Introducing smolagents: simple agents that write actions in code.
huggingface.co · 1,832 words · saved by 1 readers
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Today we are launching smolagents, a very simple library that unlocks agentic capabilities for language models. Here’s a glimpse: from smolagents import CodeAgent, DuckDuckGoSearchTool, HfApiModel agent = CodeAgent(tools=[DuckDuckGoSearchTool()], model=HfApiModel()) agent.run("How many seconds would it take for a leopard at full speed to run through Pont des Arts?") Table of Contents 🤔 What are agents? ✅ When to use agents / ⛔ when to avoid them Code agents Introducing smolagents: making agents simple 🥳 Building an agent How strong are open models for agentic workflows? Next…
related reading
- What are agents? 🤔 · Hugging Facehuggingface.co
- Building Effective AI Agents \ Anthropicanthropic.com
- Building Effective AI Agents \ Anthropicanthropic.com
- LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
- smolagents · Hugging Facehuggingface.co
- Building reliable AI agents · parth sareenparthsareen.com
- Designing agentic loopssimonwillison.net
- LangChain: the open agent platform to own your intelligencelangchain.com
- Arjun Virkarjunvirk.com
- Agent Evaluation: A Detailed Guidecameronrwolfe.substack.com
- Using tweets gathered from https://til.simonwillison.net/twitter/collecting-repliesgist.github.com
- Adding payments to your LLM agentic workflowsstripe.dev