SvectorDB: The Ultimate Serverless Vector Database for AWS
SvectorDB is a revolutionary serverless vector database designed specifically for AWS. It offers a cost-effective solution for vector search, allowing users to pay only for what they use. This means you can optimize your cloud spend and focus on scaling your product without worrying about excessive costs.
Core Features
- Hybrid Search: Use Lucene/ElasticSearch style queries to filter results based on key-value pairs, providing more precise search capabilities.
- Instant Updates: Upserts and deletions are reflected instantly, ensuring data consistency without the hassle of waiting.
- Natively Serverless: With a pay-per-request based pricing model, there's no need for provisioning or scaling, making it easy and affordable to use.
- CloudFormation Support: Integrate SvectorDB seamlessly into your existing CloudFormation templates for a smooth workflow.
- Built-in Vectorizers: Utilize the built-in vectorizers for text and images, or bring your own embeddings to customize your database.
Basic Usage Getting started with SvectorDB is straightforward. You can create or update an item with just a few lines of code. For example:
client.setItem({
databaseId,
key: 'abc',
value: Buffer.from('Hello world!'),
vector: [0.1, 0.1, 0.1, 0.1]
});
And querying the database is just as easy:
client.query({
databaseId,
query: { vector: [0.5, 0.5, 0.5, 0.5] }
});
Use Cases SvectorDB is suitable for a wide range of applications, including recommendation engines, document/image search, and retrieval augmented generation. It enables businesses to leverage vector similarity to provide more relevant suggestions and enhance search capabilities.
In terms of pricing, SvectorDB offers competitive rates. Storage is priced at $0.25/GB/month, queries are $5/million, and writes are $20/million. There's also a free tier that allows you to create up to 10 free tier indexes of up to 5k records with no time limit.
While SvectorDB has many strengths, it also has some limitations. For example, it currently does not offer the ability to create snapshots of your databases, and there is a default limit of 1 million records per database. However, the team behind SvectorDB is committed to transparency and is hyper-responsive to customer needs.
Overall, SvectorDB is a powerful tool that can help businesses of all sizes unlock the potential of vector databases on the AWS platform.
