Toronto-based AI startup Cohere has introduced a private beta for Cohere Compass, a foundation embedding model designed to allow multi-aspect data indexing and searching.
The model operates by converting data into JSON documents, which are then transformed into a special format by the model and stored in vector databases. Additionally, the model is capable of handling multi-aspect representations, the ability to comprehend the relationship between concepts present in the data, and flexibility in storing the output embeddings in several databases.
By using this site, you agree to allow SPEEDA Edge and our partners to use cookies for analytics and personalization. Visit our privacy policy for more information about our data collection practices.