UpstageEmbeddings
This notebook covers how to get started with Upstage embedding models.
Installation
Installlangchain-upstage package.
pip install -U langchain-upstage
Environment Setup
Make sure to set the following environment variables:
UPSTAGE_API_KEY: Your Upstage API key fromUpstage console.
import os
os.environ["UPSTAGE_API_KEY"]="YOUR_API_KEY"
Usage
InitializeUpstageEmbeddings class.
from langchain_upstageimport UpstageEmbeddings
embeddings= UpstageEmbeddings(model="solar-embedding-1-large")
API Reference:UpstageEmbeddings
Useembed_documents to embed list of texts or documents.
doc_result= embeddings.embed_documents(
["Sung is a professor.","This is another document"]
)
print(doc_result)
Useembed_query to embed query string.
query_result= embeddings.embed_query("What does Sung do?")
print(query_result)
Useaembed_documents andaembed_query for async operations.
# async embed query
await embeddings.aembed_query("My query to look up")
# async embed documents
await embeddings.aembed_documents(
["This is a content of the document","This is another document"]
)
Using with vector store
You can useUpstageEmbeddings with vector store component. The following demonstrates a simple example.
from langchain_community.vectorstoresimport DocArrayInMemorySearch
vectorstore= DocArrayInMemorySearch.from_texts(
["harrison worked at kensho","bears like to eat honey"],
embedding=UpstageEmbeddings(model="solar-embedding-1-large"),
)
retriever= vectorstore.as_retriever()
docs= retriever.invoke("Where did Harrison work?")
print(docs)
API Reference:DocArrayInMemorySearch
Related
- Embedding modelconceptual guide
- Embedding modelhow-to guides