Update rag.py

rag.py

@@ -112,6 +112,9 @@ class FinancialChatbot:
 
     #     return response
 
+    ValueError: Input length of input_ids is 127, but `max_length` is set to 100. This can lead to unexpected behavior. You should consider increasing `max_length` or, better yet, setting `max_new_tokens`.
+
+    
     def generate_answer(self, context, question):
         prompt = f"""
         You are a financial assistant. If the user greets you (e.g., "Hello," "Hi," "Good morning"), respond politely without requiring context. 
@@ -126,7 +129,8 @@ class FinancialChatbot:
         input_text = prompt
         # f"Context: {context}\nQuestion: {question}\nAnswer:"
         inputs = self.qwen_tokenizer.encode(input_text, return_tensors="pt")
-        outputs = self.qwen_model.generate(inputs, max_length=100)
+        # outputs = self.qwen_model.generate(inputs, max_length=100)
+        outputs = self.qwen_model.generate(inputs, max_new_tokens=50)
         return self.qwen_tokenizer.decode(outputs[0], skip_special_tokens=True)