8000 Release v0.3 - More providers, resoning models support and structured output in console · MaestroError/LarAgent · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

v0.3 - More providers, resoning models support and structured output in console

Compare
Choose a tag to compare
@MaestroError MaestroError released this 26 Mar 13:10
· 56 commits to main since this release
956e515

Release 0.3.0 changes

  • OpenAiCompatible driver: allows use of any provider compatible with OpenAI API, including Ollama, vLLM, OpenRouter and many more
  • Support for reasoning models like o1 & o3: New contributor @yannelli added a developer message type that allows us to use reasoning models in the Agents! More Thinking = Smarter agents 💪
  • Complete chat removal: New command agent:chat:remove provides a way to completely remove chat histories and their associated keys for a specific agent.
  • Structured output in console for agent:chat command: Now you can test your agent with structured output
  • Updated docs & Refactored agent initialization process: Minor updates for better clarity and smoother processes

Check examples below 👇

Community server

We will:

  • Help developers implement LarAgent in their projects
  • Shape LarAgent's future by planning new features and making decisions
  • Share the latest news
  • Discuss ideas and collaborate with contributors

Join the fresh new LarAgent community server on Discord: https://discord.gg/NAczq2T9F8

Examples

OpenAiCompatible driver

420611702-feb07fce-fdd7-496d-9343-8bf28d240296

Support for reasoning models like o1 & o3

422420386-4eabfe4e-c56b-41ba-9a1e-c304ded1fdc4

Structured output in console for agent:chat command

424600093-d1126119-64f4-4f7d-9ed3-984982ad01b6
424600036-262cbdd6-9dd9-47f1-b1d3-2796b400c0dd

What's Changed

New Contributors

Full Changelog: 0.2.2...0.3.0

0