选择客户

如在《结构化与非结构化嵌入》(/docs/guides/ai/structured-unstructured) 中所述，人工智能工作负载有很多种形式。

🌐 As described in Structured & Unstructured Embeddings, AI workloads come in many forms.

对于数据科学或短时工作负载，Supabase Vecs 客户端可以帮你入门。你只需要一个连接字符串，vecs 会处理数据库的设置，以便存储和查询带有相关元数据的向量。

🌐 For data science or ephemeral workloads, the Supabase Vecs client gets you started. You need a connection string and vecs handles setting up your database to store and query vectors with associated metadata.

对于有版本控制迁移的生产 Python 应用，我们建议通过在你的 ORM 中注册向量类型来为你的工具链添加一流的向量支持。pgvector 为最常用的 SQL 驱动/库提供了绑定，包括 Django、SQLAlchemy、SQLModel、psycopg、asyncpg 和 Peewee。

🌐 For production python applications with version controlled migrations, we recommend adding first class vector support to your toolchain by registering the vector type with your ORM. pgvector provides bindings for the most commonly used SQL drivers/libraries including Django, SQLAlchemy, SQLModel, psycopg, asyncpg and Peewee.