[Question]: why task_executor occupy too much memory

[isaacqian]

Self Checks

• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (Language Policy).
• Non-english title submitions will be closed directly ( 非英文标题的提交将会被直接关闭 ) (Language Policy).
• Please do not modify this template :) and fill in all the required fields.

Describe your problem

I launch ragflow from source, task occupy many memory, But I not parse any file, Does chat has effact? My Server's memory is 64GB, many task make memory rate to more 90%, hope anyone can help me, thank you very much

[KevinHuSh]

I suggest you to use slim version of docker image which occupies less RAM since no local embedding model loaded.

[isaacqian]

I launch project according to this guide, how to switch to slim @KevinHuSh

[KevinHuSh]

git clone https://github.com/infiniflow/ragflow.git
cd ragflow/
uv run download_deps.py
docker build -f Dockerfile.deps -t infiniflow/ragflow_deps .
docker build --build-arg LIGHTEN=1 -f Dockerfile -t infiniflow/ragflow:nightly-slim .