Rename app.py to src/app.py

app.py → src/app.py

@@ -1,20 +1,11 @@
-import gradio as gr
+import streamlit as st
 from huggingface_hub import InferenceClient
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
+# Initialize the Inference client with the model
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
+# Function to generate a response
+def respond(message, history, system_message, max_tokens, temperature, top_p):
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
@@ -27,6 +18,7 @@ def respond(
 
     response = ""
 
+    # Make the API call and stream the response
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
@@ -35,30 +27,38 @@ def respond(
         top_p=top_p,
     ):
         token = message.choices[0].delta.content
-
         response += token
         yield response
 
+# Streamlit app layout
+st.title("Zephyr Chatbot")
+
+# Textbox for user input
+user_message = st.text_input("Your message:")
+
+# Text area for displaying chat history
+history = st.session_state.get("history", [])
+
+# System message (initialization)
+system_message = st.text_area("System message", value="You are a friendly Chatbot.")
+
+# Sliders for max tokens, temperature, and top-p
+max_tokens = st.slider("Max new tokens", min_value=1, max_value=2048, value=512, step=1)
+temperature = st.slider("Temperature", min_value=0.1, max_value=4.0, value=0.7, step=0.1)
+top_p = st.slider("Top-p (nucleus sampling)", min_value=0.1, max_value=1.0, value=0.95, step=0.05)
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, 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 (nucleus sampling)",
-        ),
-    ],
-)
+# Button to send the message
+if st.button("Send"):
+    # Get the response from the model
+    response_text = ""
+    for text in respond(user_message, history, system_message, max_tokens, temperature, top_p):
+        response_text = text
 
+    # Update chat history in session state
+    history.append((user_message, response_text))
+    st.session_state["history"] = history
 
-if __name__ == "__main__":
-    demo.launch()
+    # Display chat history
+    for user_msg, assistant_msg in history:
+        st.write(f"**You:** {user_msg}")
+        st.write(f"**Bot:** {assistant_msg}")