Embeddings
Last updated
Last updated
Embeddings are numerical representations of concepts converted to number sequences, which make it easy for computers to understand the relationships between those concepts. They are capable of capturing the context of a word in a document, its semantic and syntactic similarity, and its relation with other words.
Embeddings can be selected by the user in two different section of Stack AI platform.
The most intuitive place is in a vector store. As explained in Vector Databases section, the input will be vectorized and indexed in a vector database for later usage in an AI model (so only the relevant chunks of the input are sent to the LLM).
Document search elements are also customizable with respect to their embeddings.
Below a list of the embeddings models integrated into Stack AI's platform.
text-embedding-ada-002
OpenAI
Outperforms previous OpenAI's most capable model, Davinci, at most tasks, while being priced 99.8% lower
bert-base-cased
Embeddings based on Bidirectional Encoder Representations from Transformers (BERT)
palm2
Vertex AI PaLM API supports Gecko for Embeddings
all-mpbet-base
Open source
Sentence-transformers model that maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
