Tim Eggert

Father, python-lover, rust-admirer, former CeleraOne CTO & software-architect, Father ...

[Rust Trending @RustTrending]

qdrant: Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://t.co/6yfvzHaZDq ★21948 https://t.co/JWwz9Z2wNm

[Tim Eggert @elbartus]

Such a nice read - can resonate with the authors thoughts a lot! https://t.co/GwFU4SOt0j

[Laura Wendel @Lauramaywendel]

So apparently if someone knows / guesses the name of your S3 bucket - even if it's private (!) - they can just bankrupt you by sending infinite PUT requests and there is nothing you can do about it.
> requests get rejected
> but AWS still counts it as a write operation against your account for which you have to pay at a rate of $0.005 per 1000 requests

This seems insane to me. Especially because a lot of services rely on presigned URLs for uploads / downloads which exposes your bucket name to the client. In this case the author got their bill waved, but AWS support made it clear it's an exception not the rule.

[Qdrant @qdrant_engine]

We couldn't be happier to partner with @RedHat Openshift for the launch of 𝐐𝐝𝐫𝐚𝐧𝐭 𝐇𝐲𝐛𝐫𝐢𝐝 𝐂𝐥𝐨𝐮𝐝! 🚀

Now, you can easily set up Qdrant Hybrid Cloud on Red Hat OpenShift to scale effortlessly, operate consistently across hybrid cloud environments, and maintain complete control over your vector data.

📄 Discover the benefits you get from this partnership in joint blog: https://t.co/YHRDnMootJ

[Qdrant @qdrant_engine]

Your Data, Your Rules, Anywhere!

The first managed vector database that you can run anywhere is here. Qdrant Hybrid Cloud is setting a new standard for where and how you can build your AI applications.

Now, you can deploy your vector database in any environment of your choice with unmatched flexibility and control. Be it in the cloud, on-premises, or on the edge, with:

✅ Complete control over your data and privacy
✅ Flexibility to deploy in any environment
✅ Seamless integration with every component of the modern AI stack

▶ ️Run Qdrant as a managed service on our launch partners environments, such as @OracleCloud, @RedHat, @Vultr, @OVHcloud, @Scaleway, @DigitalOcean, STACKIT, @CivoCloud.

▶ Easily integrate Qdrant with our AI ecosystem launch partners such as @llama_index, @langchain, @AirbyteHQ, @JinaAI_, @Aleph__Alpha, @Haystack_AI by @deepset_ai

🎓Together with our launch partners, we created in-depth tutorials that show the flexibility of using Qdrant Hybrid Cloud for AI-enabled use cases, like RAG, hybrid search, recommendation systems, and more, prioritizing deployment flexibility and data privacy.

[Pau Labarta Bajo @paulabartabajo_]

Looking for the right 𝗩𝗲𝗰𝘁𝗼𝗿 𝗗𝗕 for you 🫵?
This is how I found mine 🧠↓

𝗖𝗼𝗻𝘁𝗲𝘅𝘁 🖼️
There are many Vector DB vendors these days. And the thing is, when your goal is to build a RAG demo, any of them will do the job.

However, when you want to build a production-ready RAG application, you need to be more careful.

𝗪𝗵𝘆? 🤔
There are 2 things you need to think of:

1️⃣ 𝗢𝗽𝗲𝗿𝗮𝘁𝗶𝗼𝗻𝗮𝗹 𝗰𝗼𝘀𝘁𝘀 💸
How many hours and money will I have to spend to keep my Vector DB service up and running 24/7?

Ideally 0. And this is precisely what Managed Vector DBs bring to the table.

Most Vector DB vendors currently offer a Managed platform, which sounds perfect but it is not always the right choice if you are concerned about your data privacy.

2️⃣ 𝗗𝗮𝘁𝗮 𝗽𝗿𝗶𝘃𝗮𝗰𝘆 💾
A Vector DB stores your data, so if your data is highly sensitive, it is not a good idea to send it over the internet and store it on an external service, like a Managed Vector DB.

Which means you are forced to spin up your own Vector DB service, which automatically increases your operational costs 😵‍💫

𝗤𝘂𝗲𝘀𝘁𝗶𝗼𝗻❓
Is there any Vector DB that offers the best from both worlds 🌎🌍

→ A Managed Vector DB, that
→ Does NOT store your private data
?

Yes. It is called Qdrant 🚀

𝗦𝗼𝗹𝘂𝘁𝗶𝗼𝗻 🧠
@qdrant_engine has just launched the Qdrant Hybrid Cloud ☁️, that separates

→ 𝘁𝗵𝗲 𝗱𝗮𝘁𝗮 𝗽𝗹𝗮𝗻𝗲 💾, where the data is stored and processed, from
→ 𝘁𝗵𝗲 𝗰𝗼𝗻𝘁𝗿𝗼𝗹 𝗽𝗹𝗮𝗻𝗲 🎛️, which manages the cluster operations

So you get the best from both worlds.

→ A highly performant and 𝗺𝗮𝗻𝗮𝗴𝗲𝗱 𝗩𝗲𝗰𝘁𝗼𝗿 𝗗𝗕, that you can scale and upgrade with a few clicks, 🧠

plus

→ Your data 𝘀𝘁𝗮𝘆𝘀 𝗮𝘁 𝗵𝗼𝗺𝗲 🏠

Boom.

If you want to learn more about the new Qdrant Hybrid Cloud, check this blog post
↓↓↓
https://t.co/7DhbN8hQM8

[OVHcloud @OVHcloud]

📣 @qdrant_engine and OVHcloud collaborate to bring Vector Search to Startups & Enterprises in Europe with a strong Focus on Data Control and Privacy! 🔐 We are excited about this partnership, which has been established through our #OpenTrustedCloud Program. 🤝 #OVHcloud #Qdrant

[Qdrant @qdrant_engine]

We’re excited to announce the launch of Qdrant Hybrid Cloud, the first-ever managed vector database you can deploy anywhere—cloud, on-premise, or edge— designed for true deployment flexibility, data sovereignty, privacy, and control.

Why is this big? 🚀

Deployment flexibility and data sovereignty are critical as the industry moves from prototyping to deploying production-ready AI applications.

Easy integration with existing systems complements these advantages, streamlining development and operations.

Key benefits of the Hybrid Cloud:
✔️ Deploy Anywhere: Deploy Qdrant in any environment of choice with our Kubernetes-native design.
✔️ Full Data Sovereignty: Enjoy privacy control with decoupled data and control planes with complete database isolation.
✔️ Fully Managed: Enjoy the benefits of a managed vector database within your own environment.
✔️ Effortless Setup: One-line installation by simply adding your environment to your Qdrant Cloud account.

Thank you to our trusted launch partners for their collaboration:
@OracleCloud, @RedHat, @Vultr, @OVHcloud, @Scaleway, @DigitalOcean, STACKIT, @llama_index, @langchain, @AirbyteHQ, @CivoCloud, @JinaAI_, @Aleph__Alpha, @Haystack_AI by @deepset_ai.

[Andre Zayarni @andre_z]

Qdrant @qdrant_engine was not accepted into GSoC 2024. But we decided to introduce our own Summer of Code program. Please find details here. https://t.co/YvICH0EkI4

[Tim McNamara @timClicks]

Is this true?

[Qdrant @qdrant_engine]

It is time for us to update our famous Vector DB benchmark.

Here is what has changed since the last run and what has not: 🧵 👇

[Tim Eggert @elbartus]

@ptrwllrt @telgorn Nur mal checken ob du noch mitliest

[No Context Brits @NoContextBrits]

Never forget.

[Charlie Holtz @charlieholtz]

David Attenborough is now narrating my life

Here's a GPT-4-vision + @elevenlabs python script so you can star in your own Planet Earth:

[Andre Zayarni @andre_z]

Meet the new Recommendations API in @qdrant_engine v 1.6

[Qdrant @qdrant_engine]

Just 2 days until our inaugural vector space virtual talks! 🚀

Join us for a deep dive into the world of Vector Search with Andrey Vasnetsov, CTO at Qdrant. Don't miss it!

📆 Date: October 26, 2023
🕒 Time: 5:00pm GMT+2
🌐 Link to event: https://t.co/o7kAWdOtIo

[Qdrant @qdrant_engine]

Qdrant #vectordatabase is now available on Google Cloud Marketplace and can be easily used via a #GCP account to build scalable next-generation #AI applications. 🎉
https://t.co/koqWk9yPP7

[Qdrant @qdrant_engine]

The repository has already seen a lot of love from the community while under development, and we're happy to share more details in this launch article: https://t.co/kanjIEh0Cz

[Qdrant @qdrant_engine]

On a large-scale production deployment, it is important to have synchronization between the Primary and Specialized storage.

Starting today, we have a streamlined solution.

We are introducing an integration with @AirbyteHQ ETL platform!