Hybrid Deployment
Run the Holofin application in your own cloud and keep your documents there. Holofin's cloud only runs the AI models.
How It Works
In a hybrid deployment, the Holofin application runs in your cloud account: the API, the dashboard, the database, and the object storage that holds your documents and results. The AI models (OCR, vision and language models, image forensics) run in Holofin's cloud. When a workflow needs a model, your deployment sends the document to Holofin's inference endpoint and the result comes back to your environment.
- Your systems upload a document to the Holofin API on your own domain. It is stored in your object storage.
- The workflow sends the document to the inference endpoint of your region over TLS 1.2 or later.
- The inference endpoint runs the models and returns the result.
- Your deployment stores the extracted data, check results, and audit logs in your database.
Why Choose Hybrid
- Storage stays in your country:Meets data residency rules that allow processing elsewhere as long as documents are stored in-country.
- No AI infrastructure to run:You need no GPU quota, no model hosting, and no model updates. Holofin runs and updates the models.
- Faster and cheaper to set up:Hosting the full stack, GPUs included, in your account takes longer and costs more.
- Your own security policies:Your IAM, network, and encryption policies apply to the application, the database, and the storage.
- Same API:The endpoints in this documentation work unchanged. Only the base URL changes, to your own domain.
What Runs Where
| Component | Runs in |
|---|---|
| Holofin application: API, dashboard, workflows, dossiers | Your cloud |
| PostgreSQL and Redis | Your cloud |
| Object storage for documents and results | Your cloud |
| DNS, TLS certificates, and single sign-on | Your cloud |
| OCR, vision and language models, image forensics | Holofin cloud |
Inference Regions
You pick the region where your documents are processed. Your deployment only calls the endpoint of that region.
| Region | Location | Inference endpoint |
|---|---|---|
eu | European Union | https://inference.holofin.ai |
us | United States | https://us.inference.holofin.ai |
The eu region is covered by the EU data residency guarantee. Documents sent to the us region are processed in the United States: pick eu if your documents must not leave the European Union.
What You Provide
- A cloud account or project with admin access, where Holofin deploys the application.
- A domain you control for the API and the dashboard.
- Outbound HTTPS (port 443) from your deployment to the inference endpoint of your region.
No GPU quota and no AI service subscription are needed in your account.
Compare Deployment Options
| Cloud | Hybrid | BYOC | |
|---|---|---|---|
| Application, database, documents | Holofin cloud, EU | Your cloud | Your cloud |
| AI models | Holofin cloud, EU | Holofin cloud, eu or us region | Your cloud |
| Documents leave your account | Yes, Holofin stores and processes them | For inference only | No |
| GPU in your account | None | None | One 24 GB card |
To keep the AI models in your account as well, see BYOC Deployment.
Request a Hybrid Deployment
Hybrid deployments are set up per contract. To discuss your requirements, write to [email protected].