Add GAIA agent with Groq + smolagents

app.py

@@ -1,34 +1,120 @@
 import os
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
 
-# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+# --- Agent Definition ---
+def build_agent():
+    """Build and return the smolagents CodeAgent with Groq backend."""
+    from smolagents import CodeAgent, LiteLLMModel, DuckDuckGoSearchTool, WikipediaSearchTool, tool
+
+    @tool
+    def download_task_file(task_id: str) -> str:
+        """Download a file associated with a GAIA task and return its local path.
+        Use this when a question mentions or implies there is an attached file.
+
+        Args:
+            task_id: The task ID whose file should be downloaded.
+
+        Returns:
+            The local file path where the file was saved, or an error message.
+        """
+        url = f"{DEFAULT_API_URL}/files/{task_id}"
+        try:
+            resp = requests.get(url, timeout=30)
+            if resp.status_code == 404:
+                return "No file found for this task."
+            resp.raise_for_status()
+
+            # Try to determine file extension from Content-Disposition or Content-Type
+            content_disp = resp.headers.get("content-disposition", "")
+            if "filename=" in content_disp:
+                filename = content_disp.split("filename=")[-1].strip().strip('"')
+            else:
+                ct = resp.headers.get("content-type", "")
+                ext_map = {
+                    "image/png": ".png", "image/jpeg": ".jpg", "image/gif": ".gif",
+                    "application/pdf": ".pdf", "text/plain": ".txt",
+                    "text/csv": ".csv", "application/json": ".json",
+                    "audio/mpeg": ".mp3", "audio/wav": ".wav",
+                    "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet": ".xlsx",
+                }
+                ext = next((v for k, v in ext_map.items() if k in ct), ".bin")
+                filename = f"task_{task_id}{ext}"
+
+            path = f"/tmp/{filename}"
+            with open(path, "wb") as f:
+                f.write(resp.content)
+            return path
+        except Exception as e:
+            return f"Error downloading file: {e}"
+
+    groq_api_key = os.getenv("GROQ_API_KEY")
+    if not groq_api_key:
+        raise ValueError("GROQ_API_KEY environment variable not set. Add it as a Secret in your HF Space settings.")
+
+    model = LiteLLMModel(
+        model_id="groq/llama-3.3-70b-versatile",
+        api_key=groq_api_key,
+        temperature=0.0,
+    )
+
+    agent = CodeAgent(
+        tools=[
+            DuckDuckGoSearchTool(),
+            WikipediaSearchTool(),
+            download_task_file,
+        ],
+        model=model,
+        additional_authorized_imports=[
+            "requests", "json", "re", "math", "datetime",
+            "csv", "io", "os", "pathlib",
+            "PIL", "PIL.Image",
+            "pandas",
+        ],
+        max_steps=10,
+    )
+
+    return agent
+
+
 class BasicAgent:
     def __init__(self):
-        print("BasicAgent initialized.")
+        print("Initializing agent (loading smolagents + Groq)...")
+        self._agent = build_agent()
+        print("Agent ready.")
+
     def __call__(self, question: str) -> str:
-        print(f"Agent received question (first 50 chars): {question[:50]}...")
-        fixed_answer = "This is a default answer."
-        print(f"Agent returning fixed answer: {fixed_answer}")
-        return fixed_answer
+        print(f"Question: {question[:100]}...")
+        system_note = (
+            "You are a precise research assistant. "
+            "Answer the question with ONLY the final answer — no explanation, no 'FINAL ANSWER:' prefix, "
+            "no extra text. If the answer is a number, give only the number. "
+            "If it is a name, give only the name. Be exact."
+        )
+        full_prompt = f"{system_note}\n\nQuestion: {question}"
+        try:
+            result = self._agent.run(full_prompt)
+            answer = str(result).strip()
+            print(f"Answer: {answer[:100]}")
+            return answer
+        except Exception as e:
+            print(f"Agent error: {e}")
+            return f"ERROR: {e}"
+
 
-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")
 
     if profile:
-        username= f"{profile.username}"
+        username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -38,13 +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)
 
@@ -55,21 +141,12 @@ 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
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
@@ -84,19 +161,14 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             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 
+    # 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)
-
-    # 5. Submit
     print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
@@ -110,60 +182,40 @@ 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
+        print(f"Submission Failed: {error_detail}")
+        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
+        print(f"Unexpected error during submission: {e}")
+        return f"An unexpected error occurred during submission: {e}", pd.DataFrame(results_log)
 
 
-# --- Build Gradio Interface using Blocks ---
+# --- Gradio Interface ---
 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.
+        1. Make sure `GROQ_API_KEY` is set as a Secret in your HF Space settings.
+        2. Log in with your Hugging Face account below.
+        3. Click **Run Evaluation & Submit All Answers** — the agent will answer all 20 GAIA questions and submit.
 
         ---
-        **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.
+        *Note: This can take several minutes as the agent processes each question.*
         """
     )
 
     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(
@@ -172,25 +224,20 @@ 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
+    print("\n" + "-" * 30 + " App Starting " + "-" * 30)
     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("-"*(60 + len(" App Starting ")) + "\n")
+        print("ℹ️  SPACE_ID not found (running locally?).")
 
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+    print("-" * (60 + len(" App Starting ")) + "\n")
+    print("Launching Gradio Interface...")
+    demo.launch(debug=True, share=False)

requirements.txt

@@ -1,2 +1,7 @@
 gradio
-requests
+requests
+pandas
+smolagents[litellm]
+duckduckgo-search
+wikipedia-api
+Pillow