Text embedding model family trained on weakly supervised pairs.
| Критерий | E5 | OpenAI Text Embedding 3 |
|---|---|---|
| Dimensions | 1024 | 1536 by default, 256 to 3072 selectable |
| License | MIT | Proprietary |
| Max tokens | 512 | 8191 |
| Open weights | Yes | No |
| Provider | Microsoft | OpenAI |
Закрашенные строки совпадают у обеих; различия в остальных строках и определяют рекомендацию ниже.
Сформировано из различий выше по фиксированным правилам, а не моделью.
Choose E5 if…
Ни одна из зафиксированных характеристик не говорит в его пользу.
Choose OpenAI Text Embedding 3 if…
Ни одна из зафиксированных характеристик не говорит в его пользу.
model · Embedding Models
E5 is an embedding model family trained on large collections of weakly supervised text pairs, with the task described in the input so one model serves queries, passages and classification. It solves the problem that an embedding model trained on one kind of pair transfers poorly to another. It exists because describing the task in the text is a cheap way to make one model cover several retrieval settings.
model · Embedding Models
Text Embedding 3 is OpenAI's hosted embedding family, notable for letting the caller choose a shorter output vector than the model natively produces. It solves the storage problem directly: embedding indexes are sized by dimensions times vectors, so trimming 3072 dimensions to 512 or 256 shrinks the index substantially at a small quality cost. It exists because that trade is one the caller is better placed to make than the model author, and it removes the need to retrain to change it.
