crewAI

crewAI copied to clipboard

Crew Agents not using system message properly

4

Is there a reason why the Crew Agents do not use the system message properly to set up their roles. I think we maybe able to improve the performance of...

TheBitmonkey

Support Local Language Model (LLM) with API

2

Subject: Support Local Language Model (LLM) with API I hope this message finds you well. I am writing to bring attention to an issue I have encountered while working with...

Zakarialabib

I've been testing more complex tasks and I see we get hang outs, has anyone tried changing the values in the code to allow longer conversations to occur? Note: Please...

tendaysaweek

Task Description updating

3

``` MainTask = """Write the snake game in python""", # Create tasks for your agents task1 = Task( description=MainTask, agent=coder ) ``` gives an error from pydantic about description must...

iplayfast

Inquiry Regarding Integration with Local Models and Process Customisation

1

Dear CrewAI Maintainers, I hope this message finds you well. I am reaching out to discuss a couple of aspects of CrewAI that I believe could significantly enhance its utility...

yihong1120

code execution not working properly

2

I have a use case for automatically creating Dockerfile. kubernetes yamls and github actions file based on the provided repo Here is my code , Architect agent is able to...

debianmaster

Human Input Mode to allow choosing between Alway, Terminate or Never

1

in the human_input mode, can you please add the ability so the use can pick wether they want to have an input in langchain's thought or not? This will help...

naseerfaheem

Create a benchmark test for any prompt updates

1

I have some local scripts but would be nice to have it as a proper test something to meaure quality prompts get updated and translated into different language

joaomdmoura

paipeline

SashaXser