Update app.py

app.py

@@ -1,24 +1,10 @@
-#refer llama recipes for more info https://github.com/huggingface/huggingface-llama-recipes/blob/main/inference-api.ipynb
-#huggingface-llama-recipes : https://github.com/huggingface/huggingface-llama-recipes/tree/main
 import gradio as gr
-from openai import OpenAI
+import requests
 import os
 
 ACCESS_TOKEN = os.getenv("HF_TOKEN")
 
-client = OpenAI(
-    base_url="https://api-inference.huggingface.co/v1/",
-    api_key=ACCESS_TOKEN,
-)
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
+def respond(message, history: list[tuple[str, str]], system_message, max_tokens, temperature, top_p):
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
@@ -29,41 +15,35 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
-    
-    for message in  client.chat.completions.create(
-        model="CohereForAI/c4ai-command-r-plus",
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-        messages=messages,
-    ):
-        token = message.choices[0].delta.content
-        
-        response += token
-        yield response
-        
+    # 사용자의 최종 메시지를 포함한 전체 메시지 리스트를 JSON 형식으로 구성
+    data = {
+        "model": "command-r-plus:104b-fp16",
+        "prompt": message,
+        "max_tokens": max_tokens,
+        "temperature": temperature,
+        "top_p": top_p
+    }
+
+    # API 요청 보내기
+    response = requests.post("http://hugpu.ai:7877/api/generate", json=data)
+    generated_text = response.json().get('generated_text', '')  # 응답에서 생성된 텍스트 추출
+
+    return generated_text  # 생성된 텍스트 반환
+
 chatbot = gr.Chatbot(height=600)
 
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
+demo = gr.Interface(
+    fn=respond,
+    inputs=[
+        gr.Textbox(label="Your Message"),
         gr.Textbox(value="", 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",
-        ),
-        
+        gr.Slider(minimum=1, maximum=2048, value=512, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, label="Temperature"),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, label="Top-P")
     ],
-    fill_height=True,
-    chatbot=chatbot,
-    theme="Nymbo/Nymbo_Theme",
+    outputs=chatbot,
+    theme="Nymbo/Nymbo_Theme"
 )
+
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()