Update model_api.py

model_api.py

@@ -1,25 +1,25 @@
 from huggingface_hub import InferenceClient
 import os
+from dotenv import load_dotenv
+
+load_dotenv()
 
 def query_model(prompt):
-    try:
-        HF_TOKEN = os.getenv("HF_TOKEN")
 
-        client = InferenceClient(
-            model="meta-llama/Llama-3.2-3B-Instruct",
-            token=HF_TOKEN
-        )
+    HF_TOKEN = os.getenv("HF_TOKEN")
 
-        response = client.chat_completion(
-            messages=[
-                {"role": "system", "content": "You are a certified professional fitness trainer."},
-                {"role": "user", "content": prompt}
-            ],
-            max_tokens=2000,
-            temperature=0.7
-        )
+    client = InferenceClient(
+        model="meta-llama/Llama-3.2-3B-Instruct",
+        token=HF_TOKEN
+    )
 
-        return response.choices[0].message.content
+    response = client.chat_completion(
+        messages=[
+            {"role": "system", "content": "You are a professional fitness trainer."},
+            {"role": "user", "content": prompt}
+        ],
+        max_tokens=800,
+        temperature=0.7
+    )
 
-    except Exception as e:
-        return f"Error: {str(e)}"
+    return response.choices[0].message.content