Introduction: Cost-effective vector search purpose made for AWS: Pay only for what you use, optimize your cloud spend.
Added on: Jan 21, 2025
SvectorDB

What is SvectorDB

SvectorDB is a serverless vector database designed specifically for AWS, offering cost-effective vector search capabilities. It allows users to scale from 1 vector to 1 million vectors with ease, handling the heavy lifting so you can focus on your product. The database supports JavaScript, Python, and OpenAPI, and provides a quick start tutorial for easy onboarding.

How to Use SvectorDB

To use SvectorDB, you can create or update an item, query based on a vector, or query based on a key. Here's an example in JavaScript:

// Create or update an item
client.setItem({
    databaseId,
    key: 'abc',
    value: Buffer.from('Hello world!'),
    vector: [0.1, 0.1, 0.1, 0.1]
});

// Query based on a vector
client.query({
    databaseId,
    query: {
        vector: [0.5, 0.5, 0.5, 0.5]
    }
});

// Query based on key (nearest to existing vector)
client.query({
    databaseId,
    query: {
        key: 'abc'
    }
});

Use Cases of SvectorDB

SvectorDB is ideal for various use cases, including:

  • Recommendation Engines: Using vectors to represent items and users, recommendation engines leverage vector similarity to suggest relevant items to users based on their preferences.
  • Document / Image Search: Transforming documents and images into vectors enables deep meaningful search capabilities by leveraging semantic and visual similarities.
  • Retrieval Augmented Generation: Augmenting generative models with context enhances the quality of generated content, presenting a more refined and contextually relevant output.

Features of SvectorDB

  • Hybrid Search

    Use Lucene / ElasticSearch style queries to filter results based on key-value pairs.

  • Instant updates

    Upserts and deletions are reflected instantly, with no need to worry about eventual consistency.

  • Natively Serverless

    Pay per request based pricing, with no provisioning or scaling required.

  • CloudFormation Support

    Integrate SvectorDB into your existing CloudFormation templates.

  • Built-in Vectorizers

    Use built-in vectorizers for text and images, or bring your own embeddings.

  • Pay per request

    Only pay for the requests you make, with no minimum fees or upfront costs.

FAQs from SvectorDB

1

What are the limitations of SvectorDB?

SvectorDB has a default limit of 1 million records per database to ensure consistent performance. This limit can be increased by contacting support. Additionally, while internal backups are maintained, the ability to create snapshots of your databases is not offered.
2

What is the pricing model for SvectorDB?

SvectorDB offers a pay-per-request pricing model. Storage costs $0.25 per GB per month, queries cost $5 per million, and writes cost $20 per million. There is also a free tier that allows up to 5k records and 10 free tier indexes with no time limit.