s3vectorm 0.1.1

Type-safe Python ORM for AWS S3 Vectors - build RAG applications within minutes and 90% cost savings.

---

Welcome to s3vectorm Documentation

s3vectorm is a Python ORM-style library that provides a type-safe, intuitive interface for managing vector data in AWS S3 Vectors service. Built on top of Pydantic, it combines the power of AWS’s cost-effective vector storage with the reliability of runtime type validation and the familiarity of ORM-like data manipulation.

Why S3 Vectors + s3vectorm?

AWS S3 Vectors offers up to 90% cost reduction compared to traditional vector databases, making it an ideal choice for startups and cost-conscious organizations building RAG (Retrieval-Augmented Generation) applications. However, working directly with the AWS SDK can be verbose and error-prone. s3vectorm bridges this gap by providing a clean, Pythonic API that makes vector operations as simple as working with traditional database models.

Type-Safe Vector Models

Define your vector data structures using familiar Pydantic syntax with automatic validation:

from s3vectorm import Vector
from pydantic import Field

class DocumentChunk(Vector):
    document_id: str = Field(description="Source document ID")
    chunk_seq: int = Field(description="Chunk sequence number")
    title: str = Field(description="Document title")
    category: str = Field(description="Document category")
    owner_id: str = Field(description="Document owner")

Intuitive Query Builder

Build complex metadata queries using a SQLAlchemy-inspired syntax:

from s3vectorm import BaseMetadata, MetaKey

class DocumentMeta(BaseMetadata):
    document_id = MetaKey()
    category = MetaKey()
    owner_id = MetaKey()

# Build queries naturally
filter_query = (
    DocumentMeta.category.eq("research") &
    DocumentMeta.owner_id.in_(["alice", "bob"])
)

Ready for Production RAG

With s3vectorm, you can build sophisticated RAG applications in minutes, not days. The library handles the complexities of AWS S3 Vectors operations while providing the type safety and developer experience you expect from modern Python libraries. Whether you’re prototyping your first vector search feature or scaling to millions of embeddings, s3vectorm provides the foundation for reliable, cost-effective vector operations.

Install

s3vectorm is released on PyPI, so all you need is to:

$ pip install s3vectorm

To upgrade to latest version:

$ pip install --upgrade s3vectorm