Update app.py

app.py

@@ -1,19 +1,43 @@
 import streamlit as st
 from llama_cpp import Llama
 
-# llm = Llama.from_pretrained(
-#     repo_id="Mykes/med_gemma7b_gguf",
-#     filename="*Q4_K_M.gguf",
-#     verbose=False,
-#     n_ctx=512,
-#     n_batch=512,
-#     n_threads=4
-# )
+st.set_page_config(page_title="Chat with AI", page_icon="🤖")
+
+# Custom CSS for better styling
+st.markdown("""
+<style>
+.stTextInput > div > div > input {
+    background-color: #f0f2f6;
+}
+.chat-message {
+    padding: 1.5rem; border-radius: 0.5rem; margin-bottom: 1rem; display: flex
+}
+.chat-message.user {
+    background-color: #2b313e
+}
+.chat-message.bot {
+    background-color: #475063
+}
+.chat-message .avatar {
+  width: 20%;
+}
+.chat-message .avatar img {
+  max-width: 78px;
+  max-height: 78px;
+  border-radius: 50%;
+  object-fit: cover;
+}
+.chat-message .message {
+  width: 80%;
+  padding: 0 1.5rem;
+  color: #fff;
+}
+</style>
+""", unsafe_allow_html=True)
+
 @st.cache_resource
 def load_model():
     return Llama.from_pretrained(
-        # repo_id="Mykes/med_gemma7b_gguf",
-        # filename="*Q4_K_M.gguf",
         repo_id="Mykes/med_phi3-mini-4k-GGUF",
         filename="*Q4_K_M.gguf",
         verbose=False,
@@ -24,32 +48,44 @@ def load_model():
 
 llm = load_model()
 
-# basic_prompt = "Below is the context which is your conversation history and the last user question. Write a response according the context and question. ### Context: user: Ответь мне на вопрос о моем здоровье. assistant: Конечно! Какой у Вас вопрос? ### Question: {question} ### Response:"
 basic_prompt = "Q: {question}\nA:"
-input_text = st.text_input('text')
-model_input = basic_prompt.format(question=input_text)
 
-if input_text:
-    # Create an empty placeholder for the output
-    output_placeholder = st.empty()
-    
-    # Initialize an empty string to store the generated text
-    generated_text = ""
+# Initialize chat history
+if "messages" not in st.session_state:
+    st.session_state.messages = []
+
+# Display chat messages from history on app rerun
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.markdown(message["content"])
+
+# React to user input
+if prompt := st.chat_input("What is your question?"):
+    # Display user message in chat message container
+    st.chat_message("user").markdown(prompt)
+    # Add user message to chat history
+    st.session_state.messages.append({"role": "user", "content": prompt})
+
+    model_input = basic_prompt.format(question=prompt)
     
-    # Stream the output
-    for token in llm(
-        model_input,
-        # max_tokens=32,
-        max_tokens=None,
-        stop=["<end_of_turn>"],
-        echo=True,
-        stream=True  # Enable streaming
-    ):
-        # Append the new token to the generated text
-        generated_text += token['choices'][0]['text']
+    # Display assistant response in chat message container
+    with st.chat_message("assistant"):
+        message_placeholder = st.empty()
+        full_response = ""
         
-        # Update the placeholder with the current generated text
-        output_placeholder.write(generated_text)
+        for token in llm(
+            model_input,
+            max_tokens=None,
+            stop=["<end_of_turn>"],
+            echo=True,
+            stream=True
+        ):
+            full_response += token['choices'][0]['text']
+            message_placeholder.markdown(full_response + "▌")
+        message_placeholder.markdown(full_response)
+    
+    # Add assistant response to chat history
+    st.session_state.messages.append({"role": "assistant", "content": full_response})
 
-    # After the generation is complete, you can do any final processing if needed
-    st.write("Generation complete!")
+st.sidebar.title("Chat with AI")
+st.sidebar.markdown("This is a simple chat interface using Streamlit and an AI model.")