Update app.py

app.py

@@ -1,7 +1,7 @@
 # app.py (for Hugging Face Space & local dev)
 import os
 import gradio as gr
-from huggingface_hub import InferenceClient
+import openai
 from pydantic import BaseModel
 from langchain_openai import ChatOpenAI
 from langchain_core.prompts import ChatPromptTemplate
@@ -72,19 +72,24 @@ def chat_fn(user_message, history):
 
 css = ".chat-message.user {color: #0b5394;} .chat-message.bot {color: #38761d;}"
 
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
 def respond(message, history, system_message, max_tokens, temperature, top_p):
     # history is now a list of {"role":"user"/"assistant","content":...}
     messages = [{"role":"system","content":system_message}] + history
     messages.append({"role":"user","content":message})
 
-    response = ""
-    for chunk in client.chat_completion(messages=messages, stream=True,):
-            token = chunk.choices[0].delta.content or ""
-            response += token
-            # yield the **full** list of messages each time:
-            yield messages + [{"role":"assistant","content":response}]
+    for u,b in history:
+        msgs += [{"role":"user","content":u}, {"role":"assistant","content":b}]
+    msgs.append({"role":"user","content":message})
+
+    resp = ""
+    for chunk in openai.ChatCompletion.create(
+        model="gpt-4o-mini",      # or gpt-4, gpt-3.5-turbo, etc.
+        messages=msgs,
+        stream=True
+    ):
+        delta = chunk.choices[0].delta.get("content","")
+        resp += delta
+        yield resp
 
 demo = gr.ChatInterface(
     respond,