Update agent

agent.py

@@ -8,9 +8,9 @@ from langgraph.graph.message import add_messages
 from langgraph.prebuilt import ToolNode, tools_condition
 from langchain_openai import ChatOpenAI
 
-from tools import multiply, divide, add, substract
+from tools import multiply, divide, add, substract, wiki_search
 
-available_tools = [multiply, divide, add, substract, DuckDuckGoSearchRun(output_format="list", max_results=5)]
+available_tools = [multiply, divide, add, substract, DuckDuckGoSearchRun(), wiki_search]
 
 with open("system_prompt.txt", "r") as file:
     sys_prompt = SystemMessage(content=file.read())
@@ -18,6 +18,7 @@ with open("system_prompt.txt", "r") as file:
 class AgentState(TypedDict):
     messages: Annotated[list[AnyMessage], add_messages]
     
+    
 chat = ChatOpenAI(model="o4-mini",)
 chat.bind_tools(available_tools)
 

app.py

@@ -1,146 +1,217 @@
 import os
+import re
+import base64
+from enum import Enum
+from pydantic import BaseModel
+from io import BytesIO
+from tempfile import SpooledTemporaryFile
+from typing import Optional
+import logging
 import gradio as gr
 import requests
 import pandas as pd
 from langchain_core.messages import HumanMessage
+from concurrent.futures import ThreadPoolExecutor, as_completed
 
 from agent import gaia_agent
 
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+class ContentType(Enum):
+    IMAGE = "image"
+    PDF = "pdf"
+    AUDIO = "audio"
+    TEXT = "text"
+
 # (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+MAX_WORKERS = 8
+
+class LLMFile(BaseModel):
+    filename: str
+    file: bytes
+    mime: str
+    content_type: ContentType
 
 # --- Basic Agent Definition ---
 # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 class BasicAgent:
     def __init__(self):
         print("BasicAgent initialized.")
-    def __call__(self, question: str) -> str:
+    def __call__(self, question: str, content: Optional[LLMFile]) -> str:
         print(f"Agent received question (first 50 chars): {question[:50]}...")
-        messages = gaia_agent.invoke({"messages": [HumanMessage(content=question)]})
-        answer = messages['messages'][-1].content[14:]
+        
+        message_content = [{"type": "text", "text": question}]
+        
+        if content:
+            if content.content_type == ContentType.AUDIO:
+                media = {
+                    "type": "input_audio",
+                    "input_audio": {"data": base64.b64encode(content.file).encode("ascii"), "format": "wav"}
+                }
+            elif content.content_type == ContentType.IMAGE:
+                media = {
+                    "type": "image",
+                    "image_url": {"url": f"data:image/jpeg;base64,{base64.b64encode(content.file).encode("ascii")}"}
+                }
+            elif content.content_type == ContentType.PDF:
+                media = {
+                    "type": "file",
+                    "file": {
+                        "filename": content.filename,
+                        "file_data": f"data:application/pdf;base64,{base64.b64encode(content.file).encode("ascii")}",
+                    }
+                }
+                
+            message_content.append(media)
+        
+        messages = gaia_agent.invoke({"messages": [
+            HumanMessage(content=message_content)
+        ]})
+        message = messages['messages'][-1].content
+        
+        match = re.search(r'FINAL ANSWER:\s*(.*)', message)
+        if match:
+            answer = match.group(1)
+        else:
+            answer = "ERROR"
+            
         print(f"Agent returning answer: {answer}")
         return answer
 
-def run_and_submit_all( profile: gr.OAuthProfile | None):
-    """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
-    """
-    # --- Determine HF Space Runtime URL and Repo URL ---
-    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
-
-    if profile:
-        username= f"{profile.username}"
-        print(f"User logged in: {username}")
-    else:
-        print("User not logged in.")
+
+def run_and_submit_all(profile: Optional[gr.OAuthProfile]):
+    if not profile:
+        logger.warning("User not logged in.")
         return "Please Login to Hugging Face with the button.", None
 
-    api_url = DEFAULT_API_URL
-    questions_url = f"{api_url}/questions"
-    submit_url = f"{api_url}/submit"
+    username = profile.username.strip()
+    logger.info(f"User logged in: {username}")
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
-    try:
-        agent = BasicAgent()
-    except Exception as e:
-        print(f"Error instantiating agent: {e}")
-        return f"Error initializing agent: {e}", None
-    # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public)
+    session = requests.Session()
+    space_id = os.getenv("SPACE_ID")
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(agent_code)
 
-    # 2. Fetch Questions
-    print(f"Fetching questions from: {questions_url}")
+    # --- Fetch questions ---
+    questions_url = f"{DEFAULT_API_URL}/questions"
     try:
-        response = requests.get(questions_url, timeout=15)
+        response = session.get(questions_url, timeout=15)
         response.raise_for_status()
         questions_data = response.json()
         if not questions_data:
-             print("Fetched questions list is empty.")
-             return "Fetched questions list is empty or invalid format.", None
-        print(f"Fetched {len(questions_data)} questions.")
-    except requests.exceptions.RequestException as e:
-        print(f"Error fetching questions: {e}")
+            raise ValueError("Fetched questions list is empty or invalid.")
+        logger.info(f"Fetched {len(questions_data)} questions.")
+    except Exception as e:
+        logger.exception("Error fetching questions.")
         return f"Error fetching questions: {e}", None
-    except requests.exceptions.JSONDecodeError as e:
-         print(f"Error decoding JSON response from questions endpoint: {e}")
-         print(f"Response text: {response.text[:500]}")
-         return f"Error decoding server response for questions: {e}", None
+
+
+    # --- Instantiate agent ---
+    try:
+        agent = BasicAgent()
     except Exception as e:
-        print(f"An unexpected error occurred fetching questions: {e}")
-        return f"An unexpected error occurred fetching questions: {e}", None
+        logger.exception("Error initializing agent.")
+        return f"Error initializing agent: {e}", None
 
-    # 3. Run your Agent
-    results_log = []
-    answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
-    for item in questions_data:
+    # --- Run agent in parallel ---
+    def process_question(item):
         task_id = item.get("task_id")
-        question_text = item.get("question")
-        if not task_id or question_text is None:
-            print(f"Skipping item with missing task_id or question: {item}")
-            continue
+        question = item.get("question")
+        if not task_id or question is None:
+            return None, {"Task ID": task_id, "Question": question, "Submitted Answer": "INVALID QUESTION FORMAT"}
+        
+        if item.get("filename", None):
+            # --- Fetch file ---
+            file_url = f"{DEFAULT_API_URL}/files/{task_id}"
+            try:
+                response = session.get(file_url, timeout=15)
+                response.raise_for_status()
+                
+                content_disposition = response.headers.get("content-disposition", "")
+                filename = task_id + ".bin"
+                if "filename=" in content_disposition:
+                    filename = content_disposition.split("filename=")[-1].strip('"')
+                    
+                mime = response.headers.get("content-type", "")
+                
+                if mime.startswith("audio/"):
+                    media = LLMFile(filename=filename, mime=mime, content_type=ContentType.AUDIO, file=response.content)
+                elif mime.startswith("image/"):
+                    media = LLMFile(filename=filename, mime=mime, content_type=ContentType.IMAGE, file=response.content)
+                elif mime.startswith("image/"):
+                    media = LLMFile(filename=filename, mime=mime, content_type=ContentType.IMAGE, file=response.content)
+                elif mime.startswith("text/"):
+                    media = LLMFile(filename=filename, mime=mime, content_type=ContentType.TEXT, file=response.content)
+
+            except Exception as e:
+                logger.exception("Error fetching file for task id %s.", str(task_id))
+                return f"Error fetching file for task id ({task_id}): {e}", None
+        
+        
         try:
-            submitted_answer = agent(question_text)
-            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})
+            answer = agent(question, media if item.get("filename", None) else None)
+            return {"task_id": task_id, "submitted_answer": answer}, {
+                "Task ID": task_id, "Question": question, "Submitted Answer": answer
+            }
         except Exception as e:
-             print(f"Error running agent on task {task_id}: {e}")
-             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
+            logger.warning(f"Agent error on task {task_id}: {e}")
+            return None, {
+                "Task ID": task_id, "Question": question, "Submitted Answer": f"AGENT ERROR: {e}"
+            }
+
+    answers_payload = []
+    results_log = []
+
+    with ThreadPoolExecutor(max_workers=MAX_WORKERS) as executor:
+        futures = [executor.submit(process_question, item) for item in questions_data]
+        for future in as_completed(futures):
+            answer, log = future.result()
+            if answer:
+                answers_payload.append(answer)
+            results_log.append(log)
 
     if not answers_payload:
-        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 
-    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)
+    # --- Submit answers ---
+    submit_url = f"{DEFAULT_API_URL}/submit"
+    submission_data = {
+        "username": username,
+        "agent_code": agent_code,
+        "answers": answers_payload,
+    }
 
-    # 5. Submit
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
+    logger.info(f"Submitting {len(answers_payload)} answers to: {submit_url}")
     try:
-        response = requests.post(submit_url, json=submission_data, timeout=60)
+        response = session.post(submit_url, json=submission_data, timeout=60)
         response.raise_for_status()
-        result_data = response.json()
+        result = response.json()
         final_status = (
             f"Submission Successful!\n"
-            f"User: {result_data.get('username')}\n"
-            f"Overall Score: {result_data.get('score', 'N/A')}% "
-            f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
-            f"Message: {result_data.get('message', 'No message received.')}"
+            f"User: {result.get('username')}\n"
+            f"Overall Score: {result.get('score', 'N/A')}% "
+            f"({result.get('correct_count', '?')}/{result.get('total_attempted', '?')} correct)\n"
+            f"Message: {result.get('message', 'No message received.')}"
         )
-        print("Submission successful.")
-        results_df = pd.DataFrame(results_log)
-        return final_status, results_df
+        return final_status, pd.DataFrame(results_log)
+
     except requests.exceptions.HTTPError as e:
-        error_detail = f"Server responded with status {e.response.status_code}."
         try:
-            error_json = e.response.json()
-            error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
-        except requests.exceptions.JSONDecodeError:
-            error_detail += f" Response: {e.response.text[:500]}"
+            error_detail = e.response.json().get("detail", e.response.text)
+        except Exception:
+            error_detail = e.response.text[:500]
         status_message = f"Submission Failed: {error_detail}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
     except requests.exceptions.Timeout:
         status_message = "Submission Failed: The request timed out."
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
     except requests.exceptions.RequestException as e:
         status_message = f"Submission Failed: Network error - {e}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
     except Exception as e:
-        status_message = f"An unexpected error occurred during submission: {e}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
+        status_message = f"Unexpected error during submission: {e}"
+
+    logger.error(status_message)
+    return status_message, pd.DataFrame(results_log)
 
 
 # --- Build Gradio Interface using Blocks ---

pyproject.toml

@@ -14,4 +14,5 @@ dependencies = [
     "pandas>=2.3.0",
     "gradio[oauth]>=5.35.0",
     "duckduckgo-search>=8.0.4",
+    "wikipedia>=1.4.0",
 ]

tools.py

@@ -1,4 +1,6 @@
 from langchain.tools import tool
+from langchain_community.document_loaders import WikipediaLoader
+
 
 @tool
 def multiply(a: float, b: float) -> float:
@@ -43,4 +45,19 @@ def divide(a: float, b: float) -> float:
     :return: Le résultat de la division de a par b.
     :raises ZeroDivisionError: Si b est égal à zéro.
     """
-    return a / b
+    return a / b
+
+
+@tool
+def wiki_search(query: str) -> str:
+    """Search Wikipedia for a query and return maximum 2 results.
+    
+    Args:
+        query: The search query."""
+    search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
+    formatted_search_docs = "\n\n---\n\n".join(
+        [
+            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
+            for doc in search_docs
+        ])
+    return {"wiki_results": formatted_search_docs}

uv.lock

@@ -170,6 +170,19 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/84/29/587c189bbab1ccc8c86a03a5d0e13873df916380ef1be461ebe6acebf48d/authlib-1.6.0-py2.py3-none-any.whl", hash = "sha256:91685589498f79e8655e8a8947431ad6288831d643f11c55c2143ffcc738048d", size = 239981 },
 ]
 
+[[package]]
+name = "beautifulsoup4"
+version = "4.13.4"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "soupsieve" },
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/d8/e4/0c4c39e18fd76d6a628d4dd8da40543d136ce2d1752bd6eeeab0791f4d6b/beautifulsoup4-4.13.4.tar.gz", hash = "sha256:dbb3c4e1ceae6aefebdaf2423247260cd062430a410e38c66f2baa50a8437195", size = 621067 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/50/cd/30110dc0ffcf3b131156077b90e9f60ed75711223f306da4db08eff8403b/beautifulsoup4-4.13.4-py3-none-any.whl", hash = "sha256:9bbbb14bfde9d79f38b8cd5f8c7c85f4b8f2523190ebed90e950a8dea4cb1c4b", size = 187285 },
+]
+
 [[package]]
 name = "certifi"
 version = "2025.6.15"
@@ -385,6 +398,7 @@ dependencies = [
     { name = "langgraph" },
     { name = "pandas" },
     { name = "scrapingant-client" },
+    { name = "wikipedia" },
 ]
 
 [package.metadata]
@@ -398,6 +412,7 @@ requires-dist = [
     { name = "langgraph", specifier = ">=0.5.0" },
     { name = "pandas", specifier = ">=2.3.0" },
     { name = "scrapingant-client", specifier = ">=2.1.0" },
+    { name = "wikipedia", specifier = ">=1.4.0" },
 ]
 
 [[package]]
@@ -1725,6 +1740,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/e9/44/75a9c9421471a6c4805dbf2356f7c181a29c1879239abab1ea2cc8f38b40/sniffio-1.3.1-py3-none-any.whl", hash = "sha256:2f6da418d1f1e0fddd844478f41680e794e6051915791a034ff65e5f100525a2", size = 10235 },
 ]
 
+[[package]]
+name = "soupsieve"
+version = "2.7"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/3f/f4/4a80cd6ef364b2e8b65b15816a843c0980f7a5a2b4dc701fc574952aa19f/soupsieve-2.7.tar.gz", hash = "sha256:ad282f9b6926286d2ead4750552c8a6142bc4c783fd66b0293547c8fe6ae126a", size = 103418 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/e7/9c/0e6afc12c269578be5c0c1c9f4b49a8d32770a080260c333ac04cc1c832d/soupsieve-2.7-py3-none-any.whl", hash = "sha256:6e60cc5c1ffaf1cebcc12e8188320b72071e922c2e897f737cadce79ad5d30c4", size = 36677 },
+]
+
 [[package]]
 name = "sqlalchemy"
 version = "2.0.41"
@@ -1956,6 +1980,16 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/fa/a8/5b41e0da817d64113292ab1f8247140aac61cbf6cfd085d6a0fa77f4984f/websockets-15.0.1-py3-none-any.whl", hash = "sha256:f7a866fbc1e97b5c617ee4116daaa09b722101d4a3c170c787450ba409f9736f", size = 169743 },
 ]
 
+[[package]]
+name = "wikipedia"
+version = "1.4.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "beautifulsoup4" },
+    { name = "requests" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/67/35/25e68fbc99e672127cc6fbb14b8ec1ba3dfef035bf1e4c90f78f24a80b7d/wikipedia-1.4.0.tar.gz", hash = "sha256:db0fad1829fdd441b1852306e9856398204dc0786d2996dd2e0c8bb8e26133b2", size = 27748 }
+
 [[package]]
 name = "xxhash"
 version = "3.5.0"