I build a large-language model based "agent" that can can execute small tasks by using a Python REPL and pre-implemented methods. The "agent loop" is based on ReAct.

The agent can look up methods using a `method_search()` method that uses semantic search on the indexed Python methods.

I documented my findings in this blogpost and the following repo: https://github.com/peterroelants/gpt_react_repl_w_method_sea...

Great experiment. But what was the 6. task? It was missing in the blog.

Thanks for flagging, the first task was missing from the list. I updated the blogpost.