# Alpaca

Alpaca is a background technician for the Islandora digital library system. It is open source and self-hosted, installable on Docker Hub.

Canonical page: https://ourlocalhost.com/app/6037/alpaca

## Description

Alpaca is a background technician for the Islandora digital library system. It automatically organises and moves your data between different tools, ensuring that when you upload a file, tasks like creating thumbnails or extracting text happen smoothly and reliably in the background without manual effort.

## Platform availability

Available on 0 of 10 platforms.

## Health score

38/100 (Low), based on 5 of 5 factors.
- Maintained: 0 (last commit 1271 days ago)
- Popular: 90 (30,231 GitHub stars)
- Easy to install: 25 (0 install platforms, install notes, Docker image)
- Light to run: 20 (16 GB minimum RAM, runs on ARM)
- Security check: 75 (no serious findings)

## Links

- GitHub: https://github.com/alpacahq
- Docker Hub: https://hub.docker.com/r/islandora/alpaca
- Official website: https://crfm.stanford.edu/2023/03/13/alpaca.html

## Common questions

### Do I need separate installs for the Alpaca server and the chat client?

No, the project uses one static binary. Run alpaca serve on the model-hosting machine and alpaca chat on the machines that use it.

### On which machine should the Alpaca serve process run?

The source says to run alpaca serve on the machine with the GPU.

### Can I use an OpenAI-compatible client with the hosted Alpaca model?

Yes, the hosted model is exposed as a real API that can be used by anything that speaks the OpenAI protocol.

### Can the Alpaca model be run locally without a remote API?

Yes, Serge is described as running Alpaca and LLaMA models entirely locally without needing a remote API.

---
Source: Our Local Host (https://ourlocalhost.com/app/6037/alpaca), the self-hosted and open-source app directory.
