English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Vector embeddings have become ubiquitous tools for many language-relatedtasks. A leading embedding model is OpenAI's text-ada-002 which can embedapproximately 6,000 words into a 1,536-dimensional vector. While powerful,text-ada-002 is not open source and is only available via API. We trained asimple neural network to convert open-source 768-dimensional MPNet embeddingsinto text-ada-002 embeddings. We compiled a subset of 50,000 online foodreviews. We calculated MPNet and text-ada-002 embeddings for each review andtrained a simple neural network to for 75 epochs. The neural network wasdesigned to predict the corresponding text-ada-002 embedding for a given MPNETembedding. Our model achieved an average cosine similarity of 0.932 on 10,000unseen reviews in our held-out test dataset. We manually assessed the qualityof our predicted embeddings for vector search over text-ada-002-embeddedreviews. While not as good as real text-ada-002 embeddings, predictedembeddings were able to retrieve highly relevant reviews. Our final model,Vec2Vec, is lightweight (<80 MB) and fast. Future steps include training aneural network with a more sophisticated architecture and a larger dataset ofpaired embeddings to achieve greater performance. The ability to convertbetween and align embedding spaces may be helpful for interoperability,limiting dependence on proprietary models, protecting data privacy, reducingcosts, and offline operations.

Vec2Vec: A Compact Neural Network Approach for Transforming Text Embeddings with High Fidelity