Kenny Vaneetvelde
Kenny Vaneetvelde
The issue is due to the usage of the instruct GPT model, I believe, try **gpt-3.5-turbo-0125** with ChatOpenAI as @HenryHengZJ suggested
Since I did a deploy myself on GCP today I decided to test this, I don't know if it used to be bugged, but at least it works for me...
 Works perfectly fine like this for me, I am using LM Studio, I just have API-key set to "none" in the credentials, Note the IP address for you will...
They also don't support certain things inside the schema definitions such as "min_length", "default", ... I don't have an exhaustive list, but I believe instructor should filter these out and...
@jxnl Check my comment, unless you suggest doing that in a separate PR
On first sight your agents look good, what your example here is missing is the overarching orchestrator agent, but instead of the tool input schemas, you would be doing a...
> we do use the output_schema there by placing the CalculatorInputSchema. Yes, absolutely correct, this is also demonstrated for example in the query generation agent in [this example](https://github.com/BrainBlend-AI/atomic-agents/blob/main/atomic-examples/deep-research/deep_research/agents/query_agent.py) Here you...
Hello, We are currently reworking the way tools are distributed. We will be ripping them out of this package and providing them in a different way where you can take...
@fayzfi Should be max. another week to be usable. The CLI I am creating to get the tools is 90% done but I want to make sure we have a...
Well, the CLI is there, tools have been migrated, and everything is now ready for people to take ownership over the tools and modify to their hearts' content. Closing the...