crewAI
crewAI copied to clipboard
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
Adds DE language support. Not tested yet, try to do it soon. Translated with GPT-3.5 and proof read / compared manually. GPT-3.5 almost returned the perfect result, only a single...
After facing no problems running crewai, facing the following error: > ImportError: cannot import name 'InstanceOf' from 'pydantic' (/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/pydantic/init.cpython-311-darwin.so) Tried uninstall-reinstall both crewai and pydantic. Any suggestions?
Added nl.json for Dutch language support. Not tested yet as not sure which pytests should be run for language support check. Which pytests should pass for this language support to...
Thanks for the great toolset. Had tried it with a locally running _Mistral 7b_ and found that this LLM, while being very usable on commodity HW, doesn't always get case...
From discord: > only as part of prompts so far, but seems like a interesting approach, maybe I could make a concepts of boolean tasks and you could have different...
Would be great to leverage an LLM to populate the parameters for all the agents and tasks. The basic idea is here, but it needs polishing: https://github.com/yanniedog/crewai-autocrew
Its possible to use different service than browseless as they drop free tier now (I cant find any information about free tier now and I dont want to be charged...
[DEBUG]: Working Agent: Investigador [INFO]: Starting Task: Realiza un análisis exhaustivo de los últimos avances en IA en 2024. Identifica las tendencias clave, las tecnologías revolucionarias y los posibles impactos...
I am playing around with CrewAI with the goal of using it in our production app. I have done a basic setup where I am trying to setup an agent...