added tools to the agent, and new requirements

.gitignore

@@ -0,0 +1,4 @@
+.env
+.venv
+.ropeproject
+__pycache__

app.py

@@ -4,6 +4,7 @@ import requests
 import inspect
 import pandas as pd
 from llm_only_agent import LLMOnlyAgent
+import profile
 
 # (Keep Constants as is)
 # --- Constants ---
@@ -74,8 +75,9 @@ def run_and_submit_all( profile: gr.OAuthProfile | None, limit: int | None):
     results_log = []
     answers_payload = []
     # Limit for test purposes
+    limit = None
     if limit is not None:
-        question_data = question_data[:limit]
+        questions_data = questions_data[:limit]
     print(f"Running agent on {len(questions_data)} questions...")
     for item in questions_data:
         task_id = item.get("task_id")
@@ -95,7 +97,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None, limit: int | None):
         print("Agent did not produce any answers to submit.")
         return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
 
-    # 4. Prepare Submission 
+    # 4. Prepare Submission
     submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
     status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
     print(status_update)
@@ -171,7 +173,7 @@ with gr.Blocks() as demo:
     results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
 
     run_button.click(
-        fn=run_and_submit_all(limit=3),
+        fn=run_and_submit_all,
         outputs=[status_output, results_table]
     )
 
@@ -197,4 +199,4 @@ 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(debug=True, share=False)

llm_only_agent.py

@@ -1,10 +1,22 @@
-from smolagents import CodeAgent, HfApiModel, FinalAnswerTool
+import re
+from smolagents import AgentMemory, CodeAgent, InferenceClientModel, FinalAnswerTool, WebSearchTool
+from collections.abc import Callable
+
+from smolagents.default_tools import VisitWebpageTool, WikipediaSearchTool
 
 class LLMOnlyAgent:
     def __init__(self):
 
-    # Basic inference model
-        model = HfApiModel(
+        # Instructions prompt
+        self.instructions = """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."""
+
+
+        # Basic inference model
+        model = InferenceClientModel(
         max_tokens=2096,
         temperature=0.5,
         model_id='Qwen/Qwen2.5-Coder-32B-Instruct',# it is possible that this model may be overloaded
@@ -14,22 +26,25 @@ class LLMOnlyAgent:
         # Code Agent
         self.agent = CodeAgent(
             model=model,
-            system_prompt=self.system_prompt,
-            tools=[FinalAnswerTool()],
-            max_steps=2
+            instructions=self.instructions,
+            tools=[FinalAnswerTool(), WikipediaSearchTool(), WebSearchTool(), VisitWebpageTool()],
+            additional_authorized_imports=[ "markdownify" , "requests" ],
+            max_steps=10
+            # final_answer_checks=self.final_answer_checks()
         )
-        
+
         print("BasicAgent initialized.")
+
     def __call__(self, question: str) -> str:
         print(f"Agent received question (first 50 chars): {question[:50]}...")
         answer = self.agent.run(question)
         print(f"Agent returning answer: {answer}")
         return answer
 
-    def system_prompt: str
-        """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, 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."""
+    def final_answer_checks(self) -> list[Callable] :
+        return [ self.check_func ]
+
+    def check_func(self, answer: str, memory: AgentMemory) -> bool:
+        check = bool(re.match(r'^(\d+(\.\d+)?|\w+(\s+\w+){0,4}|(\d+(\.\d+)?|"[^"]*"|\w+)(\s*,\s*(\d+(\.\d+)?|"[^"]*"|\w+))+)$', answer))
+        print(f"FINAL ANSWER CHECK is {check}")
+        return check

requirements.txt

@@ -1,3 +1,8 @@
 gradio
 requests
-smolagents
+smolagents
+gradio[oauth]
+huggingface_hub[cli]
+wikipedia-api
+markdownify
+requests