Update app.py

app.py

@@ -3,40 +3,6 @@ from llama_cpp import Llama
 from huggingface_hub import hf_hub_download
 import random
 
-# Custom CSS for better styling
-custom_css = """
-    .gradio-container {
-        background: linear-gradient(to bottom, #1a1a2e, #16213e) !important;
-    }
-    .header-text {
-        text-align: center;
-        color: #e2e8f0;
-        font-size: 2.5em;
-        font-weight: bold;
-        margin: 1em 0;
-        text-shadow: 0 0 10px rgba(255, 255, 255, 0.3);
-    }
-    .subheader {
-        text-align: center;
-        color: #94a3b8;
-        font-size: 1.2em;
-        margin-bottom: 2em;
-    }
-    .controls-section {
-        background: rgba(255, 255, 255, 0.05);
-        padding: 1.5em;
-        border-radius: 10px;
-        margin: 1em 0;
-    }
-    .model-info {
-        background: rgba(0, 0, 0, 0.2);
-        padding: 1em;
-        border-radius: 8px;
-        margin-top: 1em;
-        color: #94a3b8;
-    }
-"""
-
 # Initialize model
 model_path = hf_hub_download(
     repo_id="AstroMLab/AstroSage-8B-GGUF",
@@ -75,43 +41,25 @@ def respond(message, history, system_message, max_tokens, temperature, top_p):
             messages.append({"role": "assistant", "content": assistant_msg})
     messages.append({"role": "user", "content": message})
     
-    response = llm.create_chat_completion(
-        messages=messages,
-        max_tokens=max_tokens,
-        temperature=temperature,
-        top_p=top_p
-    )
-    
-    return response["choices"][0]["message"]["content"]
-
-def regenerate(message, history, system_message, max_tokens, temperature, top_p):
-    # Remove the last assistant message from history
-    if history and len(history) > 0:
-        history = history[:-1]
-    
-    # Generate a new response
-    return respond(message, history, system_message, max_tokens, temperature, top_p)
+    try:
+        response = llm.create_chat_completion(
+            messages=messages,
+            max_tokens=max_tokens,
+            temperature=temperature,
+            top_p=top_p
+        )
+        return response["choices"][0]["message"]["content"]
+    except Exception as e:
+        return f"Error: {e}"
 
 def clear_context():
     return [], get_random_greeting()
 
-with gr.Blocks(css=custom_css) as demo:
-    gr.HTML(
-        """
-        <div class="header-text">🌌 AstroSage-LLAMA-3.1-8B</div>
-        <div class="subheader">Your AI Guide to the Cosmos</div>
-        """
-    )
+with gr.Blocks() as demo:
+    gr.HTML("<div class='header-text'>🌌 AstroSage-LLAMA-3.1-8B</div><div class='subheader'>Your AI Guide to the Cosmos</div>")
     
-    chatbot = gr.Chatbot(
-        value=[[None, get_random_greeting()]],
-        height=400,
-        show_label=False,
-    )
-    msg = gr.Textbox(
-        placeholder="Ask about astronomy, astrophysics, or cosmology...",
-        show_label=False,
-    )
+    chatbot = gr.Chatbot(height=400)
+    msg = gr.Textbox(placeholder="Ask about astronomy, astrophysics, or cosmology...")
     
     with gr.Accordion("Advanced Settings", open=False) as advanced_settings:
         system_msg = gr.Textbox(
@@ -119,82 +67,26 @@ with gr.Blocks(css=custom_css) as demo:
             label="System Message",
             lines=3
         )
-        with gr.Row():
-            max_tokens = gr.Slider(
-                minimum=1,
-                maximum=2048,
-                value=512,
-                step=1,
-                label="Max Tokens"
-            )
-            temperature = gr.Slider(
-                minimum=0.1,
-                maximum=4.0,
-                value=0.7,
-                step=0.1,
-                label="Temperature"
-            )
-            top_p = gr.Slider(
-                minimum=0.1,
-                maximum=1.0,
-                value=0.9,
-                step=0.05,
-                label="Top-p"
-            )
+        max_tokens = gr.Slider(1, 2048, value=512, step=1, label="Max Tokens")
+        temperature = gr.Slider(0.1, 4.0, value=0.7, step=0.1, label="Temperature")
+        top_p = gr.Slider(0.1, 1.0, value=0.9, step=0.05, label="Top-p")
     
     with gr.Row():
         clear = gr.Button("🌟 New Chat")
-        regenerate_btn = gr.Button("🔄 Regenerate")
         submit = gr.Button("Send 🚀", variant="primary")
     
-    gr.HTML(
-        """
-        <div class="model-info">
-            <p>📚 Model: AstroSage-LLAMA-3.1-8B (8-bit Quantized)</p>
-            <p>🔧 Built with llama.cpp, Gradio, and Python</p>
-            <p>💫 Specialized in astronomy, astrophysics, and cosmology</p>
-        </div>
-        """
-    )
-    
-    # Set up event handlers
-    msg.submit(
-        respond,
-        [msg, chatbot, system_msg, max_tokens, temperature, top_p],
-        [chatbot],
-        queue=False
-    ).then(
-        lambda: "",
-        None,
-        [msg],
-        queue=False
-    )
-    
+    def handle_submit(message, history, system_message, max_tokens, temperature, top_p):
+        response = respond(message, history, system_message, max_tokens, temperature, top_p)
+        history.append((message, response))
+        return history, ""
+
     submit.click(
-        respond,
+        handle_submit,
         [msg, chatbot, system_msg, max_tokens, temperature, top_p],
-        [chatbot],
-        queue=False
-    ).then(
-        lambda: "",
-        None,
-        [msg],
-        queue=False
+        [chatbot, msg]
     )
     
-    regenerate_btn.click(
-        regenerate,
-        [msg, chatbot, system_msg, max_tokens, temperature, top_p],
-        [chatbot],
-        queue=False
-    )
-    
-    clear.click(
-        clear_context,
-        None,
-        [chatbot, msg],
-        queue=False
-    )
+    clear.click(clear_context, [], [chatbot, msg])
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()