Update app.py

app.py

@@ -1,72 +1,54 @@
 import gradio as gr
 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
-"""
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
+def respond(message, history):
+    system_message = """You are an interactive storyteller creating an immersive choose-your-own-adventure story. 
+    For each response:
+    1. Provide vivid descriptions of the scene and characters
+    2. Include meaningful dialogue or internal monologue
+    3. End with 3 different possible actions or decisions, phrased as complete sentences
+    Example endings:
+    - You could try climbing the ancient tree to get a better view
+    - Perhaps investigating the strange sound from the cave would reveal something
+    - Maybe approaching the mysterious stranger to ask for directions is wise
+    Keep responses engaging but concise."""
+    
     messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
+    
+    # Add history and current message
+    for user_msg, bot_msg in history:
+        messages.append({"role": "user", "content": user_msg})
+        messages.append({"role": "assistant", "content": bot_msg})
+    
     messages.append({"role": "user", "content": message})
-
+    
     response = ""
-
     for message in client.chat_completion(
         messages,
-        max_tokens=max_tokens,
+        max_tokens=512,
         stream=True,
-        temperature=temperature,
-        top_p=top_p,
+        temperature=0.7,
+        top_p=0.95,
     ):
         token = message.choices[0].delta.content
-
         response += token
         yield response
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Create Gradio interface
 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)",
-        ),
+    title="Interactive Story Adventure",
+    description="Describe what you want to do next in the story using natural language...",
+    examples=[
+        "Begin my adventure",
+        "I want to explore the mysterious cave",
+        "Let's try talking to the merchant",
+        "I decide to climb the tower"
     ],
+    theme=gr.themes.Soft()
 )
 
-###updated 2.27.2025 to go public###
-# ✅ Define the Gradio interface BEFORE launching
-iface = gr.Interface(
-    fn=chatbot_response,
-    inputs="text",
-    outputs="text",
-    title="CYOA Adventure Bot",
-    description="Type your choices and shape the adventure!")
-    
 if __name__ == "__main__":
-    iface.launch(server_name="0.0.0.0", server_port=7860, share=True)
+    demo.launch(server_name="0.0.0.0", server_port=7860)