Model catalogue · Microsoft Research (E5-Modellreihe, offene Gewichte)
E5 Embedding
Multilingual embedding models with open weights, available in two size classes. Their advantage lies in mobility: because the weights are openly available, the same search index can later be continued on other hardware without recomputing it. They arrange a corpus for search; assessment and drafting they do not provide. Via Google Vertex AI the chain under section 203 of the German Criminal Code is closed - the platform operator's signed agreement is service-bound and therefore covers the open models of the Model Garden as well. This check weighs particularly heavily here, because an embedding run sends not a single request but the entire indexed corpus through the service.
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
- Open weights - the same index can later be moved to your own or a dedicated instance without recomputation
- Multilingual, available in two sizes - the small tier is enough for many file corpora
- Processing committed to the EU and to the Netherlands, covered by the service-bound section 203 agreement
Where it stops
- An embedding run sends the entire indexed corpus through the service - the scope and redaction of the index have to be settled beforehand
- Vectors are not an anonymisation technique: content can be partly reconstructed from them, so they have to be treated like plain text
- Only one individual EU region listed - no second call path inside the EU
- Pure search function - an embedding model does not summarise, assess or draft
- The platform's global endpoint gives no residency guarantee - the same models can be called there as well. Binding to the EU is therefore a configuration requirement: the global endpoint is blocked by organisational policy, otherwise the EU commitment is a settings question rather than a property.
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 E5 Embedding carries the sources with their retrieval dates.
Is E5 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