Update app.py

app.py

@@ -1,42 +1,100 @@
+# import streamlit as st
+# from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# # Load the model and tokenizer
+# @st.cache_resource
+# def load_model_and_tokenizer():
+#     model_name = "microsoft/DialoGPT-medium"  # Replace with your chosen model
+#     tokenizer = AutoTokenizer.from_pretrained(model_name)
+#     model = AutoModelForCausalLM.from_pretrained(model_name)
+#     return tokenizer, model
+
+# tokenizer, model = load_model_and_tokenizer()
+
+# # Streamlit App
+# st.title("General Chatbot")
+# st.write("A chatbot powered by an open-source model from Hugging Face.")
+
+# # Initialize the conversation
+# if "conversation_history" not in st.session_state:
+#     st.session_state["conversation_history"] = []
+
+# # Input box for user query
+# user_input = st.text_input("You:", placeholder="Ask me anything...", key="user_input")
+
+# if st.button("Send") and user_input:
+#     # Append user input to history
+#     st.session_state["conversation_history"].append({"role": "user", "content": user_input})
+    
+#     # Tokenize and generate response
+#     input_ids = tokenizer.encode(user_input + tokenizer.eos_token, return_tensors="pt")
+#     chat_history_ids = model.generate(input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id)
+#     response = tokenizer.decode(chat_history_ids[:, input_ids.shape[-1]:][0], skip_special_tokens=True)
+
+#     # Append model response to history
+#     st.session_state["conversation_history"].append({"role": "assistant", "content": response})
+
+# # Display the conversation
+# for message in st.session_state["conversation_history"]:
+#     if message["role"] == "user":
+#         st.write(f"**You:** {message['content']}")
+#     else:
+#         st.write(f"**Bot:** {message['content']}")
+
 import streamlit as st
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 # Load the model and tokenizer
 @st.cache_resource
 def load_model_and_tokenizer():
-    model_name = "microsoft/DialoGPT-medium"  # Replace with your chosen model
+    model_name = "microsoft/DialoGPT-medium"  # You can replace with any Hugging Face conversational model
     tokenizer = AutoTokenizer.from_pretrained(model_name)
     model = AutoModelForCausalLM.from_pretrained(model_name)
     return tokenizer, model
 
 tokenizer, model = load_model_and_tokenizer()
 
-# Streamlit App
+# Streamlit App Title
 st.title("General Chatbot")
-st.write("A chatbot powered by an open-source model from Hugging Face.")
+st.markdown("This chatbot is powered by an open-source model from Hugging Face. Feel free to ask me anything!")
 
-# Initialize the conversation
-if "conversation_history" not in st.session_state:
-    st.session_state["conversation_history"] = []
+# Initialize the session state for conversation history
+if "chat_history" not in st.session_state:
+    st.session_state["chat_history"] = ""
 
-# Input box for user query
-user_input = st.text_input("You:", placeholder="Ask me anything...", key="user_input")
+# User Input Section
+user_input = st.text_input("You:", placeholder="Type your message here...", key="user_input")
 
 if st.button("Send") and user_input:
-    # Append user input to history
-    st.session_state["conversation_history"].append({"role": "user", "content": user_input})
+    # Add user input to the conversation history
+    st.session_state["chat_history"] += f"User: {user_input}\n"
+
+    # Tokenize the input with conversation history
+    input_ids = tokenizer.encode(st.session_state["chat_history"], return_tensors="pt")
+
+    # Generate a response
+    chat_history_ids = model.generate(
+        input_ids,
+        max_length=1500,  # Allow long responses
+        min_length=200,   # Ensure responses are not too short
+        temperature=1.0,  # Adjust for creativity
+        top_p=0.9,        # Nucleus sampling for focused responses
+        repetition_penalty=1.2,  # Penalize repeated phrases
+        pad_token_id=tokenizer.eos_token_id
+    )
     
-    # Tokenize and generate response
-    input_ids = tokenizer.encode(user_input + tokenizer.eos_token, return_tensors="pt")
-    chat_history_ids = model.generate(input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id)
+    # Decode the model's response
     response = tokenizer.decode(chat_history_ids[:, input_ids.shape[-1]:][0], skip_special_tokens=True)
 
-    # Append model response to history
-    st.session_state["conversation_history"].append({"role": "assistant", "content": response})
+    # Add the response to the conversation history
+    st.session_state["chat_history"] += f"Bot: {response}\n"
+
+    # Display the conversation
+    st.markdown(f"**You:** {user_input}")
+    st.markdown(f"**Bot:** {response}")
+
+# Display Full Conversation History
+st.divider()
+st.subheader("Conversation History:")
+st.text(st.session_state["chat_history"])
 
-# Display the conversation
-for message in st.session_state["conversation_history"]:
-    if message["role"] == "user":
-        st.write(f"**You:** {message['content']}")
-    else:
-        st.write(f"**Bot:** {message['content']}")