medusa VS qdrant

You wrote get a 20G medium hosting package from platform.sh, did you mean 2G?

Platform.sh | REMOTE | Full-Time | https://platform.sh

Platform.sh is a unified, secure, enterprise-grade platform for building, running and scaling fleets of websites and applications.

We serve thousands of customers worldwide including The United Nations, The Financial Times, Adobe Commerce/Magento, Shopware, Orange, University of Missouri and The British Council.

We are among the momentum leaders in Cloud PaaS according to G2 https://www.g2.com/categories/cloud-platform-as-a-service-pa...

Recently, we have finished $140 million series D funding.

Here's how it works (get a free trial and go crazy):

Pick a template from https://github.com/platformsh-templates and customize it (add your assets, specify infra) as per https://docs.platform.sh/overview/structure.html

Then push to your Platform.sh repo, BOOM! magic happens and you have a working site that you can branch, test, customize, go-live. Dead simple, you don't need Kubernetes, just basic git knowledge.

Tech stack is LXC with some Python awesomeness, Puppet, Ceph and GlusterFS. Tooling is in Python and Go. Yep, we are multi-cloud (AWS, Azure, GCP, ...).

What I love:

• Great work-life balance (remote only company, you can work on a contract, but you also get PTO incl. your national holidays, parental leave)

• Lots of smart people from around the world

• Work on interesting stuff

• Company shares (discretionary)

• Good comp package, pick your HW, get reimbursed for trainings and other stuff

Join us https://platform.sh/company/careers/

Vinnie Russo built a Platform.sh template designed to ease the deployment process for a Medusa ecommerce solution. The template includes the essential Medusa backend infrastructure, the admin dashboard, and the Next.js storefront.

Great. Now that we have the embeddings, we need to store them in a vector database. We will be using Qdrant for this purpose. Qdrant is an open-source vector database that allows you to store and query high-dimensional vectors. The easiest way to get started with the Qdrant database is using the docker.

I took Qdrant for this project. The reason was that Qdrant stands for high-performance vector search, the best choice against use cases like finding similar function calls based on semantic similarity. Qdrant is not only powerful but also scalable to support a variety of advanced search features that are greatly useful to nuanced caching mechanisms like ours.

I'm currently looking to implement locally, using QDrant [1] for instance.

I'm just playing around, but it makes sense to have a runnable example for our users at work too :) [2].

[1]. https://qdrant.tech/

Also compare with qdrant's Rust implementation; they tout their performance. https://github.com/qdrant/qdrant/tree/master/lib/segment/src...

There are much better known examples, such as https://qdrant.tech/ and https://github.com/lancedb/lancedb

For more information, see our release notes. Qdrant is an open source project. We welcome your contributions; raise issues, or contribute via pull requests!

Initialize the Qdrant Client with in-memory storage. The collection name will be “imagebind_data” and we will be using cosine distance.

Qdrant is an open-source vector search engine optimized for performance and flexibility. It supports both exact and approximate nearest neighbor search, providing a balance between accuracy and speed for various AI and ML applications.