Bug fix for 0.1.2 where ImportError "soundfile" is raised when agent reaches max_steps. #151
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…on serializable format. It also parses arguments to tool calls.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
With v1.2.0, a bug got introduced to the code in wich the below error is raised when the agent is reaching max_steps.
Traceback (most recent call last): File "/home/azureuser/smolagents/examples/tool_calling_agent_from_any_llm.py", line 26, in <module> print(agent.run("What's the weather like in Paris?")) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/azureuser/smolagents/src/smolagents/agents.py", line 514, in run return self.direct_run(self.task) ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/azureuser/smolagents/src/smolagents/agents.py", line 623, in direct_run return handle_agent_output_types(final_answer) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/azureuser/smolagents/src/smolagents/types.py", line 280, in handle_agent_output_types return _v(output) ^^^^^^^^^^ File "/home/azureuser/smolagents/src/smolagents/types.py", line 193, in __init__ raise ImportError("soundfile must be installed in order to handle audio.") ImportError: soundfile must be installed in order to handle audio.The problem is that in
provide_final_answer()a Message object is returned instead of a str. This is handled as Audio type byhandle_agent_output_types.I fixed it by editing
provide_final_answer()to return the same format as thefinal_answertool.