Streamlit conversion

app.py

@@ -1,9 +1,13 @@
-import gradio as gr
+import streamlit as st
 from openai import OpenAI, APIError
 import os
 import tenacity
 
-ACCESS_TOKEN = os.getenv("HF_TOKEN")
+# Get the OpenAI API key from the Space settings
+ACCESS_TOKEN = os.getenv("ACCESS_TOKEN")
+
+# Get the model name from the Space settings
+MODEL =  "NousResearch/Hermes-3-Llama-3.1-8B"
 
 client = OpenAI(
     base_url="https://api-inference.huggingface.co/v1/",
@@ -33,7 +37,7 @@ def respond(
         response = ""
         
         for message in  client.chat.completions.create(
-            model="NousResearch/Hermes-3-Llama-3.1-8B",
+            model=MODEL,
             max_tokens=max_tokens,
             stream=True,
             temperature=temperature,
@@ -62,25 +66,16 @@ def respond(
         print(f"Error: {e}")
         yield "Error occurred. Please try again."
 
-chatbot = gr.Chatbot(height=600)
+st.title("Chatbot")
+st.write("Type a message to chat with the bot")
 
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=2048, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-P",
-        ),
-        
-    ],
-    fill_height=True,
-    chatbot=chatbot
-)
-if __name__ == "__main__":
-    demo.launch(show_error=True)
+message = st.text_input("Message")
+history = []
+system_message = st.text_input("System message")
+max_tokens = st.slider("Max new tokens", 1, 2048, 2048)
+temperature = st.slider("Temperature", 0.1, 4.0, 0.7)
+top_p = st.slider("Top-P", 0.1, 1.0, 0.95)
+
+if st.button("Send"):
+    response = respond(message, history, system_message, max_tokens, temperature, top_p)
+    st.write(response)