Langflow API slow compared to Playground.

[Frenz86]

Bug Description

I'm running langflow-1.0.12 as a docker container, the playground seems much faster than using the webhook. I thought Langsmith was the cause of the problem but, although the playground without Langsmith is much faster, via API the problem still persist.

Reproduction

Try to use any flow by playground and then by webjook.

Expected behavior

The inference time is 3 time slow on webhook

Who can help?

No response

Operating System

Ubuntu 22.04

Langflow Version

1.0.12

Python Version

3.12

Screenshot

No response

Flow File

No response

[dosubot[bot]]

Hey @Frenz86! I'm here to help you with any bugs, questions, or contributions. Let's work together to solve the issue you're facing.

The slower inference time via the webhook in Langflow version 1.0.12 running as a Docker container on Ubuntu 22.04 with Python 3.12 is likely due to the Dockerfile using Python 3.10-slim instead of Python 3.12. This discrepancy can lead to performance issues.

To resolve this, you should modify the Dockerfile to use Python 3.12. Here is the updated Dockerfile:

FROM langflowai/backend_build as backend_build

FROM python:3.12-slim
WORKDIR /app

RUN apt-get update && apt-get install git -y

COPY --from=backend_build /app/dist/*.whl /app/
RUN pip install langflow-*.whl
RUN rm *.whl

EXPOSE 80

CMD [ "uvicorn", "--host", "0.0.0.0", "--port", "7860", "--factory", "langflow.main:create_app" ]

By ensuring the Docker container uses Python 3.12, you can align the environment more closely with the one used in the Playground, potentially improving the inference time ^[1].

To continue talking to Dosu, mention @dosu.

[carlosrcoelho]

@Frenz86

Do you need any assistance with this case? If not, please let us know if this issue can be closed.

Try the new version 1.0.15

[carlosrcoelho]

Thank you for your contribution! This issue will be closed. If you have any questions or encounter another problem, please open a new issue and we will be ready to assist you.