    else:
+        bot_input_ids = new_user_input_ids
 
-    # append the new user input tokens to the chat history
-    bot_input_ids = torch.cat([torch.LongTensor(history), new_user_input_ids], dim=-1)
+    # Generate response
+    output_ids = model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id)
+    history = output_ids.tolist()
 
-    # generate a response
-    history = model.generate(
-        bot_input_ids, max_length=4000, pad_token_id=tokenizer.eos_token_id
-    ).tolist()
+    # Decode and extract bot reply
+    decoded_text = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+    user_reply = input_text
+    bot_reply = decoded_text.split(input_text)[-1].strip()
 
-    # convert the tokens to text, and then split the responses into lines
-    response = tokenizer.decode(history[0]).split("<|endoftext|>")
-    # print('decoded_response-->>'+str(response))
-    response = [
-        (response[i], response[i + 1]) for i in range(0, len(response) - 1, 2)
-    ]  # convert to tuples of list
-    # print('response-->>'+str(response))
-    return response, history
+    # Format chatbot UI output
+    chatbot_messages = []
+    if len(history) > 0:
+        chatbot_messages = [(user_reply, bot_reply)]
 
+    return chatbot_messages, history
 
+# Gradio interface
 gr.Interface(
     fn=predict,
     title=title,
@@ -43,5 +49,5 @@ gr.Interface(
     examples=examples,
     inputs=["text", "state"],
     outputs=["chatbot", "state"],
-    theme="finlaymacklon/boxy_violet",
-).launch()
+    theme="finlaymacklon/boxy_violet"
+).launch()