Update app.py

app.py

@@ -1,95 +1,85 @@
-
-from __future__ import unicode_literals
-import subprocess
 import os
-
-from dotenv import load_dotenv
-
-load_dotenv()
-
-os.environ['USER_AGENT'] = 'myagent'
-
 import gradio as gr
 import requests
 import inspect
-import tempfile
-import nest_asyncio
 import pandas as pd
+from agent import SmolAgent
+import json
 
-from agent import MyAgent
-from tools import initialize_web_tools
+# --- Constants ---
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-nest_asyncio.apply()
+USE_CACHE = False  # Set to False to disable caching
+CACHE_FILE = "cache/answers_cache.json"
+QUESTIONS_CACHE_FILE = "cache/questions_cache.json"
 
-DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-def fetch_questions(questions_url):
-    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.")
-        return questions_data
-    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
+def load_cache(filename):
+    if not USE_CACHE:
+        print(f"Caching is disabled. Not loading from {filename}.")
+        return None
+    else:
+        if os.path.exists(filename):
+            try:
+                with open(filename, "r") as f:
+                    return json.load(f)
+            except Exception as e:
+                print(f"Failed to load cache from {filename}: {e}")
+        return None
 
-def download_file(files_url, task_id):
-    try:
-        filename = task_id
-        response = requests.get(files_url+'/'+filename)
-        response.raise_for_status()
 
-        filename = response.headers['content-disposition'].split('"')[1]
-        temp_dir = tempfile.gettempdir()
-        file_path = os.path.join(temp_dir, filename)
-        with open(file_path, 'wb') as f:
-            f.write(response.content)
+def save_cache(filename, data):
+    if not USE_CACHE:
+        print(f"Caching is disabled. Not loading from {filename}.")
+        return None
+    else:
+        try:
+            with open(filename, "w") as f:
+                json.dump(data, f)
+        except Exception as e:
+            print(f"Failed to save cache to {filename}: {e}")
+
 
+def download_file(task_id):
+    """
+    Downloads a file for the given task_id from the /files/{task_id} endpoint,
+    extracts the filename from the Content-Disposition header, and saves it to disk.
+    Returns the local file path if successful, else None.
+    """
+    api_url = DEFAULT_API_URL
+    file_url = f"{api_url}/files/{task_id}"
+    try:
+        response = requests.get(file_url, stream=True, timeout=30)
+        response.raise_for_status()
+        content_disp = response.headers.get("content-disposition", "")
+        filename = None
+        if "filename=" in content_disp:
+            filename = content_disp.split("filename=")[-1].strip('"; ')
+        if not filename:
+            filename = f"{task_id}.txt"
+        os.makedirs("cache", exist_ok=True)
+        file_path = os.path.join("cache", filename)
+        with open(file_path, "wb") as f:
+            for chunk in response.iter_content(chunk_size=8192):
+                if chunk:
+                    f.write(chunk)
+        print(f"Downloaded file for task {task_id} to {file_path}")
         return file_path
-    except Exception as file_e:
-        print(f"No file found for task {task_id} or error: {file_e}")
+    except Exception as e:
+        print(f"Failed to download file for task {task_id}: {e}")
         return None
 
-async def run_my_agent(agent, questions_data, files_url):
-    results_log = []
-    answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
-    for item in questions_data:
-        task_id = item.get("task_id")
-        file_path = download_file(files_url, 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 = await agent(question_text, file_path, task_id)
-            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}"})
-    return results_log, answers_payload
 
-async 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
+
     if profile:
-        username= f"{profile.username}"
+        username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -98,35 +88,98 @@ async def run_and_submit_all( profile: gr.OAuthProfile | None):
     api_url = DEFAULT_API_URL
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
-    files_url = f"{api_url}/files"
 
     # 1. Instantiate Agent ( modify this part to create your agent)
     try:
-        web_tools = initialize_web_tools()
-        agent = MyAgent(web_tools=web_tools)
+        agent = SmolAgent()
     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_startup}/tree/main"
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
     print(agent_code)
 
-    # 2. Fetch Questions
-    questions_data = fetch_questions(questions_url)
+    # 2. Fetch Questions (with caching)
+    questions_data = load_cache(QUESTIONS_CACHE_FILE)
+    if questions_data:
+        print(f"Loaded {len(questions_data)} questions from cache.")
+    else:
+        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.")
+            save_cache(QUESTIONS_CACHE_FILE, questions_data)
+        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 (with answer caching)
+    results_log = []
+    answers_payload = []
+    answers_cache = load_cache(CACHE_FILE) or {}
+    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
+        file_name = item.get("file_name")
+
+        # Check if answer is cached
+        if task_id in answers_cache:
+            submitted_answer = answers_cache[task_id]
+            print(f"Loaded cached answer for task {task_id}")
+        else:
+            try:
+                if len(file_name) > 0:
+                    file = download_file(task_id)
+                    print(f"File for task {file_name} downloaded: {file}")
+                    submitted_answer = agent.run(question_text, file_path=file)
+                else:
+                    submitted_answer = agent.run(question_text)
+                answers_cache[task_id] = submitted_answer
+                save_cache(CACHE_FILE, answers_cache)
+            except Exception as e:
+                print(f"Error running agent on task {task_id}: {e}")
+                submitted_answer = f"AGENT ERROR: {e}"
+        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,
+            }
+        )
 
-    # 3. Run your Agent
-    results_log, answers_payload = await run_my_agent(agent, questions_data, files_url)
-    
     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}
+    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
+    # # 5. Submit
     print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
@@ -140,6 +193,7 @@ async def run_and_submit_all( profile: gr.OAuthProfile | None):
             f"Message: {result_data.get('message', 'No message received.')}"
         )
         print("Submission successful.")
+        print(final_status)
         results_df = pd.DataFrame(results_log)
         return final_status, results_df
     except requests.exceptions.HTTPError as e:
@@ -172,9 +226,14 @@ async def run_and_submit_all( profile: gr.OAuthProfile | None):
 
 # --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown("# Robin's Basic Agent Evaluation Space")
     gr.Markdown(
         """
+        ### Description
+        My submission for the final assigment of the huggingface agent course.
+        I chose to use the smolagents library to create a simple agent and stay away from the bigger multimodel models. 
+        By providing specifc tools to handle image and audio files.
+        ### Original Instructions
         **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.
@@ -190,20 +249,19 @@ 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}")
@@ -211,14 +269,18 @@ 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)