Skip to main content
Open on GitHub

NAVER

All functionality related to Naver, including HyperCLOVA X models, particularly those accessible through Naver Cloud CLOVA Studio.

Naver is a global technology company with cutting-edge technologies and a diverse business portfolio including search, commerce, fintech, content, cloud, and AI.

Naver Cloud is the cloud computing arm of Naver, a leading cloud service provider offering a comprehensive suite of cloud services to businesses through its Naver Cloud Platform (NCP).

Please refer to NCP User Guide for more detailed instructions (also in Korean).

Installation and Setup​

  • Get a CLOVA Studio API Key by issuing it and set it as an environment variable (NCP_CLOVASTUDIO_API_KEY).
    • If you are using a legacy API Key (that doesn't start with nv-* prefix), you might need to get an additional API Key by creating your app and set it as NCP_APIGW_API_KEY.

Naver integrations live in two packages:

  • langchain-naver-community: a dedicated integration package for Naver. It is a community-maintained package and is not officially maintained by Naver or LangChain.
  • langchain-community: a collection of third-party integrations, including Naver. New features should be implemented in the dedicated langchain-naver-community package.
pip install -U langchain-community langchain-naver-community

Chat models​

ChatClovaX​

See a usage example.

from langchain_community.chat_models import ChatClovaX
API Reference:ChatClovaX

Embedding models​

ClovaXEmbeddings​

See a usage example.

from langchain_community.embeddings import ClovaXEmbeddings
API Reference:ClovaXEmbeddings

Tools​

The Naver Search integration allows your LangChain applications to retrieve information from Naver's search engine. This is particularly useful for Korean language queries and getting up-to-date information about Korean topics.

To use the Naver Search tools, you need to:

  1. Sign in to the Naver Developers portal
  2. Create a new application and enable the Search API
  3. Obtain your NAVER_CLIENT_ID and NAVER_CLIENT_SECRET from the "Application List" section
  4. Set these as environment variables in your application
from langchain_naver_community.tool import NaverSearchResults
from langchain_naver_community.utils import NaverSearchAPIWrapper

# Set up the search wrapper
search = NaverSearchAPIWrapper()

# Create a tool
tool = NaverSearchResults(api_wrapper=search)

See a usage example for more details.

Specialized Search Tools​

The package also provides specialized search tools for different types of content:

from langchain_naver_community.tool import NaverNewsSearch  # For news articles
from langchain_naver_community.tool import NaverBlogSearch  # For blog posts
from langchain_naver_community.tool import NaverImageSearch  # For images

Each of these can be used within LangChain agents to provide more targeted search capabilities.

Was this page helpful?