Update app.py

app.py

@@ -1,11 +1,15 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import requests
+import json
+import os
 
-"""
-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")
+API_URL = "https://host.palple.polrambora.com/pmsq"
+API_TOKEN = os.getenv("POLLY")  
 
+headers = {
+    "Authorization": f"{API_TOKEN}",
+    "Content-Type": "application/json",
+}
 
 def respond(
     message,
@@ -13,10 +17,9 @@ def respond(
     system_message,
     max_tokens,
     temperature,
-    top_p,
 ):
-    messages = [{"role": "system", "content": system_message}]
-
+    messages = []
+    
     for val in history:
         if val[0]:
             messages.append({"role": "user", "content": val[0]})
@@ -25,19 +28,24 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
-    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
+    data = {
+        "preferences": {
+            "max_tokens": max_tokens,
+            "temperature": temperature,
+            "system_message": system_message
+        },
+        "conversation_history": history,
+        "input": message
+    }
+
+    response = requests.post(API_URL, headers=headers, data=json.dumps(data))
+    response_json = response.json()
+
+    if response.status_code == 200:
+        generated_text = response_json.msq.message[0]
+        yield generated_text
+    else:
+        yield "Error: " + response_json.get("error", "Unknown error occurred.")
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
@@ -45,19 +53,11 @@ For information on how to customize the ChatInterface, peruse the gradio docs: h
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(value="You are PMSQ", 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)",
-        ),
+        gr.Slider(minimum=0.1, maximum=4.0, value=0.3, step=0.1, label="Temperature"),
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()