Update app.py

app.py

@@ -1,160 +1,109 @@
-import requests
 import os
 import gradio as gr
+import inspect
 import pandas as pd
-import time
-import re
-import json
-import wikipedia
-import speech_recognition as sr
-from pydub import AudioSegment
-from langchain_openai import ChatOpenAI
-from langchain.agents import AgentExecutor, create_react_agent
-from langchain.memory import ConversationSummaryMemory
-from langchain.tools import Tool
-from langchain.tools.python.tool import PythonREPLTool
-from langchain_community.document_loaders import WikipediaLoader
-from langchain.prompts import PromptTemplate
+import importlib
+from importlib import resources
+import requests
+import yaml
+import numpy as np
+from smolagents import CodeAgent, DuckDuckGoSearchTool, VisitWebpageTool, WikipediaSearchTool, Tool, OpenAIServerModel, SpeechToTextTool
 
+# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# === TOOL: python_repl ===
-repl_tool = PythonREPLTool(
-    name="python_repl",
-    description="A Python REPL for calculations and parsing. Input must be valid Python code, use print() to output results."
-)
+# --- Basic Agent Definition ---
+# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 
-# === TOOL: file_saver ===
-def download_and_save_file(args: dict) -> str:
-    try:
-        if isinstance(args, str):
-            args = json.loads(args)
-        url = args.get("url")
-        local_filename = args.get("local_filename")
-        if not url or not local_filename:
-            return "Error: Both 'url' and 'local_filename' must be provided."
-        response = requests.get(url, stream=True, timeout=30)
+
+
+
+
+class GetTaskFileTool(Tool):
+    name = "get_task_file_tool"
+    description = """This tool downloads the file content associated with the given task_id if exists. Returns absolute file path"""
+    inputs = {
+        "task_id": {"type": "string", "description": "Task id"},
+        "file_name": {"type": "string", "description": "File name"},
+    }
+    output_type = "string"
+
+    def forward(self, task_id: str, file_name: str) -> str:
+        response = requests.get(f"{DEFAULT_API_URL}/files/{task_id}", timeout=15)
         response.raise_for_status()
-        os.makedirs(os.path.dirname(local_filename) or '.', exist_ok=True)
-        with open(local_filename, 'wb') as f:
-            for chunk in response.iter_content(chunk_size=8192):
-                f.write(chunk)
-        return f"File downloaded successfully to {local_filename}"
-    except Exception as e:
-        return f"Error downloading file: {e}"
+        with open(file_name, 'wb') as file:
+            file.write(response.content)
+        return os.path.abspath(file_name)
 
-file_saver_tool = Tool(
-    name="file_saver",
-    description="Downloads a file from a URL and saves it as the given local filename. Input: JSON with 'url' and 'local_filename'.",
-    func=download_and_save_file,
-)
+class LoadXlsxFileTool(Tool):
+    name = "load_xlsx_file_tool"
+    description = """This tool loads xlsx file into pandas and returns it"""
+    inputs = {
+        "file_path": {"type": "string", "description": "File path"}
+    }
+    output_type = "object"
 
-# === TOOL: audio_transcriber_tool ===
-def transcribe_audio_from_path(local_audio_path: str, language: str = "en-US") -> str:
-    r = sr.Recognizer()
-    temp_wav_path = "temp_audio_to_transcribe.wav"
-    transcribed_text = ""
-    try:
-        if local_audio_path.startswith("http://") or local_audio_path.startswith("https://"):
-            return "Error: Only local file paths allowed. Use 'file_saver' first."
-        if not os.path.exists(local_audio_path):
-            return f"Error: File not found: '{local_audio_path}'."
-        audio = AudioSegment.from_file(local_audio_path)
-        audio.export(temp_wav_path, format="wav")
-        with sr.AudioFile(temp_wav_path) as source:
-            audio_listened = r.record(source)
-            try:
-                transcribed_text = r.recognize_google(audio_listened, language=language)
-            except sr.UnknownValueError:
-                return "Could not understand audio."
-            except sr.RequestError as e:
-                return f"Could not request results from Google Speech Recognition; {e}"
-    except Exception as e:
-        return f"Error: {e}"
-    finally:
-        if os.path.exists(temp_wav_path):
-            os.remove(temp_wav_path)
-    return transcribed_text.strip()
-
-audio_transcriber_tool = Tool(
-    name="audio_transcriber_tool",
-    description="Transcribes audio from a local file path to text. Input: path to audio file (e.g., 'myfile.mp3'). Use 'file_saver' to download first. Optionally set language.",
-    func=transcribe_audio_from_path,
-)
+    def forward(self, file_path: str) -> object:
+        return pd.read_excel(file_path)
 
-# === TOOL: wikipedia_search_tool2 ===
-def wiki_search(query: str) -> str:
-    search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
-    formatted_search_docs = "\n\n---\n\n".join(
-        [
-            f'<Document source="{doc.metadata.get("source", "")}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
-            for doc in search_docs
-        ])
-    return formatted_search_docs
-
-wikipedia_search_tool2 = Tool(
-    name="wikipedia_search_tool2",
-    description="Search Wikipedia for a query and return up to 2 results. Input: query string.",
-    func=wiki_search,
-)
+class LoadTextFileTool(Tool):
+    name = "load_text_file_tool"
+    description = """This tool loads any text file"""
+    inputs = {
+        "file_path": {"type": "string", "description": "File path"}
+    }
+    output_type = "string"
 
-# === PROMPT ===
-prompt = PromptTemplate(
-    input_variables=["input", "agent_scratchpad", "chat_history", "tool_names"],
-    template="""
-You are a smart and helpful AI Agent/Assistant that excels at fact-based reasoning. You are allowed and encouraged to use one or more tools as needed to answer complex questions and perform tasks.
-STRICT FINAL ANSWER RULES:
-- Final Answer must be a number, a few words, or a comma-separated list, as requested.
-- No units or extra punctuation unless asked.
-Your response must start with 'Thought:' and finish with 'Final Answer:'.
-You have access to the following tools:
-{tools}
-Use this format:
-Thought: [thinking]
-Action: [tool_name]
-Action Input: [input]
-Observation: [result]
-...
-Thought: [done]
-Final Answer: [concise answer]
-
-{chat_history}
-New input: {input}
----
-{agent_scratchpad}
-"""
+    def forward(self, file_path: str) -> object:
+        with open(file_path, 'r', encoding='utf-8') as file:
+            return file.read()
+
+prompts = yaml.safe_load(
+    resources.files("smolagents.prompts").joinpath("code_agent.yaml").read_text()
 )
 
-# === AGENT ===
-class BasicAgent:
-    def __init__(
-        self,
-        agent,
-        tools,
-        verbose=False,
-        handle_parsing_errors=True,
-        max_iterations=9,
-        memory=None
-    ):
-        self.agent_obj = AgentExecutor(
-            agent=agent,
-            tools=tools,
-            verbose=verbose,
-            handle_parsing_errors=handle_parsing_errors,
-            max_iterations=max_iterations,
-            memory=memory
-        )
+prompts["system_prompt"] = ("You are a general AI assistant. I will ask you a question. Report your thoughts, and finish your answer with the following template: FINAL ANSWER: [YOUR FINAL ANSWER]. YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string. "
+                            + prompts["system_prompt"])
 
-    def __call__(self, question: str) -> str:
-        result = self.agent_obj.invoke(
-            {"input": question},
-            config={"configurable": {"session_id": "test-session"}},
-        )
-        return result['output']
+def init_agent():
+    gemini_model = OpenAIServerModel(
+            model_id="deepseek-ai/DeepSeek-R1-0528",
+            api_base="https://llm.chutes.ai/v1",
+            api_key=os.getenv("CHUTES_API_KEY"),
+            temperature=0.7
+    )
+    agent = CodeAgent(
+        tools=[
+            DuckDuckGoSearchTool(),
+            VisitWebpageTool(),
+            WikipediaSearchTool(),
+            GetTaskFileTool(),
+            SpeechToTextTool(),
+            LoadXlsxFileTool(),
+            LoadTextFileTool()
+        ],
+        model=gemini_model,
+        prompt_templates=prompts,
+        max_steps=15,
+        additional_authorized_imports = ["pandas"]
+    )
+    return agent
+    
+    
+    
+    
+    
+    
+
+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}"
         print(f"User logged in: {username}")
@@ -166,30 +115,17 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    openai_api_key = os.getenv("OPENAI_API_KEY")
-    if not openai_api_key:
-        print("OpenAI API key not found in environment variables.")
-        return "OpenAI API key not found. Please set OPENAI_API_KEY environment variable.", None
-    print(f"Using OpenAI API key: {openai_api_key[:4]}... (truncated for security)")
-
-    llm_client = ChatOpenAI(model='gpt-4o', temperature=0, api_key=openai_api_key)
-
-    summary_memory = ConversationSummaryMemory(llm=llm_client, memory_key="chat_history")
-
-    summary_react_agent = create_react_agent(
-        llm=llm_client,
-        tools=[repl_tool, file_saver_tool, audio_transcriber_tool, wikipedia_search_tool2],
-        prompt=prompt
-    )
-
+    # 1. Instantiate Agent ( modify this part to create your agent)
     try:
-        agent = BasicAgent(summary_react_agent, [repl_tool, file_saver_tool, audio_transcriber_tool, wikipedia_search_tool2], True, True, 30, summary_memory)
+        agent = init_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)
@@ -210,23 +146,27 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         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")
+        print(question_text)
         file_name = item.get("file_name")
-        full_question_for_agent = question_text
-        if file_name:
-            attachment_url = f"https://agents-course-unit4-scoring.hf.space/files/{task_id}"
-            full_question_for_agent += f"\n\nAttachment '{file_name}' available at EXACT URL: {attachment_url}"
-            print(f"Running agent on task {task_id}: {full_question_for_agent}",flush=True)
+        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(full_question_for_agent)
+            submitted_answer = agent.run(f"Task id: {task_id}. Task file: {file_name if file_name != '' else 'is absent'}. Task: " + question_text)
+            if isinstance(submitted_answer, (np.integer, np.floating)):
+                submitted_answer = submitted_answer.item()  # Convert NumPy types to Python native types
+            elif isinstance(submitted_answer, list):
+                submitted_answer = [x.item() if isinstance(x, (np.integer, np.floating)) else x for x in submitted_answer]
+            submitted_answer = str(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})
-            time.sleep(1)
         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}"})
@@ -235,10 +175,12 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         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)
@@ -252,31 +194,60 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
             f"Message: {result_data.get('message', 'No message received.')}"
         )
         print("Submission successful.")
-        cleaned_final_status = re.sub(r'[^\x20-\x7E\n\r\t]+', '', final_status)
-        cleaned_final_status = cleaned_final_status.strip()
         results_df = pd.DataFrame(results_log)
-        return cleaned_final_status, results_df
+        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"Submission Failed: {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
 
-# --- Gradio Interface ---
+
+# --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
     gr.Markdown("# Basic Agent Evaluation Runner")
     gr.Markdown(
         """
         **Instructions:**
-        1. Clone this space and modify the code as needed.
-        2. Log in to your Hugging Face account below.
-        3. Click 'Run Evaluation & Submit All Answers' to see your score!
+        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.
         """
     )
+
     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]
@@ -284,19 +255,24 @@ 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")
+    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:
+
+    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")
+
     print("Launching Gradio Interface for Basic Agent Evaluation...")
     demo.launch(debug=True, share=False)