How to use Chroma to store and query vector embeddings

1

Hugging Face

In embedding_util.py, used by our app.py module, we define a custom embedding class (that I am calling CustomEmbeddingFunction) by inheriting chroma's EmbeddingFunction class and leveraging the Transformers library. This function tokenizes the input text and generates embeddings using a pre-trained model, in this case, thenlper/gte-base one of the currently top performing open source embedding models - and very runnable on many consumer hardware devices. The inspiration the implementation of generate_embeddings came from the gte-base model card on Hugging Face.

#Social & Communications #AI #Chatbots 252 social mentions

2

Git

Git installed on your system (for cloning Chroma).

#Git #Git Tools #Code Collaboration 214 social mentions