Update app.py

app.py

@@ -9,11 +9,8 @@ from huggingface_hub import InferenceClient
 # ===============================
 HF_TOKEN = os.getenv("HF")
 
-client = InferenceClient(
-    model="Qwen/Qwen2.5-7B-Instruct",
-    token=HF_TOKEN,
-    provider="hf-inference"
-)
+client = InferenceClient(model="Qwen/Qwen2.5-7B-Instruct", token=HF_TOKEN )
+
 
 # ===============================
 # SAFETY
@@ -52,7 +49,7 @@ User question:
 {user_question}
 """
     response = ""
-    for chunk in client.chat.completions.create(
+    for chunk in client.chat_completion(
         messages=[{"role": "user", "content": prompt}],
         max_tokens=150,
         temperature=0,
@@ -93,7 +90,7 @@ User question:
             planner_prompt += f"\nPrevious error:\n{last_error}\nFix the code."
 
         code = ""
-        for chunk in client.chat.completions.create(
+        for chunk in client.chat_completion(
             messages=[{"role": "user", "content": planner_prompt}],
             max_tokens=400,
             temperature=0.2,
@@ -175,7 +172,7 @@ Focus on meaning and implications.
             if show_code:
                 response += f"🧾 Generated Python code:\n\n```python\n{code}\n```\n\n"
 
-            for chunk in client.chat.completions.create(
+            for chunk in client.chat_completion(
                 messages=[{"role": "user", "content": insight_prompt}],
                 max_tokens=350,
                 temperature=0.4,
@@ -209,7 +206,7 @@ Do not generate code.
 """
 
         response = ""
-        for chunk in client.chat.completions.create(
+        for chunk in client.chat_completion(
             messages=[{"role": "user", "content": insight_prompt}],
             max_tokens=400,
             temperature=0.4,