To create high-quality embeddings that work effectively in an RAG pipeline, one needs to utilize pre-trained embedding models, like OpenAI’s embedding models. There are various types of embeddings one can create and corresponding models available. For instance:

Word Embeddings: In word embeddings, each word has a fixed vector regardless of context. Popular models for creating this type of embedding are Word2Vec and GloVe.

Contextual Embeddings: Contextual embeddings take into account that the meaning of a word can change based on context. Take, for instance, the bank of a river and opening a bank account. Some models that can be used for producing contextual embeddings are BERT and OpenAI’s embedding models (like text-embedding-ada-002)

Sentence Embeddings: These are embeddings capturing the meaning of full sentences. A popular embedding model for creating sentence embeddings is Sentence-BERT.

When the war ended and the internet came back, this was one of the first messages I received from Wiki, my colleague at Belonix.

Every now and then, I look back at it and have a good laugh at my own luck. :*)))

The first version of EyeQ is reachable

This is the first unpolished version but in the site you can solve cases and read about detectives

EyeQ is a place for crime and riddle fans, for those who want to acquire the sharp skills of bright detectives

There's a lot of work to put into it, but as developers say: "make it exist first" :))