Snowflake is a cloud-based data-warehousing platform that allows you to store and query large amounts of data.
This page covers how to use the Snowflake ecosystem within LangChain.

​
Embedding models

Snowflake offers their open-weight arctic line of embedding models for free on Hugging Face. The most recent model, snowflake-arctic-embed-m-v1.5 feature matryoshka embedding which allows for effective vector truncation. You can use these models via the HuggingFaceEmbeddings connector: 
pip install langchain-community sentence-transformers

from langchain_huggingface import HuggingFaceEmbeddings

model = HuggingFaceEmbeddings(model_name="snowflake/arctic-embed-m-v1.5")

​
Document loader

You can use the SnowflakeLoader to load data from Snowflake: 
from langchain_community.document_loaders import SnowflakeLoader