ContentVec
safe-models's ContentVec is a embedding model. ContentVec is an open-weights embed model.
by safe-models
Best for
Ways to use ContentVec in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your safe-models API key. osFoundry discovers ContentVec automatically — assign it to a Maestro role (router, direct, orchestrator, or fallback) in the Pipeline tab and it is live in every chat. Your key, your provider account — no token markup.
Deploy a dedicated endpoint
ContentVec is open-weights — run it locally for free, or deploy a dedicated GPU endpoint in your workspace for reserved capacity with no rate limits.
Use it in a Room App
Room Apps declare AI features in their manifest, then call them with invokeAI:
import { invokeAI } from '@osfoundry/app-sdk'
// 'summarize' is an AI feature declared in your app manifest.
const result = await invokeAI('summarize', userText)
Call it from your own apps
Once a model is wired into your workspace you can host it as an API and reach it from your own services, scripts, or CI — outside osFoundry.
ContentVec vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about ContentVec
Is ContentVec free to use?
ContentVec is free to run locally on your own hardware. Hosted access through osFoundry is metered (input Free (local), output Free (local)). You can switch between local and hosted at any time.
Can I use ContentVec commercially?
Commercial use is allowed with conditions. Licence terms not specified — verify the upstream model card before commercial use. Check upstream documentation.
Can I run ContentVec locally?
Yes. ContentVec is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is ContentVec best at?
ContentVec is well-suited to feature extraction.
How do I use ContentVec in osFoundry?
Paste your safe-models API key in the key dialog (or deploy the open weights for self-hostable models), assign ContentVec to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by safe-models on January 18, 2025. Source: https://huggingface.co/safe-models/ContentVec