Using open-source models for faster and cheaper text embeddings

This blog post from Replicate provides a guide on using the open-source BAAI/bge-large-en-v1.5 model for text embeddings.

It covers prerequisites, installation, generating embeddings from a list of text and from JSONL files, and a real-world example using the SAMSum dataset.

The post notes that the model is state-of-the-art, open source, and cheaper to run on Replicate compared to OpenAI embeddings.