The “langchian deep_agent” is calling the sub-agent very slowly. Could you please tell me how to solve this problem? I have only loaded one sub-agent.
Hello @xiaoyang , could you please share some code?
ok, here are some code
agent = create_deep_agent(
model=model,
tools=[
],
subagents=SUBAGENTS,
system_prompt=MAIN_AGENT_PROMPT,
backend=FilesystemBackend(root_dir=r"\Parse\src\api", virtual_mode=True),
interrupt_on={
}
)
Hi @xiaoyang what do you mean by “is calling the sub-agent very slowly”. What model are you using? Are you using thinking mode? Since you are using create_deep_agent this intentionally works slower compared to create_agent.
- Could you try using different/faster model and observe its behaviour
- Do you have any logging? You could add some output logging or middleware to observe where exactly it works slowly
感觉思考非常慢，底层应该多次在反复思考
i am use deepseek-chat model , and this model has only one tool.
@xiaoyang is this self-hosted?
use crate_deep_agent is model self-hosted
I think so that is the reason why your execution is too slow. Can you just do a simple request, and perhaps see what the inference speed of your model is.
yes, i think deep_agent send multiple requests to the API . so it was very slow
So that is the problem, I would recommend you host your model on better specs or use a mini version of the model.