added reading files from GAIA

app.py

@@ -3,7 +3,14 @@ import requests
 import pandas as pd
 import gradio as gr
 from dotenv import load_dotenv
-from smolagents import CodeAgent, DuckDuckGoSearchTool, InferenceClientModel, WikipediaSearchTool
+from smolagents import (
+    CodeAgent,
+    DuckDuckGoSearchTool,
+    InferenceClientModel,
+    WikipediaSearchTool,
+    VisitWebpageTool,
+    Tool,
+)
 
 load_dotenv()
 
@@ -11,8 +18,86 @@ load_dotenv()
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
+# Format instructions appended to every question
+# so that the agent returns exact-match-friendly
+# answers via final_answer().
+ANSWER_FORMAT_INSTRUCTIONS = """
+ 
+IMPORTANT FORMAT INSTRUCTIONS:
+Your final_answer must be as concise as possible:
+- If the answer is a number, return ONLY the number
+  (no units, no commas, no $ or % unless asked).
+- If the answer is a string, return ONLY the
+  essential words (no articles like "the"/"a",
+  no abbreviations for cities, write digits in
+  plain text unless told otherwise).
+- If the answer is a comma separated list, apply
+  the rules above to each element.
+Do NOT include explanations in your final_answer,
+just the bare answer.
+"""
+
+
 # --- Basic Agent Definition ---
 # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+# --------------------------------------------------
+# Custom tool: download a GAIA task file
+# --------------------------------------------------
+class GaiaFileFetcherTool(Tool):
+    """Downloads the file attached to a GAIA task."""
+ 
+    name = "fetch_task_file"
+    description = (
+        "Downloads the file attached to a GAIA task "
+        "given its task_id. Returns the local path "
+        "to the downloaded file so you can read it."
+    )
+    inputs = {
+        "task_id": {
+            "type": "string",
+            "description": (
+                "The task_id of the GAIA question "
+                "whose attached file you need."
+            ),
+        }
+    }
+    output_type = "string"
+ 
+    def __init__(self, api_url: str, **kwargs):
+        super().__init__(**kwargs)
+        self.api_url = api_url
+ 
+    def forward(self, task_id: str) -> str:
+        import requests as _req
+        import tempfile as _tmp
+        import mimetypes as _mt
+ 
+        url = f"{self.api_url}/files/{task_id}"
+        resp = _req.get(url, timeout=30)
+        resp.raise_for_status()
+ 
+        # Derive a sensible extension from headers
+        ct = resp.headers.get("Content-Type", "")
+        ext = _mt.guess_extension(ct.split(";")[0]) or ""
+ 
+        cd = resp.headers.get(
+            "Content-Disposition", ""
+        )
+        fname = ""
+        if "filename=" in cd:
+            fname = cd.split("filename=")[-1]
+            fname = fname.strip('"').strip("'")
+ 
+        if not fname:
+            fname = f"{task_id}{ext}"
+ 
+        path = os.path.join(
+            _tmp.gettempdir(), fname
+        )
+        with open(path, "wb") as f:
+            f.write(resp.content)
+        return path
+    
 class BasicAgent:
     def __init__(self):
         print("BasicAgent initialized.")
@@ -20,28 +105,67 @@ class BasicAgent:
             model_id="Qwen/Qwen2.5-72B-Instruct",
             token=os.getenv("HF_TOKEN"),
         )
+
+        self.file_tool = GaiaFileFetcherTool(
+            api_url=DEFAULT_API_URL,
+        )
+        
         self.agent = CodeAgent(
             model=model,
-            tools=[DuckDuckGoSearchTool(), WikipediaSearchTool(user_agent="BasicAgent/1.0")],
-            max_steps=8,
+            tools=[
+                DuckDuckGoSearchTool(),
+                WikipediaSearchTool(user_agent="GaiaAgent/1.0"),
+                VisitWebpageTool(),
+                self.file_tool,
+            ],
+            max_steps=15,
             verbosity_level=0,
+            additional_authorized_imports=[
+                "json",
+                "re",
+                "csv",
+                "math",
+                "statistics",
+                "datetime",
+                "collections",
+                "itertools",
+                "os",
+            ],
         )
 
-    def __call__(self, question: str) -> str:
-        return str(self.agent.run(question))
+    def __call__(
+        self,
+        question: str,
+        task_id: str,
+        has_file: bool = False,
+    ) -> str:
+        # Build the prompt for the agent
+        prompt = question
+
+        if has_file:
+            prompt += (
+                f"\n\n[This question has an attached "
+                f"file. Use the fetch_task_file tool "
+                f"with task_id='{task_id}' to "
+                f"download and read it.]"
+            )
+
+        prompt += ANSWER_FORMAT_INSTRUCTIONS
+
+        raw = str(self.agent.run(prompt))
+        return raw.strip()
 
-        
 
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+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
+    space_id = os.getenv("SPACE_ID")  # Get the SPACE_ID for sending link to the code
 
     if profile:
-        username= f"{profile.username}"
+        username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -68,16 +192,16 @@ 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
+            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}")
         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
+        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
@@ -94,18 +218,36 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             continue
         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})
+            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 running agent on task {task_id}: {e}")
+            results_log.append(
+                {
+                    "Task ID": task_id,
+                    "Question": question_text,
+                    "Submitted Answer": f"AGENT ERROR: {e}",
+                }
+            )
 
     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}
+    # 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)
 
@@ -175,20 +317,19 @@ with gr.Blocks() as demo:
 
     run_button = gr.Button("Run Evaluation & Submit All Answers")
 
-    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
+    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(
-        fn=run_and_submit_all,
-        outputs=[status_output, results_table]
-    )
+    run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table])
 
 if __name__ == "__main__":
-    print("\n" + "-"*30 + " App Starting " + "-"*30)
+    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")  # Get SPACE_ID at startup
 
     if space_host_startup:
         print(f"✅ SPACE_HOST found: {space_host_startup}")
@@ -196,14 +337,18 @@ if __name__ == "__main__":
     else:
         print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
 
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
+    if space_id_startup:  # Print repo URLs if SPACE_ID is found
         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")
+        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 environment variable not found (running locally?). Repo URL cannot be determined."
+        )
 
-    print("-"*(60 + len(" App Starting ")) + "\n")
+    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)