Create app.py

app.py

@@ -0,0 +1,100 @@
+import gradio as gr
+from huggingface_hub import InferenceClient
+import os
+
+# Initialize the Inference Client
+client = InferenceClient(token=os.environ.get("HF_TOKEN"))
+
+# List of available models (you can add more)
+AVAILABLE_MODELS = [
+    "meta-llama/Llama-3.3-70B-Instruct",
+    "Qwen/Qwen2.5-Coder-32B-Instruct",
+    "mistralai/Mistral-7B-Instruct-v0.3",
+    "google/gemma-2-9b-it",
+    "microsoft/Phi-3.5-mini-instruct",
+    "HuggingFaceH4/zephyr-7b-beta",
+    "tiiuae/falcon-7b-instruct",
+    "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
+]
+
+def chat_with_models(message, history, selected_models):
+    """
+    Send message to selected models and return their responses
+    """
+    if not selected_models:
+        return history + [(message, "⚠️ Please select at least one model first!")]
+    
+    if len(selected_models) > 5:
+        return history + [(message, "⚠️ Please select maximum 5 models only!")]
+    
+    # Create response text
+    responses = []
+    
+    for model_name in selected_models:
+        try:
+            response = client.chat_completion(
+                model=model_name,
+                messages=[{"role": "user", "content": message}],
+                max_tokens=500,
+            )
+            model_response = response.choices[0].message.content
+            responses.append(f"**{model_name}:**\n{model_response}\n")
+        except Exception as e:
+            responses.append(f"**{model_name}:**\n❌ Error: {str(e)}\n")
+    
+    combined_response = "\n---\n\n".join(responses)
+    return history + [(message, combined_response)]
+
+# Create the Gradio interface
+with gr.Blocks(title="Anki-Chat: Multi-Model Chat", theme=gr.themes.Soft()) as demo:
+    gr.Markdown(
+        """
+        # 🤖 Anki-Chat: Multi-Model Chat Interface
+        
+        Select up to 5 AI models and chat with them simultaneously to compare their responses!
+        """
+    )
+    
+    with gr.Row():
+        with gr.Column(scale=1):
+            gr.Markdown("### Select Models (Max 5)")
+            model_checkboxes = gr.CheckboxGroup(
+                choices=AVAILABLE_MODELS,
+                label="Available Models",
+                value=[AVAILABLE_MODELS[0]],  # Default to first model
+            )
+        
+        with gr.Column(scale=2):
+            chatbot = gr.Chatbot(
+                label="Chat",
+                height=500,
+            )
+            
+            with gr.Row():
+                msg = gr.Textbox(
+                    label="Your Message",
+                    placeholder="Type your message here...",
+                    scale=4,
+                )
+                send_btn = gr.Button("Send", scale=1, variant="primary")
+            
+            clear_btn = gr.Button("Clear Chat")
+    
+    # Event handlers
+    msg.submit(chat_with_models, [msg, chatbot, model_checkboxes], [chatbot]).then(
+        lambda: "", None, [msg]
+    )
+    send_btn.click(chat_with_models, [msg, chatbot, model_checkboxes], [chatbot]).then(
+        lambda: "", None, [msg]
+    )
+    clear_btn.click(lambda: [], None, [chatbot])
+    
+    gr.Markdown(
+        """
+        ---
+        **Note:** This app uses Hugging Face's Inference API. Some models may take longer to respond or may be rate-limited.
+        """
+    )
+
+if __name__ == "__main__":
+    demo.launch()