Update app.py

app.py

@@ -1,20 +1,12 @@
-import gradio as gr
+from flask import Flask, request, jsonify
 from huggingface_hub import InferenceClient
 
-"""
-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
-"""
+# Initialize Flask app and Hugging Face client
+app = Flask(__name__)
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
+# Helper function to generate a response from the AI model
+def generate_response(message, history, system_message, max_tokens, temperature, top_p):
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
@@ -24,9 +16,9 @@ def respond(
             messages.append({"role": "assistant", "content": val[1]})
 
     messages.append({"role": "user", "content": message})
-
     response = ""
 
+    # Streaming response from the Hugging Face model
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
@@ -35,30 +27,32 @@ def respond(
         top_p=top_p,
     ):
         token = message.choices[0].delta.content
-
         response += token
-        yield response
 
+    return response
+
+# API endpoint to handle requests
+@app.route("/chat", methods=["POST"])
+def chat():
+    try:
+        data = request.json
+        message = data.get("message", "")
+        history = data.get("history", [])
+        system_message = data.get("system_message", "You are a friendly chatbot.")
+        max_tokens = data.get("max_tokens", 512)
+        temperature = data.get("temperature", 0.7)
+        top_p = data.get("top_p", 0.95)
+
+        # Validate inputs
+        if not isinstance(history, list) or not all(isinstance(pair, list) for pair in history):
+            return jsonify({"error": "Invalid history format. It should be a list of [message, response] pairs."}), 400
 
-"""
-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)",
-        ),
-    ],
-)
+        # Generate AI response
+        response = generate_response(message, history, system_message, max_tokens, temperature, top_p)
 
+        return jsonify({"response": response})
+    except Exception as e:
+        return jsonify({"error": str(e)}), 500
 
 if __name__ == "__main__":
-    demo.launch()
+    app.run(host="0.0.0.0", port=8000)