This plugin leverages open-sourced TensorFlow's Universal Sentence Encoder text embedding models to generate 512-dimensional embedding vectors from text within your Bubble application. It can handle both individual strings and lists of text, providing flexibility based on your specific needs.
The plugin operates by taking a string of text or a list of texts as input, processing it through TensorFlow's pre-trained machine learning models, and outputting a numerical vector representation of each text.

The output embeddings from this plugin can be stored efficiently in a 512-dimensional vector database. This enables you to utilize them for a variety of purposes such as semantic search, recommendation systems, or other applications where understanding the semantic similarity between different pieces of text is valuable.