Error when using Huggingface inference

[Himasnhu-AT]

Context:

I'm trying out using Agno with hugging face inference, but getting an error.

question:

How can i create my own tools and use them with agents

ERROR details:

agent = Agent(
    model=HuggingFace(
        id="meta-llama/Meta-Llama-3-70B-Instruct",
    ),
    tools=[DuckDuckGoTools(), Newspaper4kTools()],
    description="You are a senior NYT researcher writing an article on a topic.",
    instructions=[
        "For a given topic, search for the top 5 links.",
        "Then read each URL and extract the article text, if a URL isn't available, ignore it.",
        "Analyse and prepare an NYT worthy article based on the information.",
    ],
    markdown=True,
    show_tool_calls=True,
    add_datetime_to_instructions=True,
)

agent.print_response("Simulation theory", stream=True)

Error:

▰▰▰▰▰▰▱ Thinking...
┏━ Message ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃                                                                                                                 ┃
┃ Simulation theory                                                                                               ┃
┃                                                                                                                 ┃
┗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┛
---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
[<ipython-input-38-576a1e1a3861>](https://localhost:8080/#) in <cell line: 0>()
     32 )
     33 
---> 34 agent.print_response("Simulation theory", stream=True)

3 frames
[/usr/local/lib/python3.11/dist-packages/agno/agent/agent.py](https://localhost:8080/#) in print_response(self, message, messages, audio, images, videos, stream, markdown, show_message, show_reasoning, show_full_reasoning, console, tags_to_include_in_markdown, **kwargs)
   3358                 if render:
   3359                     live_log.update(Group(*panels))
-> 3360                 for resp in self.run(
   3361                     message=message, messages=messages, audio=audio, images=images, videos=videos, stream=True, **kwargs
   3362                 ):

[/usr/local/lib/python3.11/dist-packages/agno/agent/agent.py](https://localhost:8080/#) in _run(self, message, stream, audio, images, videos, messages, stream_intermediate_steps, **kwargs)
    532         if self.stream:
    533             model_response = ModelResponse(content="")
--> 534             for model_response_chunk in self.model.response_stream(messages=run_messages.messages):
    535                 # If the model response is an assistant_response, yield a RunResponse with the content
    536                 if model_response_chunk.event == ModelResponseEvent.assistant_response.value:

[/usr/local/lib/python3.11/dist-packages/agno/models/base.py](https://localhost:8080/#) in response_stream(self, messages)
    455                 assistant_message.audio_output = stream_data.response_audio
    456             if stream_data.response_tool_calls and len(stream_data.response_tool_calls) > 0:
--> 457                 assistant_message.tool_calls = self.parse_tool_calls(stream_data.response_tool_calls)
    458 
    459             # Add assistant message to messages

[/usr/local/lib/python3.11/dist-packages/agno/models/huggingface/huggingface.py](https://localhost:8080/#) in parse_tool_calls(tool_calls_data)
    327         for _tool_call in tool_calls_data:
    328             _index = _tool_call.index
--> 329             _tool_call_id = _tool_call.id
    330             _tool_call_type = _tool_call.type
    331             _function_name = _tool_call.function.name if _tool_call.function else None

AttributeError: 'str' object has no attribute 'id'

[manthanguptaa]

Hey @Himasnhu-AT! Thanks so much for raising this issue. I was able to replicate it on my end, too. We’ll make it a priority to fix this as soon as possible. Really appreciate your patience, and feel free to reach out if you have any more questions or concerns in the meantime!

[wakeupmh]

relates to: #2161 (comment)