Update app.py

app.py

@@ -1,51 +1,39 @@
 import streamlit as st
-from transformers import AutoTokenizer, AutoModelForCausalLM
+from transformers import pipeline
 
-# Create a class for the session state
-class SessionState:
-    def __init__(self):
-        self.conversation_history = []
+# Choose an appropriate Hugging Face model for your chat application (replace with your desired model)
+model_name = "facebook/bart-base"
 
-# Initialize the session state
-session_state = SessionState()
+# Initialize the conversational AI pipeline
+chat_pipeline = pipeline("conversational", model=model_name)
 
-# Sidebar for setting parameters
-st.sidebar.title("Model Parameters")
-# You can add more parameters here as needed
-max_length = st.sidebar.slider("Max Length", 10, 100, 50)
-temperature = st.sidebar.slider("Temperature", 0.0, 1.0, 0.7)
+# Initialize session state to store chat history
+if "chat_history" not in st.session_state:
+    st.session_state["chat_history"] = []
 
-# Load the model and tokenizer with a loading message
-with st.spinner('Wait for model to respond..'):
-    model_name = "llmware/bling-red-pajamas-3b-0.1"
-    model = AutoModelForCausalLM.from_pretrained(model_name)
-    tokenizer = AutoTokenizer.from_pretrained(model_name)
+def display_chat_history():
+    """Displays the chat history in the Streamlit app."""
+    for message in st.session_state["chat_history"]:
+        st.write(f"{message['user']}: {message['text']}")
 
-# Create a chat input for the user
-input_text = st.chat_input("Enter your message:")
+def process_user_input(user_input):
+    """Processes user input using the conversational AI model and updates chat history."""
+    if user_input:
+        bot_response = chat_pipeline(user_input, max_length=1000)[0]["generated_text"]
+        st.session_state["chat_history"].append({"user": "You", "text": user_input})
+        st.session_state["chat_history"].append({"user": "Bot", "text": bot_response})
 
-# Check if the user has entered a message
-if input_text:
-    # Add the user's message to the conversation history
-    session_state.conversation_history.append(input_text)
+st.title("Streamlit Chat App with Hugging Face Model")
 
-    # Display the user's message
-    st.write("**User:**", input_text)
+# Display chat history
+display_chat_history()
 
-    # Create conversation history string
-    history_string = "\n".join(session_state.conversation_history)
+# User input using st.chat_input
+user_input = st.chat_input("Type your message here...", key="user_input")
 
-    # Tokenize the input text and history
-    inputs = tokenizer.encode_plus(history_string, input_text, return_tensors="pt")
+# Process user input on Enter key press
+if st.session_state.get("user_input", "") != user_input:
+    process_user_input(user_input)
+    st.session_state["user_input"] = ""  # Clear input field
 
-    # Generate the response from the model with additional parameters
-    outputs = model.generate(**inputs, max_length=max_length, temperature=temperature)
-
-    # Decode the response
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True).strip()
-
-    # Add the model's response to the conversation history
-    session_state.conversation_history.append(response)
-
-    # Display the model's response
-    st.write("**Assistant:**", response)
+st.write("**Note:** This is a simple demonstration. For more advanced features, consider using a dedicated chatbot framework.")