🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents. - huggingface/smolagents

An HF's Smolagent to automate molecular dynamics simulations using GROMACS. - virtualramblas/gromacs_smolagent

Hugging Face introduced a new code library last week to enable developers to easily build artificial intelligence (AI) agents. Dubbed smolagents, the tool defines the basic logic for general purpose simple AI agents that can perform actions by executing them in code. Smolagent can be connected with any open-source large language model (LLM) or a select number of cloud-based LLMs. Developers can also build tools to connect the external output part of the agent.

🤗 Prueba de concepto de un chat interactivo construido con Flask y Tailwind CSS. Utiliza smolagents para generar respuestas a preguntas. Incluye formateo básico de texto y una interfaz minimalista....

YouTube video by Richard Aragon

When I am using Qwen model in smolagent or Llamaindex, it’s giving error In smolagent, it’s giving following error: Error in generating model output: Client.post() got an unexpected keyword argument 'stream' In LlamaIndex, getting this error: RuntimeError: Cannot send a request, as the client has been closed.

401 errors are often caused by mistakes or malfunctions, but 402 errors are usually caused by exceeding the monthly usage limit. Hugging Face Payment Error 402 & You've Exceeded Monthly Quota Languages at Hugging Face > Whenever I want generate a response from the api it shows payment error 402 and this link “https://huggingface.co/api/inference-proxy/hf-inference/models/Qwen/QwQ-32B/v1/chat/completions”. After tapping on the link it showing “Sorry, we can’t find the page you are looking for.” Also showing this promise error in console “You have exceeded your monthly included credits for Inference Providers. Subscribe to PRO to get 20x more monthly allowance.”, I haven’t use a bit. I create a new account for t…

Hello @John6666 and @sabler I have given write permission for the token, tried to recreate the token twice, but was not able access the model. Still getting 402 error.

The token I’m using is set to WRITE, but like @John6666 said, you should be able to use READ just fine.

If you are unsure about token permissions, using a READ token makes it easy. Also, it seems that the key operation when copying and pasting may be the cause. Invalid token or no access to Hugging Face Beginners > Dont paste the token with ctrl+p, right click to paste it.

Hello @sabler I have paid for the Pro, still I am getting the error. Created a new token as well. What Permissions did you end setting for the token so that it could work

What are best practices to test smolagent agents? I guess one would need to mock the tools used by the agent, but I’m not sure what’s the best way to steer the test…

Can I somehow avoid using HfApiModel? How can I use the local models? I did not find explanation in any place. It asks me to buy the paid track for HF. And I just want to try out the smolagent framework.

I encountered a similar problem before. I used pip install and it was successfully installed but it still shows `ModuleNotFoundError` . I realized that I have two python folders, version 3.10 and 3.12. The files were downloaded in my python 3.12 folder but I am using python 3.10 as my kernel in VSCode. I just transferred the files to my python 3.10 folder and restarted the kernel. Though I haven’t tried using HuggingFace yet.