Update app.py

app.py

@@ -1,64 +1,107 @@
+import os
 import gradio as gr
-from huggingface_hub import InferenceClient
+from openai import OpenAI
+from typing import List, Tuple
 
-"""
-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")
+# Initialize OpenRouter client
+client = OpenAI(
+    base_url="https://openrouter.ai/api/v1",
+    api_key=os.getenv("OPENROUTER_API_KEY")
+)
 
+# Available models
+MODELS = [
+    "nousresearch/hermes-3-llama-3.1-405b",
+    "anthropic/claude-3-opus",
+    "google/gemma-7b",
+    "mistralai/mixtral-8x7b"
+]
 
 def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
+    message: str,
+    history: List[Tuple[str, str]],
+    system_message: str,
+    model: str,
+    max_tokens: int,
+    temperature: float,
+    top_p: float,
+) -> str:
+    # Construct messages array with system message and history
     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 conversation history
+    for user_msg, assistant_msg in history:
+        if user_msg:
+            messages.append({"role": "user", "content": user_msg})
+        if assistant_msg:
+            messages.append({"role": "assistant", "content": assistant_msg})
+    
+    # Add current message
     messages.append({"role": "user", "content": message})
+    
+    try:
+        completion = client.chat.completions.create(
+            extra_headers={
+                "HTTP-Referer": os.getenv("SITE_URL", "https://huggingface.co/spaces"),
+                "X-Title": os.getenv("SITE_NAME", "OpenRouter Gradio Interface"),
+            },
+            model=model,
+            messages=messages,
+            max_tokens=max_tokens,
+            temperature=temperature,
+            top_p=top_p,
+            stream=True  # Enable streaming
+        )
+        
+        # Stream the response
+        response = ""
+        for chunk in completion:
+            if chunk.choices[0].delta.content is not None:
+                response += chunk.choices[0].delta.content
+                yield response
+                
+    except Exception as e:
+        yield f"Error: {str(e)}"
 
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        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.Textbox(
+            value="You are a helpful and friendly AI assistant.",
+            label="System message"
+        ),
+        gr.Dropdown(
+            choices=MODELS,
+            value=MODELS[0],
+            label="Model"
+        ),
+        gr.Slider(
+            minimum=1,
+            maximum=2048,
+            value=512,
+            step=1,
+            label="Max new tokens"
+        ),
+        gr.Slider(
+            minimum=0.1,
+            maximum=2.0,
+            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)",
+            label="Top-p (nucleus sampling)"
         ),
     ],
+    title="OpenRouter Chat Interface",
+    description="Chat with various AI models through OpenRouter API"
 )
 
-
+# Launch the app
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()