FileNotFoundError in code_executor_agent from tutorial

[jeannot-prvlimburg]

The following code from the tutorial:

from autogen import ConversableAgent
from autogen.coding import LocalCommandLineCodeExecutor

# Create a temporary directory to store the code files.
temp_dir = tempfile.TemporaryDirectory()

# Create a local command line code executor.
executor = LocalCommandLineCodeExecutor(
    timeout=10,  # Timeout for each code execution in seconds.
    work_dir=temp_dir.name,  # Use the temporary directory to store the code files.
)

# Create an agent with code executor configuration.
code_executor_agent = ConversableAgent(
    "code_executor_agent",
    llm_config=False,  # Turn off LLM for this agent.
    code_execution_config={"executor": executor},  # Use the local command line code executor.
    human_input_mode="ALWAYS",  # Always take human input for this agent for safety.
)`

config_list = [{"model": "gpt-4", 
                "api_key": os.environ["AZURE_OPENAI_API_KEY"],
                "base_url": os.environ["AZURE_OPENAI_ENDPOINT"],
                "api_type": "azure",
                "api_version": "2024-02-15-preview"}]

# The code writer agent's system message is to instruct the LLM on how to use
# the code executor in the code executor agent.
code_writer_system_message = """You are a helpful AI assistant.
Solve tasks using your coding and language skills.
In the following cases, suggest python code (in a python coding block) or shell script (in a sh coding block) for the user to execute.
1. When you need to collect info, use the code to output the info you need, for example, browse or search the web, download/read a file, print the content of a webpage or a file, get the current date/time, check the operating system. After sufficient info is printed and the task is ready to be solved based on your language skill, you can solve the task by yourself.
2. When you need to perform some task with code, use the code to perform the task and output the result. Finish the task smartly.
Solve the task step by step if you need to. If a plan is not provided, explain your plan first. Be clear which step uses code, and which step uses your language skill.
When using code, you must indicate the script type in the code block. The user cannot provide any other feedback or perform any other action beyond executing the code you suggest. The user can't modify your code. So do not suggest incomplete code which requires users to modify. Don't use a code block if it's not intended to be executed by the user.
If you want the user to save the code in a file before executing it, put # filename: <filename> inside the code block as the first line. Don't include multiple code blocks in one response. Do not ask users to copy and paste the result. Instead, use 'print' function for the output when relevant. Check the execution result returned by the user.
If the result indicates there is an error, fix the error and output the code again. Suggest the full code instead of partial code or code changes. If the error can't be fixed or if the task is not solved even after the code is executed successfully, analyze the problem, revisit your assumption, collect additional info you need, and think of a different approach to try.
When you find an answer, verify the answer carefully. Include verifiable evidence in your response if possible.
Reply 'TERMINATE' in the end when everything is done.
"""

code_writer_agent = ConversableAgent(
    "code_writer_agent",
    system_message=code_writer_system_message,
    llm_config={"config_list": config_list},
    code_execution_config=False,  # Turn off code execution for this agent.
)

chat_result = code_executor_agent.initiate_chat(
    code_writer_agent,
    message="Write Python code to calculate and print the 14th Fibonacci number.",
)

Results for me in this output and error:

Write Python code to calculate and print the 14th Fibonacci number.

--------------------------------------------------------------------------------

>>>>>>>> USING AUTO REPLY...
code_writer_agent (to code_executor_agent):

Sure, Fibonacci numbers can be calculated using various methods, such as using the iterative method, using recursion, or using the matrix exponentiation method. I will implement the iterative method because it is the most efficient way for this small scale problem.

The Fibonacci Series is a series of numbers in which each number is the sum of the two preceding numbers. Usually, the sequence starts with 0 and 1.

Here is the Python code to calculate and print the 14th Fibonacci number using the iterative method:

python
def fibonacci(n):
    if n<=0:
        return "Input should be greater than 0"
    elif n==1:
        return 0
    elif n==2:
        return 1
    else:
        a,b = 0,1
        for i in range(2,n):
            a, b = b, a+b
        return b

print(fibonacci(14))

You can run this Python script to get the 14th Fibonacci number.

--------------------------------------------------------------------------------

>>>>>>>> NO HUMAN INPUT RECEIVED.

>>>>>>>> USING AUTO REPLY...

>>>>>>>> EXECUTING CODE BLOCK (inferred language is python)...`

`FileNotFoundError                         Traceback (most recent call last)
Cell In[37], [line 1](vscode-notebook-cell:?execution_count=37&line=1)
----> [1](vscode-notebook-cell:?execution_count=37&line=1) chat_result = code_executor_agent.initiate_chat(
      [2](vscode-notebook-cell:?execution_count=37&line=2)     code_writer_agent,
      [3](vscode-notebook-cell:?execution_count=37&line=3)     message="Write Python code to calculate and print the 14th Fibonacci number.",
      [4](vscode-notebook-cell:?execution_count=37&line=4) )

File c:\ProgramData\Anaconda3\Lib\site-packages\autogen\agentchat\conversable_agent.py:1087, in ConversableAgent.initiate_chat(self, recipient, clear_history, silent, cache, max_turns, summary_method, summary_args, message, **kwargs)
   [1085](file:///C:/ProgramData/Anaconda3/Lib/site-packages/autogen/agentchat/conversable_agent.py:1085)     else:
   [1086](file:///C:/ProgramData/Anaconda3/Lib/site-packages/autogen/agentchat/conversable_agent.py:1086)         msg2send = self.generate_init_message(message, **kwargs)
-> [1087](file:///C:/ProgramData/Anaconda3/Lib/site-packages/autogen/agentchat/conversable_agent.py:1087)     self.send(msg2send, recipient, silent=silent)
   [1088](file:///C:/ProgramData/Anaconda3/Lib/site-packages/autogen/agentchat/conversable_agent.py:1088) summary = self._summarize_chat(
   [1089](file:///C:/ProgramData/Anaconda3/Lib/site-packages/autogen/agentchat/conversable_agent.py:1089)     summary_method,
   [1090](file:///C:/ProgramData/Anaconda3/Lib/site-packages/autogen/agentchat/conversable_agent.py:1090)     summary_args,
   [1091](file:///C:/ProgramData/Anaconda3/Lib/site-packages/autogen/agentchat/conversable_agent.py:1091)     recipient,
   [1092](file:///C:/ProgramData/Anaconda3/Lib/site-packages/autogen/agentchat/conversable_agent.py:1092)     cache=cache,
   [1093](file:///C:/ProgramData/Anaconda3/Lib/site-packages/autogen/agentchat/conversable_agent.py:1093) )
   [1094](file:///C:/ProgramData/Anaconda3/Lib/site-packages/autogen/agentchat/conversable_agent.py:1094) for agent in [self, recipient]:

File c:\ProgramData\Anaconda3\Lib\site-packages\autogen\agentchat\conversable_agent.py:723, in ConversableAgent.send(self, message, recipient, request_reply, silent)
    [721](file:///C:/ProgramData/Anaconda3/Lib/site-packages/autogen/agentchat/conversable_agent.py:721) valid = self._append_oai_message(message, "assistant", recipient)
    [722](file:///C:/ProgramData/Anaconda3/Lib/site-packages/autogen/agentchat/conversable_agent.py:722) if valid:
--> [723](file:///C:/ProgramData/Anaconda3/Lib/site-packages/autogen/agentchat/conversable_agent.py:723)     recipient.receive(message, self, request_reply, silent)
    [724](file:///C:/ProgramData/Anaconda3/Lib/site-packages/autogen/agentchat/conversable_agent.py:724) else:
...
   [1042](file:///C:/ProgramData/Anaconda3/Lib/pathlib.py:1042) if "b" not in mode:
   [1043](file:///C:/ProgramData/Anaconda3/Lib/pathlib.py:1043)     encoding = io.text_encoding(encoding)
-> [1044](file:///C:/ProgramData/Anaconda3/Lib/pathlib.py:1044) return io.open(self, mode, buffering, encoding, errors, newline)

FileNotFoundError: [Errno 2] No such file or directory: 'C:\\Users\\<my_name>\\AppData\\Local\\Temp\\tmp7_1wu7fx\\tmp_code_ffccb3622f5d953bb2285e6ae3424fc2.py'

Any idea on why this happens?

[jeannot-prvlimburg]

The solution that worked for me was adding code_execution_config to the code_writer_agent definition.

code_writer_agent = ConversableAgent(
    "code_writer_agent",
    system_message=code_writer_system_message,
    llm_config={"config_list": config_list},
    code_execution_config={"executor": executor},
)