Skip to main content


This notebook goes over how to use Langchain with YandexGPT.

To use, you should have the yandexcloud python package installed.

%pip install --upgrade --quiet  yandexcloud

First, you should create service account with the ai.languageModels.user role.

Next, you have two authentication options:

  • IAM token. You can specify the token in a constructor parameter iam_token or in an environment variable YC_IAM_TOKEN.

  • API key You can specify the key in a constructor parameter api_key or in an environment variable YC_API_KEY.

To specify the model you can use model_uri parameter, see the documentation for more details.

By default, the latest version of yandexgpt-lite is used from the folder specified in the parameter folder_id or YC_FOLDER_ID environment variable.

from langchain.chains import LLMChain
from langchain_community.llms import YandexGPT
from langchain_core.prompts import PromptTemplate
template = "What is the capital of {country}?"
prompt = PromptTemplate.from_template(template)
llm = YandexGPT()
llm_chain = LLMChain(prompt=prompt, llm=llm)
country = "Russia"

'The capital of Russia is Moscow.'

Help us out by providing feedback on this documentation page: