[Feature] support using groq hosted llama-3.2-90b-vision-preview for both text and image organization

AIxHunter / FileWizardAI

Add AI capabilities to your file system using Ollama, Groq, OpenAi and other's api

153 stars 9 forks source link

[Feature] support using groq hosted llama-3.2-90b-vision-preview for both text and image organization #6

Closed barakplasma closed 1 month ago

barakplasma commented 1 month ago

I noticed on groq vision docs / groq playground that they have the latest llama model which also supports images. Is there a way / plan to use this instead of ollama?

AIxHunter commented 1 month ago

Yes, actually Groq is the recommended model to be used (at least for text processing), you only need to update your .env file to point to Groq, check the examples section in the documentation

barakplasma commented 1 month ago

Thanks

AIxHunter commented 1 month ago

@barakplasma your welcome, if you tested newer models for Groq can you please create a PR and update the Groq models in the .env file in that documentation ?