Skip to main content
veDB for MySQL is a cloud-native, high-performance database service developed by Volcano Engine(Volcengine). Volcengine is a cloud service platform developed by ByteDance, the parent company of TikTok. This integration allows you to use veDB for MySQL as a vector store in LangChain.

​
Setup

To use the veDB for MySQL vector store, you’ll need a Volcengine account and a veDB for MySQL instance.

​
Installation

Install the integration package:
pip
pip install -U langchain-volcengine-mysql

​
Instantiation

Configure the vedb submodule, then access vedb.vector_store. 
from langchain_volcengine_mysql import vedb
from langchain_openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings()

vedb.configure(
    host="your-vedb-host.example.com",
    port=3306,
    user="your_user",
    password="your_password",
    database="your_db",
    table_name="vector_embeddings",
    embedding_dim=1536,
    embedding_function=embeddings,
)

vector_store = vedb.vector_store
retriever = vedb.retriever

​
Manage vector store

​
Add items

from langchain_core.documents import Document

docs = [
    Document(page_content="veDB for MySQL supports vector search.", metadata={"source": "docs"}),
    Document(page_content="LangChain can query it via a unified interface.", metadata={"source": "docs"}),
]

vector_store.add_documents(documents=docs, ids=["1", "2"])

​
Delete items

vector_store.delete(ids=["1"])

​
Query vector store

results = vector_store.similarity_search(query="Tell me about veDB", k=1)
for doc in results:
    print(f"* {doc.page_content} [{doc.metadata}]")

​
Use as a retriever

docs = retriever.invoke("Tell me about veDB")

​
API reference

See the official PyPI docs.
Edit this page on GitHub or file an issue.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.