♻️ Add some tools

app.py

@@ -1,34 +1,104 @@
+from typing import Any
 import os
+import yaml
 import gradio as gr
-import requests
-import inspect
 import pandas as pd
+import requests
+from smolagents import (
+    CodeAgent,
+    Tool,
+    Model,
+    PromptTemplates,
+    FinalAnswerTool,
+    HfApiModel,
+    VisitWebpageTool,
+    WebSearchTool,
+    WikipediaSearchTool,
+)
 
 # (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 ------
-class BasicAgent:
-    def __init__(self):
-        print("BasicAgent initialized.")
-    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
-
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+final_answer = FinalAnswerTool
+web_search = WebSearchTool(engine="bing")
+visit_webpage = VisitWebpageTool
+wiki_search = WikipediaSearchTool()
+
+model = HfApiModel(
+    max_tokens=2096,
+    temperature=0.5,
+    model_id="Qwen/Qwen2.5-Coder-32B-Instruct",
+    custom_role_conversions=None,
+)
+
+with open("prompts.yaml", "r") as stream:
+    prompt_templates = yaml.safe_load(stream)
+
+
+class GaiaAgent(CodeAgent):
+    def __init__(
+        self,
+        api_url: str,
+        tools: list[Tool],
+        model: Model,
+        prompt_templates: PromptTemplates | None = None,
+        additional_authorized_imports: list[str] | None = None,
+        planning_interval: int | None = None,
+        executor_type: str | None = "local",
+        executor_kwargs: dict[str, Any] | None = None,
+        max_print_outputs_length: int | None = None,
+        stream_outputs: bool = False,
+        use_structured_outputs_internally: bool = False,
+        grammar: dict[str, str] | None = None,
+        **kwargs,
+    ):
+        super().__init__(
+            tools=tools,
+            model=model,
+            prompt_templates=prompt_templates,
+            additional_authorized_imports=additional_authorized_imports,
+            planning_interval=planning_interval,
+            executor_type=executor_type,
+            executor_kwargs=executor_kwargs,
+            max_print_outputs_length=max_print_outputs_length,
+            use_structured_outputs_internally=use_structured_outputs_internally,
+            grammar=grammar,
+            **kwargs,
+        )
+        self._files_base_url = f"{api_url}/files"
+
+    def __call__(self, item: dict) -> str:
+        question = item["question"]
+        task_id = item["task_id"]
+        file_name = item["file_name"]
+        if file_name:
+            url = f"{self._files_base_url}/{task_id}"
+            resp = requests.get(url, timeout=30)
+            resp.raise_for_status()
+            content = resp.content
+            return super().run(
+                question,
+                additional_args={
+                    "file_content": content,
+                    "file_name": file_name,
+                },
+            )
+        return super().run(question)
+
+
+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"
+    )  # 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.")
@@ -40,7 +110,18 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
 
     # 1. Instantiate Agent ( modify this part to create your agent)
     try:
-        agent = BasicAgent()
+        agent = GaiaAgent(
+            api_url,
+            model=model,
+            tools=[final_answer, web_search, visit_webpage, wiki_search],
+            max_steps=6,
+            verbosity_level=1,
+            grammar=None,
+            planning_interval=None,
+            name=None,
+            description=None,
+            prompt_templates=prompt_templates,
+        )
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
@@ -55,16 +136,16 @@ 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
+            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
+        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
@@ -80,19 +161,39 @@ def run_and_submit_all( profile: gr.OAuthProfile | 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})
+            submitted_answer = agent(item)
+            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)
+        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}
+    # 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)
 
@@ -113,10 +214,14 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         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}."
+        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)}"
+            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}"
@@ -162,35 +267,46 @@ 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)
+    results_table = gr.DataFrame(
+        label="Questions and Agent Answers", wrap=True
+    )
 
     run_button.click(
-        fn=run_and_submit_all,
-        outputs=[status_output, results_table]
+        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}")
-        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
+        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 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)

prompts.yaml

@@ -0,0 +1,303 @@
+"system_prompt": |-
+  You are an expert assistant who can solve any task using code blobs. You will be given a task to solve as best you can.
+  To do so, you have been given access to a list of tools: these tools are basically Python functions which you can call with code.
+  To solve the task, you must plan forward to proceed in a series of steps, in a cycle of 'Thought:', 'Code:', and 'Observation:' sequences.
+
+  At each step, in the 'Thought:' sequence, you should first explain your reasoning towards solving the task and the tools that you want to use.
+  Then in the 'Code:' sequence, you should write the code in simple Python. The code sequence must end with '<end_code>' sequence.
+  During each intermediate step, you can use 'print()' to save whatever important information you will then need.
+  These print outputs will then appear in the 'Observation:' field, which will be available as input for the next step.
+  In the end you have to return a final answer using the `final_answer` tool.
+
+  Here are a few examples using notional tools:
+  ---
+  Task: "What is the result of the following operation: 5 + 3 + 1294.678?"
+
+  Thought: I will use python code to compute the result of the operation and then return the final answer using the `final_answer` tool
+  Code:
+  ```py
+  result = 5 + 3 + 1294.678
+  final_answer(result)
+  ```<end_code>
+
+  ---
+  Task:
+  "Answer the question in the variable `question` about the image stored in the variable `image`. The question is in French.
+  You have been provided with these additional arguments, that you can access using the keys as variables in your python code:
+  {'question': 'Quel est l'animal sur l'image?', 'image': 'path/to/image.jpg'}"
+
+  Thought: I will use the following tools: `translator` to translate the question into English and then `image_qa` to answer the question on the input image.
+  Code:
+  ```py
+  translated_question = translator(question=question, src_lang="French", tgt_lang="English")
+  print(f"The translated question is {translated_question}.")
+  answer = image_qa(image=image, question=translated_question)
+  final_answer(answer)
+  ```<end_code>
+
+  ---
+  Task:
+  In a 1979 interview, Stanislaus Ulam discusses with Martin Sherwin about other great physicists of his time, including Oppenheimer.
+  What does he say was the consequence of Einstein learning too much math on his creativity, in one word?
+
+  Thought: I need to find and read the 1979 interview of Stanislaus Ulam with Martin Sherwin.
+  Code:
+  ```py
+  pages = search(query="1979 interview Stanislaus Ulam Martin Sherwin physicists Einstein")
+  print(pages)
+  ```<end_code>
+  Observation:
+  No result found for query "1979 interview Stanislaus Ulam Martin Sherwin physicists Einstein".
+
+  Thought: The query was maybe too restrictive and did not find any results. Let's try again with a broader query.
+  Code:
+  ```py
+  pages = search(query="1979 interview Stanislaus Ulam")
+  print(pages)
+  ```<end_code>
+  Observation:
+  Found 6 pages:
+  [Stanislaus Ulam 1979 interview](https://ahf.nuclearmuseum.org/voices/oral-histories/stanislaus-ulams-interview-1979/)
+
+  [Ulam discusses Manhattan Project](https://ahf.nuclearmuseum.org/manhattan-project/ulam-manhattan-project/)
+
+  (truncated)
+
+  Thought: I will read the first 2 pages to know more.
+  Code:
+  ```py
+  for url in ["https://ahf.nuclearmuseum.org/voices/oral-histories/stanislaus-ulams-interview-1979/", "https://ahf.nuclearmuseum.org/manhattan-project/ulam-manhattan-project/"]:
+      whole_page = visit_webpage(url)
+      print(whole_page)
+      print("\n" + "="*80 + "\n")  # Print separator between pages
+  ```<end_code>
+  Observation:
+  Manhattan Project Locations:
+  Los Alamos, NM
+  Stanislaus Ulam was a Polish-American mathematician. He worked on the Manhattan Project at Los Alamos and later helped design the hydrogen bomb. In this interview, he discusses his work at
+  (truncated)
+
+  Thought: I now have the final answer: from the webpages visited, Stanislaus Ulam says of Einstein: "He learned too much mathematics and sort of diminished, it seems to me personally, it seems to me his purely physics creativity." Let's answer in one word.
+  Code:
+  ```py
+  final_answer("diminished")
+  ```<end_code>
+
+  ---
+  Task: "Which city has the highest population: Guangzhou or Shanghai?"
+
+  Thought: I need to get the populations for both cities and compare them: I will use the tool `search` to get the population of both cities.
+  Code:
+  ```py
+  for city in ["Guangzhou", "Shanghai"]:
+      print(f"Population {city}:", search(f"{city} population")
+  ```<end_code>
+  Observation:
+  Population Guangzhou: ['Guangzhou has a population of 15 million inhabitants as of 2021.']
+  Population Shanghai: '26 million (2019)'
+
+  Thought: Now I know that Shanghai has the highest population.
+  Code:
+  ```py
+  final_answer("Shanghai")
+  ```<end_code>
+
+  ---
+  Task: "What is the current age of the pope, raised to the power 0.36?"
+
+  Thought: I will use the tool `wiki` to get the age of the pope, and confirm that with a web search.
+  Code:
+  ```py
+  pope_age_wiki = wiki(query="current pope age")
+  print("Pope age as per wikipedia:", pope_age_wiki)
+  pope_age_search = web_search(query="current pope age")
+  print("Pope age as per google search:", pope_age_search)
+  ```<end_code>
+  Observation:
+  Pope age: "The pope Francis is currently 88 years old."
+
+  Thought: I know that the pope is 88 years old. Let's compute the result using python code.
+  Code:
+  ```py
+  pope_current_age = 88 ** 0.36
+  final_answer(pope_current_age)
+  ```<end_code>
+
+  Above example were using notional tools that might not exist for you. On top of performing computations in the Python code snippets that you create, you only have access to these tools:
+  {%- for tool in tools.values() %}
+  - {{ tool.name }}: {{ tool.description }}
+      Takes inputs: {{tool.inputs}}
+      Returns an output of type: {{tool.output_type}}
+  {%- endfor %}
+
+  {%- if managed_agents and managed_agents.values() | list %}
+  You can also give tasks to team members.
+  Calling a team member works the same as for calling a tool: simply, the only argument you can give in the call is 'task', a long string explaining your task.
+  Given that this team member is a real human, you should be very verbose in your task.
+  Here is a list of the team members that you can call:
+  {%- for agent in managed_agents.values() %}
+  - {{ agent.name }}: {{ agent.description }}
+  {%- endfor %}
+  {%- else %}
+  {%- endif %}
+
+  Here are the rules you should always follow to solve your task:
+  1. Always provide a 'Thought:' sequence, and a 'Code:\n```py' sequence ending with '```<end_code>' sequence, else you will fail.
+  2. Use only variables that you have defined!
+  3. Always use the right arguments for the tools. DO NOT pass the arguments as a dict as in 'answer = wiki({'query': "What is the place where James Bond lives?"})', but use the arguments directly as in 'answer = wiki(query="What is the place where James Bond lives?")'.
+  4. Take care to not chain too many sequential tool calls in the same code block, especially when the output format is unpredictable. For instance, a call to search has an unpredictable return format, so do not have another tool call that depends on its output in the same block: rather output results with print() to use them in the next block.
+  5. Call a tool only when needed, and never re-do a tool call that you previously did with the exact same parameters.
+  6. Don't name any new variable with the same name as a tool: for instance don't name a variable 'final_answer'.
+  7. Never create any notional variables in our code, as having these in your logs will derail you from the true variables.
+  8. You can use imports in your code, but only from the following list of modules: {{authorized_imports}}
+  9. The state persists between code executions: so if in one step you've created variables or imported modules, these will all persist.
+  10. Don't give up! You're in charge of solving the task, not providing directions to solve it.
+
+  Now Begin! If you solve the task correctly, you will receive a reward of $1,000,000.
+"planning":
+  "initial_facts": |-
+    Below I will present you a task.
+
+    You will now build a comprehensive preparatory survey of which facts we have at our disposal and which ones we still need.
+    To do so, you will have to read the task and identify things that must be discovered in order to successfully complete it.
+    Don't make any assumptions. For each item, provide a thorough reasoning. Here is how you will structure this survey:
+
+    ---
+    ### 1. Facts given in the task
+    List here the specific facts given in the task that could help you (there might be nothing here).
+
+    ### 2. Facts to look up
+    List here any facts that we may need to look up.
+    Also list where to find each of these, for instance a website, a file... - maybe the task contains some sources that you should re-use here.
+
+    ### 3. Facts to derive
+    List here anything that we want to derive from the above by logical reasoning, for instance computation or simulation.
+
+    Keep in mind that "facts" will typically be specific names, dates, values, etc. Your answer should use the below headings:
+    ### 1. Facts given in the task
+    ### 2. Facts to look up
+    ### 3. Facts to derive
+    Do not add anything else.
+  "initial_plan": |-
+    You are a world expert at making efficient plans to solve any task using a set of carefully crafted tools.
+
+    Now for the given task, develop a step-by-step high-level plan taking into account the above inputs and list of facts.
+    This plan should involve individual tasks based on the available tools, that if executed correctly will yield the correct answer.
+    Do not skip steps, do not add any superfluous steps. Only write the high-level plan, DO NOT DETAIL INDIVIDUAL TOOL CALLS.
+    After writing the final step of the plan, write the '\n<end_plan>' tag and stop there.
+
+    Here is your task:
+
+    Task:
+    ```
+    {{task}}
+    ```
+    You can leverage these tools:
+    {%- for tool in tools.values() %}
+    - {{ tool.name }}: {{ tool.description }}
+        Takes inputs: {{tool.inputs}}
+        Returns an output of type: {{tool.output_type}}
+    {%- endfor %}
+
+    {%- if managed_agents and managed_agents.values() | list %}
+    You can also give tasks to team members.
+    Calling a team member works the same as for calling a tool: simply, the only argument you can give in the call is 'request', a long string explaining your request.
+    Given that this team member is a real human, you should be very verbose in your request.
+    Here is a list of the team members that you can call:
+    {%- for agent in managed_agents.values() %}
+    - {{ agent.name }}: {{ agent.description }}
+    {%- endfor %}
+    {%- else %}
+    {%- endif %}
+
+    List of facts that you know:
+    ```
+    {{answer_facts}}
+    ```
+
+    Now begin! Write your plan below.
+  "update_facts_pre_messages": |-
+    You are a world expert at gathering known and unknown facts based on a conversation.
+    Below you will find a task, and a history of attempts made to solve the task. You will have to produce a list of these:
+    ### 1. Facts given in the task
+    ### 2. Facts that we have learned
+    ### 3. Facts still to look up
+    ### 4. Facts still to derive
+    Find the task and history below:
+  "update_facts_post_messages": |-
+    Earlier we've built a list of facts.
+    But since in your previous steps you may have learned useful new facts or invalidated some false ones.
+    Please update your list of facts based on the previous history, and provide these headings:
+    ### 1. Facts given in the task
+    ### 2. Facts that we have learned
+    ### 3. Facts still to look up
+    ### 4. Facts still to derive
+
+    Now write your new list of facts below.
+  "update_plan_pre_messages": |-
+    You are a world expert at making efficient plans to solve any task using a set of carefully crafted tools.
+
+    You have been given a task:
+    ```
+    {{task}}
+    ```
+
+    Find below the record of what has been tried so far to solve it. Then you will be asked to make an updated plan to solve the task.
+    If the previous tries so far have met some success, you can make an updated plan based on these actions.
+    If you are stalled, you can make a completely new plan starting from scratch.
+  "update_plan_post_messages": |-
+    You're still working towards solving this task:
+    ```
+    {{task}}
+    ```
+
+    You can leverage these tools:
+    {%- for tool in tools.values() %}
+    - {{ tool.name }}: {{ tool.description }}
+        Takes inputs: {{tool.inputs}}
+        Returns an output of type: {{tool.output_type}}
+    {%- endfor %}
+
+    {%- if managed_agents and managed_agents.values() | list %}
+    You can also give tasks to team members.
+    Calling a team member works the same as for calling a tool: simply, the only argument you can give in the call is 'task'.
+    Given that this team member is a real human, you should be very verbose in your task, it should be a long string providing informations as detailed as necessary.
+    Here is a list of the team members that you can call:
+    {%- for agent in managed_agents.values() %}
+    - {{ agent.name }}: {{ agent.description }}
+    {%- endfor %}
+    {%- else %}
+    {%- endif %}
+
+    Here is the up to date list of facts that you know:
+    ```
+    {{facts_update}}
+    ```
+
+    Now for the given task, develop a step-by-step high-level plan taking into account the above inputs and list of facts.
+    This plan should involve individual tasks based on the available tools, that if executed correctly will yield the correct answer.
+    Beware that you have {remaining_steps} steps remaining.
+    Do not skip steps, do not add any superfluous steps. Only write the high-level plan, DO NOT DETAIL INDIVIDUAL TOOL CALLS.
+    After writing the final step of the plan, write the '\n<end_plan>' tag and stop there.
+
+    Now write your new plan below.
+"managed_agent":
+  "task": |-
+    You're a helpful agent named '{{name}}'.
+    You have been submitted this task by your manager.
+    ---
+    Task:
+    {{task}}
+    ---
+    You're helping your manager solve a wider task: so make sure to not provide a one-line answer, but give as much information as possible to give them a clear understanding of the answer.
+
+    Your final_answer WILL HAVE to contain these parts:
+    ### 1. Task outcome (short version):
+    ### 2. Task outcome (extremely detailed version):
+    ### 3. Additional context (if relevant):
+
+    Put all these in your final_answer tool, everything that you do not pass as an argument to final_answer will be lost.
+    And even if your task resolution is not successful, please return as much context as possible, so that your manager can act upon this feedback.
+  "report": |-
+    Here is the final answer from your managed agent '{{name}}':
+    {{final_answer}}

pyproject.toml

@@ -0,0 +1,2 @@
+[tool.ruff]
+line-length = 79

requirements.txt

@@ -1,2 +1,4 @@
 gradio
-requests
+requests
+smolagents[toolkit]
+wikipedia-api