Update app.py

app.py

@@ -1,48 +1,120 @@
-
 import os
+import time
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
-from smolagents import CodeAgent, DuckDuckGoSearchTool,PythonInterpreterTool,OpenAIServerModel , LiteLLMModel
-from langchain_openai import ChatOpenAI
-from dotenv import load_dotenv
-load_dotenv()
-import litellm
-litellm._turn_on_debug()
-# (Keep Constants as is)
+from smolagents import ToolCallingAgent, OpenAIServerModel, DuckDuckGoSearchTool, PythonInterpreterTool, Tool
+
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+# --- Custom Tools ---
+
+class WikipediaTool(Tool):
+    name = "wikipedia_search"
+    description = "Search Wikipedia and get article text. Use this when the question mentions Wikipedia or needs encyclopedic facts."
+    inputs = {"query": {"type": "string", "description": "The topic to search on Wikipedia"}}
+    output_type = "string"
+
+    def forward(self, query: str) -> str:
+        try:
+            search_url = (
+                f"https://en.wikipedia.org/w/api.php"
+                f"?action=query&titles={query.replace(' ', '_')}"
+                f"&prop=extracts&explaintext=true&format=json"
+            )
+            r = requests.get(search_url, timeout=10)
+            pages = r.json()["query"]["pages"]
+            page = next(iter(pages.values()))
+            text = page.get("extract", "No content found")
+            return text[:4000]
+        except Exception as e:
+            return f"Wikipedia error: {e}"
+
+
+class YouTubeTranscriptTool(Tool):
+    name = "youtube_transcript"
+    description = "Gets the transcript of a YouTube video. Use when the question contains a YouTube URL or asks about video content."
+    inputs = {"url": {"type": "string", "description": "YouTube video URL or video ID"}}
+    output_type = "string"
+
+    def forward(self, url: str) -> str:
+        try:
+            from youtube_transcript_api import YouTubeTranscriptApi
+            if "v=" in url:
+                video_id = url.split("v=")[1].split("&")[0]
+            elif "youtu.be/" in url:
+                video_id = url.split("youtu.be/")[1].split("?")[0]
+            else:
+                video_id = url.strip()
+            transcript = YouTubeTranscriptApi.get_transcript(video_id)
+            return " ".join([t["text"] for t in transcript])[:4000]
+        except Exception as e:
+            return f"Transcript error: {e}"
+
+
+class FileDownloadTool(Tool):
+    name = "download_file"
+    description = "Downloads a file attached to a GAIA question using its task_id. Use when the question references an attached file, image, CSV, or PDF."
+    inputs = {"task_id": {"type": "string", "description": "The task_id of the current question"}}
+    output_type = "string"
+
+    def forward(self, task_id: str) -> str:
+        try:
+            url = f"https://agents-course-unit4-scoring.hf.space/files/{task_id}"
+            r = requests.get(url, timeout=15)
+            if r.status_code == 200:
+                return r.text[:4000]
+            return f"No file found for task_id {task_id}"
+        except Exception as e:
+            return f"File download error: {e}"
+
+
+# --- Agent ---
+
 class BasicAgent:
     def __init__(self):
-        model =OpenAIServerModel(
+        model = OpenAIServerModel(
             model_id="llama-3.3-70b-versatile",
             api_base="https://api.groq.com/openai/v1",
             api_key=os.getenv("GROQ_API_KEY")
         )
-        self.agent = CodeAgent(
+        self.agent = ToolCallingAgent(
             model=model,
-            tools=[DuckDuckGoSearchTool(), PythonInterpreterTool()],
-            verbosity_level=1
+            tools=[
+                DuckDuckGoSearchTool(),
+                PythonInterpreterTool(),
+                WikipediaTool(),
+                YouTubeTranscriptTool(),
+                FileDownloadTool(),
+            ],
+            max_steps=4,
         )
 
-    def __call__(self, question: str) -> str:
-        return self.agent.run(question)
+    def __call__(self, question: str, task_id: str = "") -> str:
+        try:
+            prompt = f"""Answer the following question accurately.
+Return ONLY the final answer — no explanation, no punctuation, no extra words.
+If the answer is a number, return just the number.
+If the answer is a name, return just the name.
+If the answer is a list, return comma separated values.
+Task ID (use this with download_file tool if the question references a file): {task_id}
+
+Question: {question}"""
+            result = self.agent.run(prompt)
+            return str(result)
+        except Exception as e:
+            print(f"Agent error: {e}")
+            return "I don't know"
+
 
+# --- Main Evaluation Function ---
 
-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
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    space_id = os.getenv("SPACE_ID")
 
     if profile:
-        username= f"{profile.username}"
+        username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -52,13 +124,13 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
+    # 1. Instantiate 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)
+
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
     print(agent_code)
 
@@ -69,49 +141,48 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         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
+            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}")
-        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
     except Exception as e:
-        print(f"An unexpected error occurred fetching questions: {e}")
-        return f"An unexpected error occurred fetching questions: {e}", None
+        return f"Error fetching questions: {e}", None
 
-    # 3. Run your Agent
+    # 3. Run Agent on each question
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
-    for item in questions_data:
+
+    for i, item in enumerate(questions_data):
         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
+
+        print(f"\n[{i+1}/{len(questions_data)}] Task: {task_id}")
+        print(f"Question: {question_text[:100]}...")
+
         try:
-            submitted_answer = agent(question_text)
+            submitted_answer = agent(question_text, task_id)
+            print(f"Answer: {submitted_answer}")
             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:
-             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}"})
+            print(f"Error on task {task_id}: {e}")
+            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
+
+        # Rate limit protection — Groq free tier is 6000 tokens/min
+        if i < len(questions_data) - 1:
+            print("Waiting 12s to respect rate limits...")
+            time.sleep(12)
 
     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 
+    # 4. Submit
     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)
+    print(f"\nSubmitting {len(answers_payload)} answers...")
 
-    # 5. Submit
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
         response.raise_for_status()
@@ -124,60 +195,35 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             f"Message: {result_data.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:
+        except Exception:
             error_detail += f" Response: {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
+        return f"Submission Failed: {error_detail}", pd.DataFrame(results_log)
     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
+        return f"Submission error: {e}", pd.DataFrame(results_log)
+
 
+# --- Gradio UI ---
 
-# --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown("# GAIA Agent Evaluation Runner")
     gr.Markdown(
         """
         **Instructions:**
-
-        1.  Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...
-        2.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
-        3.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
-
-        ---
-        **Disclaimers:**
-        Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
-        This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
+        1. Log in to your Hugging Face account using the button below.
+        2. Click 'Run Evaluation & Submit All Answers' to start.
+        3. The agent will answer all 20 questions and submit. Takes ~5 minutes due to rate limits.
         """
     )
 
     gr.LoginButton()
-
     run_button = gr.Button("Run Evaluation & Submit All Answers")
-
     status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
-    # Removed max_rows=10 from DataFrame constructor
     results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
 
     run_button.click(
@@ -187,24 +233,20 @@ with gr.Blocks() as demo:
 
 if __name__ == "__main__":
     print("\n" + "-"*30 + " App Starting " + "-"*30)
-    # Check for SPACE_HOST and SPACE_ID at startup for information
+
     space_host_startup = os.getenv("SPACE_HOST")
-    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
+    space_id_startup = os.getenv("SPACE_ID")
 
     if space_host_startup:
         print(f"✅ SPACE_HOST found: {space_host_startup}")
-        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
     else:
-        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
+        print("ℹ️  SPACE_HOST not found (running locally).")
 
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
+    if space_id_startup:
         print(f"✅ SPACE_ID found: {space_id_startup}")
-        print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
-        print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
     else:
-        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
+        print("ℹ️  SPACE_ID not found (running locally).")
 
     print("-"*(60 + len(" App Starting ")) + "\n")
-
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
+    print("Launching Gradio Interface...")
     demo.launch(debug=True, share=False)