Platform Configuration

This page separates the default flow (for most teams) from the on-prem flow (advanced).

Default (for most users)

If you use data pools in standard meinGPT cloud mode, you do not need to configure your own Data Vault.

• Connect sources in meinGPT
• Select your data pool
• Use it in assistants and workflows

The underlying vault component is managed in the background.

On-Premise / Advanced (customer-managed Data Vault)

Extra setup is only required when you operate your own Data Vault runtime.

1. Create Data Vault in meinGPT

1. Open Company Settings > Data Vaults
2. Click Add DataVault
3. Enter a name
4. Save ID and Secret Key from the dialog

Details: Create DataVault

2. Configure runtime

Set these values in your vault runtime:

• VAULT_ID
• VAULT_SECRET
• MEINGPT_URL

Example:

VAULT_ID=...
VAULT_SECRET=...
MEINGPT_URL=https://app.meingpt.com

Also configure at least these sections in config/app_config.yaml:

• vault.id
• vault.secret
• meingpt_url
• weaviate.*
• embedding_model.*

Details: Local Deployment and Configuration Reference

3. Configure data pools in meinGPT

Data pools are still created in meinGPT (name, source type, permissions). The vault fetches this configuration at runtime.

You can optionally define additional local data_pools in app_config.yaml (advanced).

4. Verify

• Check vault health
• Trigger sync
• Check status and logs

Details: Verification

Decision guide

• Fast start / no self-operation: default flow
• Own infrastructure / full control: on-prem flow

Next steps

• Data Pools (RAG)
• Local Deployment
• Configuration Reference