Update app.py

app.py

@@ -1,16 +1,10 @@
-import gradio as gr
+from flask import Flask, render_template, request, jsonify
 from huggingface_hub import InferenceClient
 
+app = Flask(__name__)
 client = InferenceClient("Futuresony/future_ai_12_10_2024.gguf")
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
+def respond(message, history, system_message, max_tokens, temperature, top_p):
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
@@ -20,7 +14,6 @@ def respond(
             messages.append({"role": "assistant", "content": val[1]})
 
     messages.append({"role": "user", "content": message})
-
     response = ""
 
     for message in client.chat_completion(
@@ -32,23 +25,25 @@ def respond(
     ):
         token = message.choices[0].delta.content
         response += token
-        yield response
-
-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)",
-        ),
-    ],
-)
-
-if __name__ == "__main__":
-    demo.launch()  # This will create a public link
+    return response
+
+@app.route('/')
+def index():
+    return render_template('index.html')
+
+@app.route('/get_response', methods=['POST'])
+def get_response():
+    data = request.json
+    message = data['message']
+    history = data.get('history', [])
+    system_message = data.get('system_message', "You are a friendly chatbot.")
+    max_tokens = int(data.get('max_tokens', 512))
+    temperature = float(data.get('temperature', 0.7))
+    top_p = float(data.get('top_p', 0.95))
+
+    response = respond(message, history, system_message, max_tokens, temperature, top_p)
+    return jsonify({'response': response})
+
+if __name__ == '__main__':
+    app.run(debug=True)
+