text2vec-transformers

Weaviate on Stackoverflow badge Weaviate issues on Github badge Weaviate total Docker pulls badge

💡 You are looking at older or release candidate documentation. The current Weaviate version is v1.15.2


A text2vec-transformers module will be released soon, but take a look at this example! :)

Introduction

Due to Weaviate’s ability to import vectors directly, you can always chose whichever module fits your needs best. At the same time we’re aiming to provide convenience options for the most commonly requested modules. With the upcoming text2vec-transformers module, you’ll be able to use the same convenient edge to edge approach which you are accustomed to from the text2vec-contextionary module with any BERT-like transformer model.

The text2vec-transformers module allow you to use a pre-trained language transformer model as Weaviate vectorization module. Transformer differ from the Contextionary as they allow you to plug in a pretrained NLP module specific to your use case. Transformer models handle text as sequential data, which is a different learning method than the text2vec-contextionary.

Try it out

Can’t wait for the full module to be ready? No worries, because with this tutorial you can already play around with Weaviate and a well-know transformer model!

More resources

If you can’t find the answer to your question here, please look at the:

  1. Frequently Asked Questions. Or,
  2. Knowledge base of old issues. Or,
  3. For questions: Stackoverflow. Or,
  4. For issues: Github. Or,
  5. Ask your question in the Slack channel: Slack.

Edit on Github

Table of Contents