Text embedding models | 🦜️🔗 Langchain
python.langchain.com/docs/modules/data_connection/text_embedding/
4 Users
0 Comments
25 Highlights
0 Notes
Tags
Top Highlights
two methods: one for embedding documents and one for embedding a query.
The Embeddings class is a class designed for interfacing with text embedding models. There are lots of embedding model providers (OpenAI, Cohere, Hugging Face, etc) - this class is designed to provide a standard interface for all of them. Embeddings create a vector representation of a piece of text. This is useful because it means we can think about text in the vector space, and do things like semantic search where we look for pieces of text that are most similar in the vector space.
one for embedding a query
Embeddings
a class designed for interfacing with text embedding models
create a vector representation of a piece of text
can think about text in the vector space
do things like semantic search
one for embedding a query.
former
latter
takes a single text
takes as input multiple texts
some embedding providers have different embedding methods
documents
queries
embed_documents
Embed list of texts
embed_query
Embed a single piece of text for the purpose of comparing to other embedded pieces of texts
Ready to highlight and find good content?
Glasp is a social web highlighter that people can highlight and organize quotes and thoughts from the web, and access other like-minded people’s learning.