This notebook goes over how to use Langchain withYandexGPT embeddings models.

To use, you should have theyandexcloud python package installed.

%pip install--upgrade--quiet  yandexcloud

First, you shouldcreate service account with theai.languageModels.user role.

Next, you have two authentication options:

• IAM token.You can specify the token in a constructor parameteriam_token or in an environment variableYC_IAM_TOKEN.
• API keyYou can specify the key in a constructor parameterapi_key or in an environment variableYC_API_KEY.

To specify the model you can usemodel_uri parameter, seethe documentation for more details.

By default, the latest version oftext-search-query is used from the folder specified in the parameterfolder_id orYC_FOLDER_ID environment variable.

from langchain_community.embeddings.yandeximport YandexGPTEmbeddings

embeddings= YandexGPTEmbeddings()

text="This is a test document."

query_result= embeddings.embed_query(text)

doc_result= embeddings.embed_documents([text])

query_result[:5]

[-0.021392822265625,
 0.096435546875,
 -0.046966552734375,
 -0.0183258056640625,
 -0.00555419921875]

doc_result[0][:5]

[-0.021392822265625,
 0.096435546875,
 -0.046966552734375,
 -0.0183258056640625,
 -0.00555419921875]

Related​

• Embedding modelconceptual guide
• Embedding modelhow-to guides