update prompt and tools

agent.py

@@ -2,6 +2,8 @@ import os
 from dotenv import load_dotenv
 import pandas as pd
 import json
+import base64
+
 from langgraph.graph import START, StateGraph, MessagesState
 from langgraph.prebuilt import tools_condition
 from langgraph.prebuilt import ToolNode
@@ -42,6 +44,32 @@ tavily_search_tool = TavilySearch(
 # Initialize Tavily Extract Tool
 tavily_extract_tool = TavilyExtract()
 
+@tool
+def describe_image(file_name: str) -> str:
+  """Describe the image.
+
+  Args:
+    file_name: name of image file
+  """
+  with open(file_name, "rb") as image_file:
+      encoded_image = base64.b64encode(image_file.read()).decode("utf-8")
+  message_local = HumanMessage(
+      content=[
+          {"type": "text", "text": "Describe the local image."},
+          {"type": "image_url", "image_url": f"data:image/png;base64,{encoded_image}"},
+      ]
+  )
+  llm = ChatGoogleGenerativeAI(
+    model="gemini-2.0-flash",
+    temperature=0.1,
+    max_tokens=None,
+    timeout=None,
+    max_retries=2,
+    # other params...
+  )
+  result_local = llm.invoke([message_local])
+  return "Response for local image: {result_local.content}"
+
 
 @tool
 def read_excel_file(file_name: str) -> str:
@@ -96,7 +124,7 @@ def wiki_search(query: str) -> str:
     return {"wiki_results": formatted_search_docs}
 
 @tool
-def solve_logic_or_math_problem(problem: str) -> str:
+def solve_math_problem(problem: str) -> str:
     """Solve logic or math problem.
     
     Args:
@@ -132,6 +160,7 @@ def solve_logic_or_math_problem(problem: str) -> str:
     
 system_prompt = """
 You are a helpful assistant tasked with answering questions using a set of tools. 
+If the question is related to math or logic or a puzzle, ALWAYS USE a tool and NOT trying to answer by yourself.
 Now, 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, 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.
@@ -141,13 +170,15 @@ sys_msg = SystemMessage(content=system_prompt)
 
 
 tools = [
+    solve_math_problem,
     wiki_search,
+    describe_image,
     tavily_search_tool,
     tavily_extract_tool,
     repl_tool,
     read_excel_file,
     transcribe_audio,
-    solve_logic_or_math_problem
+    
 ]
 
 

app.py

@@ -79,11 +79,12 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     for item in questions_data:
         task_id = item.get("task_id")
         question_text = item.get("question")
+        file_name = item.get("file_name")
         if not task_id or question_text is None:
             print(f"Skipping item with missing task_id or question: {item}")
             continue
         try:
-            submitted_answer = agent(question_text)
+            submitted_answer = agent(question_text + f"(file_name: '{file_name}')" if len(file_name)>0 else "")
             answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
         except Exception as e: