An open API service indexing awesome lists of open source software.

https://github.com/smallrye/smallrye-llm

Experimentation around LLM and MicroProfile
https://github.com/smallrye/smallrye-llm

Last synced: 6 months ago
JSON representation

Experimentation around LLM and MicroProfile

Awesome Lists containing this project

README

          

:ci: https://github.com/smallrye/smallrye-llm/actions?query=workflow%3A%22SmallRye+Build%22

image:https://github.com/smallrye/smallrye-llm/workflows/SmallRye%20Build/badge.svg?branch=main[link={ci}]
image:https://img.shields.io/github/license/smallrye/smallrye-llm.svg["License", link="http://www.apache.org/licenses/LICENSE-2.0"]
image:https://img.shields.io/maven-central/v/io.smallrye.llm/smallrye-llm?color=green["Maven", link="https://central.sonatype.com/search?q=io.smallrye.llm%3Asmallrye-llm-parent"]

= 🚀 Smallrye LLM

Experimentation around LLM and MicroProfile

== How to run examples

=== Use LM Studio

==== Install LM Studio

https://lmstudio.ai/

==== Download model

Mistral 7B Instruct v0.2

==== Run

On left goto "local server", select the model in dropdown combo on the top, then start server

=== Use Ollama

Running Ollama with the llama3.1 model:

[source,bash]
----
CONTAINER_ENGINE=$(command -v podman || command -v docker)
$CONTAINER_ENGINE run -d --rm --name ollama --replace --pull=always -p 11434:11434 -v ollama:/root/.ollama --stop-signal=SIGKILL docker.io/ollama/ollama
$CONTAINER_ENGINE exec -it ollama ollama run llama3.1
----

=== Run the examples

Go to each example `README.md` to see how to execute the example.

== Contributing

If you want to contribute, please have a look at link:CONTRIBUTING.md[CONTRIBUTING.md].

== License

This project is licensed under the Apache License 2.0 - see the link:LICENSE[LICENSE] file for details.