Update src/generation/llm.py

src/generation/llm.py

@@ -99,8 +99,12 @@ class LLM:
             )
             # Decode the generated tokens
             response = self.tokenizer.decode(outputs[0], skip_special_tokens=True)
+            response = response.strip()
+            keyword = "assistant"
+            index = response.find(keyword)
+            output = response[index + len(keyword):].strip() if index != -1 else response
             print("Response generated successfully!")
-            return response.strip()
+            return output
         except Exception as e:
             raise RuntimeError(f"Failed to generate response: {str(e)}")