Update app.py

app.py

@@ -121,16 +121,30 @@ retriever = db.as_retriever(
 
 
 # Set up the LLM
+# llm = ChatOpenAI(
+#     base_url="https://api-inference.huggingface.co/v1/",
+#     temperature=0,
+#     api_key=HF_TOKEN,
+#     model="mistralai/Mistral-Nemo-Instruct-2407",
+#     max_tokens=None,
+#     timeout=None
+    
+# )
+
+
 llm = ChatOpenAI(
-    base_url="https://api-inference.huggingface.co/v1/",
+    base_url="https://openrouter.ai/api/v1",
     temperature=0,
     api_key=HF_TOKEN,
-    model="mistralai/Mistral-Nemo-Instruct-2407",
+    model="google/gemini-2.0-flash-exp:free",
     max_tokens=None,
     timeout=None
     
 )
 
+
+
+
 # quantization_config = BitsAndBytesConfig(
 #         load_in_4bit=True,
 #         bnb_4bit_compute_dtype=torch.bfloat16,