Update model

agent.py

@@ -2,7 +2,9 @@ import base64
 import os
 import re
 import tempfile
+import time
 from pathlib import Path
+from time import sleep
 from typing import TypedDict, Annotated, Optional
 import pandas as pd
 import requests
@@ -18,6 +20,7 @@ from langgraph.prebuilt import tools_condition
 from mediawikiapi import MediaWikiAPI
 from wikipedia_tool import WikipediaTool
 from yt_tool import speech_recognition_pipe, yt_transcribe
+from calculus_tools import add, substract, multiple, divide
 
 
 @tool
@@ -41,39 +44,11 @@ def read_xlsx_file(file_path: str) -> str:
     except Exception as e:
         return f"Error analyzing CSV file: {str(e)}"
 
-@tool
-def addition(a: int, b: int) -> int:
-    """
-        Add two int numbers.
-
-        Args:
-            a: int
-            b int
-
-        Returns:
-            a + b
-        """
-    return a + b
-
-@tool
-def multiple(a: int, b: int) -> float:
-    """
-        Multiple two float numbers.
-
-        Args:
-            a: int
-            b int
-
-        Returns:
-            a * b
-        """
-    return a * b
-
 class Agent:
     def __init__(self):
 
         llm = ChatGoogleGenerativeAI(
-            model="gemini-2.5-flash-preview-04-17",
+            model="gemini-2.5-flash-preview-05-20",
             # model="gemini-2.0-flash",
             # model="gemini-1.5-pro",
             temperature=0
@@ -83,8 +58,10 @@ class Agent:
             WikipediaTool(api_wrapper=WikipediaAPIWrapper(wiki_client=MediaWikiAPI())),
             TavilySearch(),
             read_xlsx_file,
-            addition,
+            add,
+            substract,
             multiple,
+            divide,
             yt_transcribe
         ]
 
@@ -256,11 +233,17 @@ class Agent:
         return builder.compile()
 
     def run(self, question: str, task_id: str, file_name: str | None):
-        system_prompt = SystemMessage(content="You are a general AI assistant. I will ask you a question. Report your thoughts, and finish your answer with the following template: FINAL ANSWER: [YOUR FINAL ANSWER]. YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, use digit not letter, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.")
+        system_prompt = SystemMessage(content="""
+        You are a general AI assistant. I will ask you a question. Report your thoughts, and finish your answer with the following template: FINAL ANSWER: [YOUR FINAL ANSWER]. YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, use digit not letter, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.
+        
+        If you are asked a list of items separated by coma, add a space after each coma.
+        
+        If you are asked a list in alphabetical order, it is the first word of each item that matters.
+        """)
 
         messages = [system_prompt, HumanMessage(content=question)]
 
-        response = self.graph.invoke({"messages": messages, "task_id": task_id, "file_name": file_name}, debug=True)
+        response = self.graph.invoke({"messages": messages, "task_id": task_id, "file_name": file_name})
 
         answer = response['messages'][-1].content
 

app.py

@@ -93,6 +93,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
     for item in questions_data:
+        time.sleep(60)
         task_id = item.get("task_id")
         question_text = item.get("question")
         file_name = item.get("file_name")
@@ -215,4 +216,4 @@ if __name__ == "__main__":
     print("-"*(60 + len(" App Starting ")) + "\n")
 
     print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+    demo.launch(share=False)