https://github.com/continuedev/proxy-server
Inference Proxy Server
https://github.com/continuedev/proxy-server
Last synced: 5 months ago
JSON representation
Inference Proxy Server
- Host: GitHub
- URL: https://github.com/continuedev/proxy-server
- Owner: continuedev
- Created: 2023-06-15T16:37:44.000Z (almost 3 years ago)
- Default Branch: main
- Last Pushed: 2023-07-28T01:12:04.000Z (over 2 years ago)
- Last Synced: 2025-01-09T11:31:42.120Z (about 1 year ago)
- Language: Python
- Size: 14.6 KB
- Stars: 3
- Watchers: 1
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# proxy-server
Inference Proxy Server
Run `gcloud run deploy` to deploy the Docker container to production.
Run locally with `docker build -t proxy_server . && docker run -v ~/.config:/root/.config -t -p 8080:8080 proxy_server`.
The `-v ~/.config:/root/.config` flag is required to allow the container to access the default Google Cloud credentials when you are running on your local machine. If you don't have these setup, do so with `gcloud auth application-default login`.
The container also depends on a Cloud SQL instance.