Update app.py

app.py

@@ -1,222 +1,257 @@
+import base64
 import os
-import gradio as gr
+import io
+import contextlib
 import requests
-import inspect
-import pandas as pd
-
-import spaces
-from agent import graph
-from langchain_core.messages import HumanMessage, SystemMessage
-
-# (Keep Constants as is)
-# --- Constants ---
-DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
-
-# --- ZeroGPU Bypass ---
-# This dummy function tricks the Space into thinking we are using the GPU, preventing crashes.
-@spaces.GPU(duration=1)
-def gpu_check():
-    return "GPU available"
-
-# --- 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:
-        response = graph.invoke({
-            "messages": [SystemMessage(content = """
-            You are a helpful assistant tasked with answering questions using a set of tools.
-Now, I will ask you a question. Report your thoughts, and answer in the fewest words possible.
-If the answer is only one word, format it as such, no extra punctuation.
-If your answer is a list, use a comma delimited list. Ex "cornstarch, freshly squeezed lemon juice, granulated sugar" or "Myanmar, Indonesia"
-If your answer is a number, only respond with the number, nothing else.
-DO NOT USE SQUARE BRACKETS IN YOUR ANSWERS UNLESS DIRECTLY STATED.
-DO NOT START YOUR ANSWER WITH "YOUR FINAL ANSWER".
-YOUR ANSWER SHOULD ONLY BE THE ANSWER AND NOTHING ELSE.
-    """), HumanMessage(content=question)],
-            "file_path": None,
-            "url": None,
-            "task_id": None
-        })
-        answer = response["messages"][-1].text
-        return answer
-
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+from typing import TypedDict, Annotated
+from langchain_core.messages import HumanMessage, AnyMessage
+from langgraph.graph import START, StateGraph, add_messages
+from langgraph.prebuilt import ToolNode, tools_condition
+from langchain_community.tools import tool, DuckDuckGoSearchRun
+from langchain_community.document_loaders import WikipediaLoader
+from langchain_google_genai import ChatGoogleGenerativeAI
+from pathlib import Path
+import tempfile
+from dotenv import load_dotenv
+
+# constants
+API_URL = "https://agents-course-unit4-scoring.hf.space"
+QUESTIONS_URL = f"{API_URL}/questions"
+FILES_URL = f"{API_URL}/files"
+SUBMIT_URL = f"{API_URL}/submit"
+load_dotenv()
+
+class AgentState(TypedDict):
+    messages: Annotated[list[AnyMessage], add_messages]
+    file_path: str | None
+    task_id: str | None
+    url: str | None
+
+def build_gemini_llm():
+    if not os.environ.get("GOOGLE_API_KEY"):
+        raise ValueError("GOOGLE_API_KEY environment variable is not set.")
+    return ChatGoogleGenerativeAI(model = "gemini-3.7-flash", temperature = 0, max_output_tokens = 1025, include_thoughts=True)
+
+@tool
+def add_numbers(a: int, b: int) -> int:
     """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
+    Adds two numbers and return the result.
+    Args:
+        a (int)
+        b (int)
     """
-    # --- Determine HF Space Runtime URL and Repo URL ---
-    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
+    return a + b
 
-    if profile:
-        username= f"{profile.username}"
-        print(f"User logged in: {username}")
-    else:
-        print("User not logged in.")
-        return "Please Login to Hugging Face with the button.", None
+@tool
+def subtract_numbers(a: int, b: int) -> int:
+    """
+    Subtracts the second number from the first and return the result.
+    Args:
+        a (int)
+        b (int)
+    """
+    return a - b
 
-    api_url = DEFAULT_API_URL
-    questions_url = f"{api_url}/questions"
-    submit_url = f"{api_url}/submit"
+@tool
+def multiply_numbers(a: int, b: int) -> int:
+    """
+    Multiplies two numbers and return the result.
+    Args:
+        a (int)
+        b (int)
+    """
+    return a * b
 
-    # 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)
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(agent_code)
-
-    # 2. Fetch Questions
-    print(f"Fetching questions from: {questions_url}")
+@tool
+def divide_numbers(a: int, b: int) -> float:
+    """
+    Divides the first number by the second and return the result.
+    Args:
+        a (int)
+        b (int)
+    """
+    return a / b
+
+@tool
+def search_web(query:str) -> str:
+        """
+        Searches the web for the answer to a given question or topic.
+        Args:
+            query (str): the question or topic to search for.
+        """
+        return DuckDuckGoSearchRun().run(query)
+
+@tool
+def extract_text_from_image(img_path: str) -> str:
+    """
+    Describe the image and extract any text in it.
+    Args:
+        img_path (str): the path to the image file.
+    """
+    all_text = ""
     try:
-        response = requests.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}")
-        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
+        # Read image and encode as base64
+        with open(img_path, "rb") as image_file:
+            image_bytes = image_file.read()
+
+        image_base64 = base64.b64encode(image_bytes).decode("utf-8")
+
+        # Prepare the prompt including the base64 image data
+        message = [
+            HumanMessage(
+                content=[
+                    {
+                        "type": "text",
+                        "text": (
+                            "Describe the image and extract any text in it."
+                        ),
+                    },
+                    {
+                        "type": "image_url",
+                        "image_url": {
+                            "url": f"data:image/png;base64,{image_base64}"
+                        },
+                    },
+                ]
+            )
+        ]
+        response = model.invoke(message)
+        # Append extracted text
+        all_text += response.text + "\n\n"
+        return all_text.strip()
     except Exception as e:
-        print(f"An unexpected error occurred fetching questions: {e}")
-        return f"An unexpected error occurred fetching questions: {e}", None
-
-    # 3. Run your Agent
-    results_log = []
-    answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
-    for item in 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
-        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})
-        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}"})
-
-    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)
-
-    # 5. Submit
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
+        # A butler should handle errors gracefully
+        error_msg = f"Error extracting text: {str(e)}"
+        print(error_msg)
+        return ""
+
+@tool
+def download_and_read_file(task_id: str) -> str:
+    """
+    Download and read the file attached to the GAIA task its contents.
+    Always call this first if there is a file attached to a GAIA Task.
+    Args:
+        task_id (str): The ID of the GAIA task.
+    Returns:
+        str: The contents of the file as a string.
+    """
+
     try:
-        response = requests.post(submit_url, json=submission_data, timeout=60)
+        # Download the file from the GAIA API
+        response = requests.get(f"{FILES_URL}/{task_id}", timeout = 10)
         response.raise_for_status()
-        result_data = 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.')}"
-        )
-        print("Submission successful.")
-        results_df = pd.DataFrame(results_log)
-        return final_status, results_df
-    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]}"
-        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
 
+        # Determine the file type and read its contents
+        content_disposition = response.headers.get("content-disposition", "")
+        content_type = response.headers.get("content-type", "")
+        filename = None
+        if "filename=" in content_disposition:
+            filename = content_disposition.split("filename=")[1].strip('"')
 
-# --- Build Gradio Interface using Blocks ---
-with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
-    gr.Markdown(
-        """
-        **Instructions:**
+        if not filename:
+            filename = f"{task_id}.bin"
 
-        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.
+        ext = Path(filename).suffix.lower()
 
-        ---
-        **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.
-        """
-    )
+        if ext in(".txt", ".py", ".json", ".md", ".ymal", ".html", ".xml", ""):
+            return response.text
 
-    gr.LoginButton()
+        if ext == ".xlsx" or "xlsx" in content_type:
+            import pandas as pd
+            with tempfile.NamedTemporaryFile(suffix=".xlsx", delete=False) as file:
+                file.write(response.content)
+                temp_path = file.name
 
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
+            read_file = pd.read_excel(temp_path)
+            return read_file.to_string()
+        if ext == ".csv" or "csv" in content_type:
+            import pandas as pd
+            with tempfile.NamedTemporaryFile(suffix=".csv", delete=False) as file:
+                file.write(response.content)
+                temp_path = file.name
+            read_file = pd.read_csv(temp_path)
+            return read_file.to_string()
+        if ext == ".csv" or "csv" in content_type:
+                    import pandas as pd
+                    with tempfile.NamedTemporaryFile(suffix=".csv", delete=False) as file:
+                        file.write(response.content)
+                        temp_path = file.name
+                    read_file = pd.read_csv(temp_path)
+                    return read_file.to_string()
+        if ext == ".jpg" or ext == ".jpeg" or ext == ".png" or "image" in content_type:
+            from PIL import Image
+            with tempfile.NamedTemporaryFile(suffix=ext, delete=False) as file:
+                file.write(response.content)
+                temp_path = file.name
+            return extract_text_from_image(temp_path)
+        
+        # Unsupported file type 
+        return ( 
+            f"Unsupported file type: {content_type}. "
+            "I downloaded the file successfully, but I don't know "
+            "how to extract its contents." 
+            ) 
+    except requests.RequestException as e: 
+        return f"Failed to download file: {e}" 
+    except Exception as e: return f"Failed to read file: {e}"
+        
+    except Exception as e:
+        return f"error downloading or reading file: {str(e)}"
+
+    return file_content
+
+@tool
+def wikipedia_search(query: str):
+    """
+    Search wikipedia for a query and return a max of three results.
+    Takes a string query as the search query
+    Args:
+        query (str): The search query.
+    """
+    try:
+        search_results = WikipediaLoader(query=query, load_max_docs=3).load()
+
+        if not search_results:
+            return f"No Wikipedia results found for {query}. Consider another query or try a web search."
+        return "\n\n---\n\n".join(
+            f"Title: {doc.metadata.get('title', 'Unknown')}\n"
+            f"Content: {doc.page_content}"
+            for doc in search_results
+        )
+    except Exception as e:
+        print(f"Wikipedia search failed for {query}: {e}")
+        return f"Wikipedia search failed for {query}. Try a web search instead."
 
-    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]
-    )
+model = build_gemini_llm()
+tools = [
+    add_numbers,
+    subtract_numbers,
+    multiply_numbers,
+    divide_numbers,
+    extract_text_from_image,
+    search_web
+]
+model_with_tools = model.bind_tools(tools)
 
-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
+def assistant(state: AgentState):
+    response = model_with_tools.invoke(state["messages"])
+    reasoning_tokens = response.usage_metadata["output_token_details"]["reasoning"]
+    print("Reasoning tokens used:", reasoning_tokens)
+    return {
+        "messages": [response],
+        "file_path": state["file_path"],
+        "task_id": state["task_id"],
+        "url": state["url"]
+    }
 
-    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?).")
+builder = StateGraph(AgentState)
 
-    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")
-    else:
-        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
+builder.add_node("assistant", assistant)
+builder.add_node("tools", ToolNode(tools))
 
-    print("-"*(60 + len(" App Starting ")) + "\n")
+builder.add_edge(START, "assistant")
+builder.add_conditional_edges("assistant", tools_condition)
+builder.add_edge("tools", "assistant")
 
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+graph = builder.compile()