Update model_api.py

model_api.py

@@ -2,21 +2,21 @@ from huggingface_hub import InferenceClient
 import os
 
 def query_model(prompt):
-    try:
-        HF_TOKEN = os.getenv("HF_TOKEN")
 
-        client = InferenceClient(
-            model="HuggingFaceH4/zephyr-7b-beta",
-            token=HF_TOKEN
-        )
+    HF_TOKEN = os.getenv("HF_TOKEN")
 
-        response = client.text_generation(
-            prompt,
-            max_new_tokens=1200,
-            temperature=0.7
-        )
+    client = InferenceClient(
+        model="microsoft/Phi-3-mini-4k-instruct",
+        token=HF_TOKEN
+    )
 
-        return response
+    response = client.chat_completion(
+        messages=[
+            {"role": "system", "content": "You are a certified professional fitness trainer."},
+            {"role": "user", "content": prompt}
+        ],
+        max_tokens=1500,
+        temperature=0.7
+    )
 
-    except Exception as e:
-        return f"Error: {str(e)}"
+    return response.choices[0].message.content