Update app.py

app.py

@@ -1,45 +1,53 @@
-from flask import Flask, request, jsonify, render_template
+import gradio as gr
 from huggingface_hub import InferenceClient
-import os
 
-# Initialize the Flask app
-app = Flask(__name__)
+# HuggingFace API Client
+client = InferenceClient(model="Futuresony/future_ai_12_10_2024.gguf")
 
-# Initialize the Hugging Face Inference Client
-client = InferenceClient("Futuresony/future_ai_12_10_2024.gguf")
+def respond(message, history, system_message, max_tokens, temperature, top_p):
+    """
+    Function to process user messages and return AI responses.
+    """
+    messages = [{"role": "system", "content": system_message}]
+    
+    # Append conversation history
+    for user, assistant in history:
+        if user:
+            messages.append({"role": "user", "content": user})
+        if assistant:
+            messages.append({"role": "assistant", "content": assistant})
+    
+    # Add user message
+    messages.append({"role": "user", "content": message})
 
-@app.route("/")
-def home():
-    # Render the HTML template
-    return render_template("index.html")
-
-@app.route("/message", methods=["POST"])
-def fetch_message():
-    data = request.json
-    message = data.get("text", "")
-    if not message:
-        return jsonify({"error": "No input provided."}), 400
-
-    # Define model parameters
-    model_params = {
-        "temperature": 0.7,  # Controls randomness
-        "top_p": 0.9,       # Nucleus sampling
-        "max_length": 300,  # Limit response length
-        "do_sample": True   # Enable sampling
-    }
-
-    # Process the message using the Hugging Face model
+    response = ""
     try:
-        response = client.text_generation(
-            message,
-            **model_params  # Pass parameters
-        )
-        return jsonify({"response": response})
+        # Stream AI-generated responses
+        for chunk in client.chat_completion(
+            messages=messages,
+            max_tokens=max_tokens,
+            stream=True,
+            temperature=temperature,
+            top_p=top_p,
+        ):
+            token = chunk.choices[0].delta.content
+            response += token
+            yield response
     except Exception as e:
-        return jsonify({"error": str(e)}), 500
+        yield f"Error: {str(e)}"
+
+# Gradio Chat Interface
+demo = gr.ChatInterface(
+    fn=respond,
+    inputs=[
+        gr.Textbox(value="You are a helpful assistant.", label="System Prompt"),
+        gr.Slider(1, 2048, value=512, step=1, label="Max Tokens"),
+        gr.Slider(0.1, 4.0, value=0.7, step=0.1, label="Temperature"),
+        gr.Slider(0.1, 1.0, value=0.95, step=0.05, label="Top-P"),
+    ],
+)
 
+# Run Gradio App
 if __name__ == "__main__":
-    # Use PORT environment variable or default to 7860
-    port = int(os.getenv("PORT", 7860))
-    app.run(host="0.0.0.0", port=port)
+    demo.launch(server_name="0.0.0.0", server_port=7860)