Update app.py

app.py

@@ -70,19 +70,24 @@ def format_docs(docs: List[Document]) -> str:
 
 # =================== Generate Response from Hugging Face Model ===================
 def generate_response(input_dict: Dict[str, Any]) -> str:
-    client = InferenceClient(api_key=HF_TOKEN)
+    client = InferenceClient(api_key=HF_TOKEN.strip())
     prompt = grantbuddy_prompt.format(**input_dict)
 
-    response = client.chat.completions.create(
-        model="Qwen/Qwen2.5-1.5B-Instruct",
-        messages=[
-            {"role": "system", "content": prompt},
-            {"role": "user", "content": input_dict["question"]},
-        ],
-        max_tokens=1000,
-        temperature=0.2,
-    )
-    return response.choices[0].message.content
+    try:
+        response = client.chat.completions.create(
+            model="Qwen/Qwen2.5-1.5B-Instruct",
+            messages=[
+                {"role": "system", "content": prompt},
+                {"role": "user", "content": input_dict["question"]},
+            ],
+            max_tokens=1000,
+            temperature=0.2,
+        )
+        return response.choices[0].message.content
+    except Exception as e:
+        st.error(f"❌ Error from model: {e}")
+        return "⚠️ Failed to generate response. Please check your model, HF token, or request format."
+
 
 # =================== RAG Chain ===================
 def get_rag_chain(retriever):