Model catalogue · Google
Google Text-Embedding
The established previous generation of Google embeddings turns text into vectors and includes an expressly multilingual tier. It is the right choice where an existing search index is not to be recomputed or where foreign-language documents are decisive. Via Google Vertex AI the chain is closed: the platform operator's signed confidentiality agreement under section 203 of the German Criminal Code is service-bound and covers the embeddings as well as the language models, callable through the EU endpoint and through individual EU regions. Two points belong in the setup: an embedding run sends the entire indexed corpus through the service, and the London processing location listed for two tiers lies outside the EU endpoint.
Everything section 203 requires is settled, including the provider's confidentiality undertaking. You do not have to clarify anything further.
What it is good for
- Established embedding line with a multilingual tier for foreign-language documents
- Callable through the EU endpoint and through individual EU regions, processing committed to the EU
- Covered by the same service-bound section 203 agreement as the platform's language models
Where it stops
- London is listed as the processing location for two tiers; the United Kingdom is excluded from the EU endpoint - this call path has to be blocked
- An embedding run sends the entire indexed corpus through the service - the scope and redaction of the index have to be settled beforehand
- Previous generation: for new indexes the current embedding tier is usually the better choice
- CLOUD Act exposure remains - the third-country module is mandatory
Routes examined
The same model, procured differently, is a different legal position. What is examined per route is the contract chain, not the model.
| Route | Section 203 status | Version on this route |
|---|---|---|
| Google EU platform (Gemini Enterprise, formerly Vertex AI) | covered | - |
The conditions behind a conditional status - which piece is open on which route and who closes it - are set out in the full matrix in the German catalogue, and we go through them in the conversation. The German page for Google Text-Embedding carries the sources with their retrieval dates.
Is Google Text-Embedding the right fit?
We go through your tasks and the route that carries them - and say plainly where it does not.
Arrange a conversation