Integration of Groq LPU Inference generation (#140)

[symdec]

Following this issue : #140

• Add GroqGenerator class, taking inspiration from CohereGenerator and others (from the 2.0 release)
• Update managers.py to include this new generator
• Update README to precise the availability of this Groq Generation feature + section to recommend using the environment variable before launching Verba (to have updated models list)

The generation has been successfully tested locally with various Groq models :

• using the GROQ_API_KEY variable set in the .env file before the launch
• using no .env file and providing the API key in the graphical config interface

[weaviate-git-bot]

To avoid any confusion in the future about your contribution to Weaviate, we work with a Contributor License Agreement. If you agree, you can simply add a comment to this PR that you agree with the CLA so that we can merge.

beep boop - the Weaviate bot 👋🤖

PS:
Are you already a member of the Weaviate Slack channel?

[symdec]

I agree with the CLA.

[thomashacker]

Thanks a lot for the PR, I'll have a look 🚀