Skip to main content


ERNIE Embedding-V1 is a text representation model based on Baidu Wenxin large-scale model technology, which converts text into a vector form represented by numerical values, and is used in text retrieval, information recommendation, knowledge mining and other scenarios.

Deprecated Warning

We recommend users using langchain_community.embeddings.ErnieEmbeddings to use langchain_community.embeddings.QianfanEmbeddingsEndpoint instead.

documentation for QianfanEmbeddingsEndpoint is here.

they are 2 why we recommend users to use QianfanEmbeddingsEndpoint:

  1. QianfanEmbeddingsEndpoint support more embedding model in the Qianfan platform.
  2. ErnieEmbeddings is lack of maintenance and deprecated.

Some tips for migration:

from langchain_community.embeddings import QianfanEmbeddingsEndpoint

embeddings = QianfanEmbeddingsEndpoint(
qianfan_ak="your qianfan ak",
qianfan_sk="your qianfan sk",


from langchain_community.embeddings import ErnieEmbeddings

API Reference:

embeddings = ErnieEmbeddings()
query_result = embeddings.embed_query("foo")
doc_results = embeddings.embed_documents(["foo"])

Help us out by providing feedback on this documentation page: