MiniCOIL v1 MiniCOIL is a sparse neural embedding model for textual retrieval. It creates 4 dimensional embeddings for each word stem, capturing the word's meaning. These meaning embeddings are combined into a bag of words (BoW) representation of the input text. The final sparse representation is calculated by weighting each word using the BM25 scoring formula. In the case of a word's absence in the miniCOIL vocabulary, word weight in sparse representation is purely based on the BM25 score. Read more about miniCOIL in the article. Usage This model is designed to be used with the FastEmbed library. Note: This model was designed with Qdrant's specifics in mind; miniCOIL sparse vectors in Qdrant have to be configured with Modifier.IDF. Otherwise, you'll have to personally calculate & scale the produced sparse representations by the IDF part of the BM25 formula.
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy