I want to build the one of the agent that not required any LLM support . Simple python function can handle its ( function will use SQLfluff). i tried without LLM and getting error to use LLM. is there any function or variable that will exclude LLM help for Agent
I could think of 2 ways to address this problem. Both seem like workarounds, but could get the job done -
Using CodeInterpreterTool - You can execute your code and use this tool within an agent. Two downsides of this are that the code would be executed in a sandboxed environment, which may not work for you. And secondly, it will anyways have to go through a LLM.
Using Custom Tool - You can create a small package of your code and expose it via an API. You can then invoke this API within your custom tool to get the result. Two downsides of this are that again result will have to go through LLM & the need to create an API.
Please note that I am new to CrewAI and these might not be the optimal solutions, but these are the ones I could think of.
Let me know if this helps, Thanks!
Looking more closely at your problem, it seems that your needs might be better addressed with the Flow paradigm, which gives you all the advantages of orchestrating methods, which can be pure Python code or whatever else you need, including (of course) crews and agents.
I suggest you take another look at the Flow documentation, especially right here where you’ll see an example that uses methods without any crew.