Open ajeetraina opened 1 year ago
Thanks much.
This is the main website: www.llmdash.com.
We are aiming for submission to the AI/ML Hackathon on 11/7.
The actual cache is a Rust server which comes in the form of a single container, I will open the cache repo once we finish the integration and are ready for release.
The cache supports the full OpenAI API (it is a write-through cache), so you point your open AI SDK to the cache, and the cache talks to open ai).
Tried the extension and it came up really well on Docker Desktop. Still trying to figure out how to use it. If you add details, that would be great.
Just to let you know that you can use the self-publishing process to get your extension in the marketplace quickly.
You can learn more about our publishing process here: https://docs.docker.com/desktop/extensions-sdk/extensions/publish/