Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Docker Compose Enhancements for LocalGPT Deployment #707

Open
wants to merge 10 commits into
base: main
Choose a base branch
from

Conversation

tosin2013
Copy link

@tosin2013 tosin2013 commented Jan 9, 2024

Docker Compose Enhancements for LocalGPT Deployment

Key Improvements:

  • Streamlined LocalGPT API and UI Deployment: This update simplifies the process of simultaneously deploying the LocalGPT API and its user interface using a single Docker Compose file.
  • Flexible Device Utilization: Users can now conveniently choose between CPU or GPU devices (if available) by setting the DEVICE_TYPE environment variable.
  • Customizable Source Documents: The SOURCE_DOCUMENTS environment variable enables effortless specification of the directory containing source documents for LocalGPT to process.
  • Efficient Volume Mounting: The configuration maps local cache and source document directories to corresponding container paths, ensuring data persistence and accessibility.
  • Network Configuration: A dedicated network, localgpt-network, facilitates seamless communication between the API and UI containers.

Key Changes:

  • Structure: The Docker Compose file is now organized into two distinct services:
    • localgpt: Responsible for building and running the LocalGPT API container.
    • localgpt-ui: Manages the construction and execution of the LocalGPT UI container.
  • Environment Variables: The introduction of DEVICE_TYPE and SOURCE_DOCUMENTS variables empowers users to tailor the deployment to their specific requirements.
  • Volume Mounting: The configuration ensures persistence of cache and source documents.
  • Network: The establishment of a dedicated network streamlines communication between the services.

@sandykadam
Copy link

sandykadam commented Mar 22, 2024

Thanks @tosin2013 for this fix. I forked your repo and was trying to run on local but for some reason "localgpt" doesn't run on any port, only "localgpt-localgpt-ui" runs on 5111
And when I submit query from chat UI i get "Internal server error"

Any suggestions appreciated, thanks in advance.

Screenshot 2024-03-22 at 16 32 26

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants