Update app.py

app.py

@@ -1,202 +1,142 @@
-import os
-import gradio as gr
+from smolagents import CodeAgent, tool, OpenAIServerModel
 import requests
-import inspect
-import pandas as pd
-from agent import BasicAgent
-from constants import DEFAULT_API_URL, OPENROUTER_MODEL
-
-# (Keep Constants as is)
-# --- Constants ---
-DEFAULT_API_URL = DEFAULT_API_URL
-OPENROUTER_API = os.getenv("OPENROUTER_API")
-OPENROUTER_MODEL = OPENROUTER_MODEL
-
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-class Agent:
-    def __init__(self):
-        self.agent = BasicAgent(OPENROUTER_API, OPENROUTER_MODEL, DEFAULT_API_URL)
-        self.agent.initialize_agent()
-        print("BasicAgent initialized.")
-    def __call__(self, input: tuple):
-        return self.agent.run(input)
-
-
-
-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.")
-        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"
-
-    # 1. Instantiate Agent ( modify this part to create your agent)
-    try:
-        agent = Agent()
-    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}")
-    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
-    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")
-        file_name = item.get("file_name")
-        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(input=(task_id, question_text, file_name))
-            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}")
-    try:
-        response = requests.post(submit_url, json=submission_data, timeout=60)
-        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.')}"
+import io
+from PIL import Image
+from constants import DEFAULT_API_URL
+
+class BasicAgent:
+    def __init__(self, OPENROUTER_API: str, OPENROUTER_MODEL: str, api_url: str):
+        self.api_url = api_url
+        self.model = OpenAIServerModel(
+            model_id=OPENROUTER_MODEL,
+            api_base="https://openrouter.ai/api/v1",
+            api_key=OPENROUTER_API
         )
-        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
-
-
-# --- Build Gradio Interface using Blocks ---
-with gr.Blocks() as demo:
-    gr.Markdown("# Basic 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.
-
+        self.agent = None
+
+    def initialize_agent(self):
+        self.agent = CodeAgent(
+            model=self.model,
+            tools=[get_file],
+            add_base_tools=True,
+            additional_authorized_imports=['pandas', 'io']
+        )
+        # self.agent.tools.pop('visit_webpage') # replacing tool
+        return self.agent
+
+
+    def run(self, input: tuple):
+        id, question, file = input
+
+        # check if has image
+        img = None
+        if file and file.split('.')[1] == 'png':
+            img = [Image.open(get_file(file))]
+
+        # make a prompt
+        prompt = f"""
+        You are CodeAgent assistant. The user asks you a question and you provide them with a verified and specific answer.
+        As an agent you have some tools to use. You may use them on demand.
+        Your normal workflow should follow the following sequence:
+        1. You received the question and (in some cases) additional information as a file_id. You analize it.
+        2. At the planning stage you making a sequence of steps to complete this task in planning variable
+        3. At the execution stage you provide an executable python code which will be parsed and executed by the program.
+            Remember to provide executable code here, without any additional characters which may crash the execution and parsing.
+        4. After execution you decide whether you had a final result an you can close the task providing this result or you should continue.
+            If ccontinue, review you previous planning sequence: what is done, what should be change in this plan or what we should add to it?
+        EACH STEP INCLUDES BOTH PLANNING AND EXECUTIONS STAGES:
+            * you provide planning in a separate variable at the beggining of your answer, variable name: planning
+            * execution is the rest code where you trying to achive the planned goals.
+        
+        The example:
+        User: What is Axelord?
+        [Step 1]
+        Agent: 
+            Planning stage:
+                planning = "
+                    Okay, user want me to tell him what is Axelord. I do not have this answer in my memory so I need to find it.
+                    Plan:
+                    1. To search: What is Axelord.
+                    2. Provide an aswer.
+                "
+            Execution stage:
+                query = "What is Axelord?"                                 
+                search_result = web_search(query)                                             
+                print(search_result)
+            Result:
+                The pages about this topic.
+            Output:
+                None
+        [Step 2]
+        Agent:
+            Planning stage:
+                planning = "
+                    Okay, I found some websites about that.
+                    Plan:
+                    1. To search: What is Axelord. - DONE.
+                    2. Visit the webpage to get more inforamtion.
+                    3. Provide an answer.
+                "
+            Execution stage:
+                url = "https://en.wikipedia.org/wiki/Axelord"                           
+                wikipedia_page = visit_webpage(url)                                           
+                print(wikipedia_page) 
+            Result:
+                page html output which contains an answer.
+            Output:
+                FinalAnswerTool(Answer)
+        
+        In the example above you saw how you can use searching tools, but you also has some others.
+        You complete the task step by step. You recognise when the planning stage and you can do planning, and when
+        the execution stage and you MUST provide an executable python code.
+        
+        The user's question is:
+        {question}
+        
         ---
-        **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.
+        Additional information you may use:
+        file_id: {file}
+        
+        IMPORTANT:
+            * You do not answer in plain text.
+            * You only answer in python code. Every plain text you need to provide you should include in a text variable
+            * You may receive both images sometimes as a context. Do not forget to use them to handle the task.
         """
-    )
-
-    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(
-        fn=run_and_submit_all,
-        outputs=[status_output, results_table]
-    )
-
-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
-
-    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?).")
-
-    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.")
-
-    print("-"*(60 + len(" App Starting ")) + "\n")
+        # run
+        return self.agent.run(
+            task = prompt,
+            images = img
+        )
 
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+# tools
+@tool
+def get_file(file_id: str) -> io.BytesIO | io.StringIO | None:
+    """A tool that fetches the file's content from the server.
+    Use it every time you need to get file for completing the task.
+    IMPORTANT: ONLY USE IT WHEN THE FILE_ID ARGUMENT IS NOT EMPTY.
+    YOU MUST ENSURE THAT FILE_ID ARGUMENT IS NOT EMPTY WHEN YOU USE IT.
+    Args:
+        file_id: id of a file required to fetch
+    Returns:
+        io.BytesIO: file emulation for .xlsx or .png files. You can use this object as a file itself. It is already converted to BytesIO.
+        io.StringIO: file emulation for .py files. You can use this object as a file itself. It is already converted to StringIO.
+    """
+    # make request
+    response = requests.get(DEFAULT_API_URL+'/files/'+file_id.split('.')[0], timeout=15)
+    response.raise_for_status()
+
+    # prepare the output
+    file_format = file_id.split('.')[1]
+    match file_format:
+        case 'png':
+            print('png uploaded')
+            return io.BytesIO(response.content)
+        case 'xlsx':
+            print('xlsx uploaded')
+            return io.BytesIO(response.content)
+        case 'py':
+            print('py uploaded')
+            return io.StringIO(response.text)
+        case _:
+            return None