chroma-core / chroma

the AI-native open-source embedding database
https://www.trychroma.com/
Apache License 2.0
14.59k stars 1.22k forks source link

[Feature Request]: Universal Sentence Encoder(USE) Embedding Function #1722

Open csbasil opened 7 months ago

csbasil commented 7 months ago

Describe the problem

Built in support for Google's Universal Sentence Encoder (USE) which can useful for greater-than-word length text, such as sentences, phrases or short paragraphs.

USE Paper

Describe the proposed solution

A new embedding function with USE support. USE model is available on TensorFlow Hub(https://tfhub.dev/google/universal-sentence-encoder/4) as well as HuggingFace(Dimitre/universal-sentence-encoder).

Alternatives considered

No response

Importance

nice to have

Additional Information

No response

csbasil commented 7 months ago

I have created a PR - https://github.com/chroma-core/chroma/pull/1723 for the same