Update app.py

app.py

@@ -1,64 +1,83 @@
+import requests
 import gradio as gr
-from huggingface_hub import InferenceClient
+import logging
+import nest_asyncio
+from typing import Any
+from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
 
-"""
-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")
+# Logging Setup
+logger = logging.getLogger(__name__)
 
+# Default Hugging Face model and API URL
+DEFAULT_HUGGINGFACE_MODEL = "Eric1227/dolphin-2.5-mixtral-8x7b-MLX-6bit"  # Use your desired model
+HUGGINGFACE_API_URL = "https://api-inference.huggingface.co/models/{model_name}"
+API_KEY = "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"  # Your Hugging Face API key
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# Apply nest_asyncio to handle event loops in Jupyter (if using it)
+nest_asyncio.apply()
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+# Remote MCP Client Setup (Update with your remote MCP server URL)
+REMOTE_MCP_URL = "http://your.remote.mcp.server/sse"
+mcp_client = BasicMCPClient(REMOTE_MCP_URL)
+mcp_tool = McpToolSpec(client=mcp_client)
 
-    messages.append({"role": "user", "content": message})
+# Function to call Hugging Face Inference API
+def query_huggingface_api(prompt: str, model_name: str = DEFAULT_HUGGINGFACE_MODEL) -> str:
+    headers = {
+        "Authorization": f"Bearer {API_KEY}",
+        "Content-Type": "application/json"
+    }
 
-    response = ""
+    payload = {
+        "inputs": prompt
+    }
 
-    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 = requests.post(HUGGINGFACE_API_URL.format(model_name=model_name),
+                             headers=headers, json=payload)
 
-        response += token
-        yield response
+    if response.status_code == 200:
+        return response.json()[0]["generated_text"]
+    else:
+        logger.error(f"Error from Hugging Face API: {response.status_code}, {response.text}")
+        return "Error processing your request."
 
+# Function to interact with MCP (for processing or augmenting responses)
+def interact_with_mcp(input_text: str) -> str:
+    # Send input to MCP (modify as per your MCP interaction logic)
+    try:
+        response = mcp_client.query(input_text)  # Assuming `query` method is used for MCP interaction
+        return response['response']  # Adjust based on your MCP response format
+    except Exception as e:
+        logger.error(f"Error interacting with MCP: {str(e)}")
+        return "MCP interaction failed."
 
-"""
-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)",
-        ),
-    ],
-)
+# Create the function that Gradio will call for inference
+def generate_response_with_mcp(prompt: str) -> str:
+    # First, interact with the Hugging Face model
+    model_response = query_huggingface_api(prompt)
+    
+    # Then, send that response to the MCP system for additional processing
+    mcp_response = interact_with_mcp(model_response)
+    
+    # Combine Hugging Face and MCP responses (or modify logic as needed)
+    return f"Model Response: {model_response}\n\nMCP Response: {mcp_response}"
 
+# Set up Gradio interface
+def launch_gradio_interface():
+    with gr.Blocks() as demo:
+        gr.Markdown("### Hugging Face Model + Remote MCP Integration")
+        
+        with gr.Row():
+            prompt_input = gr.Textbox(label="Enter Your Prompt", placeholder="Type something here...")
+            output_text = gr.Textbox(label="Generated Response")
+        
+        # Button to submit the prompt
+        submit_btn = gr.Button("Generate Response")
+        
+        # Link the button action to the function
+        submit_btn.click(generate_response_with_mcp, inputs=prompt_input, outputs=output_text)
 
-if __name__ == "__main__":
     demo.launch()
+
+if __name__ == "__main__":
+    launch_gradio_interface()