Baidu integrations

Integrate with Baidu using LangChain Python.

This page covers all LangChain integrations with Baidu products, such as PaddleOCR.

PaddleOCR

The langchain-paddleocr package implements integrations of PaddleOCR’s capabilities. PaddleOCR is a powerful and lightweight OCR toolkit developed by Baidu that connects images and PDFs with LLMs. It supports over 100 languages and transforms document content into structured, AI-ready data.

Document loaders

PaddleOCRVLLoader

Provides PaddleOCR’s large-model document parsing capabilities.

Get started

Baidu AI Cloud

Installation and setup

Register and get the Qianfan AK and SK keys here.

LLMs

Baidu qianfan

See a usage example.

from langchain_community.llms import QianfanLLMEndpoint

Chat models

Qianfan chat endpoint

See a usage example. See another usage example.

from langchain_community.chat_models import QianfanChatEndpoint

Embedding models

Baidu qianfan

See a usage example. See another usage example.

from langchain_community.embeddings import QianfanEmbeddingsEndpoint

Document loaders

Baidu BOS directory loader

from langchain_community.document_loaders.baiducloud_bos_directory import BaiduBOSDirectoryLoader

Baidu BOS file loader

from langchain_community.document_loaders.baiducloud_bos_file import BaiduBOSFileLoader

Vector stores

Baidu cloud ElasticSearch VectorSearch

See a usage example.

from langchain_community.vectorstores import BESVectorStore

Baidu VectorDB

See a usage example.

from langchain_community.vectorstores import BaiduVectorDB

---

Edit this page on GitHub or file an issue.

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.