Weaviate is hiring! 🌟 Join our team and help shape the future of AI technology. Check out our open roles: • Event Marketing Manager: https://lnkd.in/d4sK7kNq • Senior Software Engineer Database: https://lnkd.in/daa2F-uM • Revenue Operations Manager: https://lnkd.in/dSkHt2uh • Client-Focused Site Reliability Engineer: https://lnkd.in/dAvgickM • Machine Learning Engineer: https://lnkd.in/edunj5yu Explore more roles and learn more about them on our Careers page: https://lnkd.in/dzibHnwZ Stay tuned for more opportunities coming soon! 👀
Weaviate
Technologie, informatie en internet
Amsterdam, North Holland 19.506 volgers
The AI-native database for a new generation of software.
Over ons
Weaviate is a cloud-native, real-time vector database that allows you to bring your machine-learning models to scale. There are extensions for specific use cases, such as semantic search, plugins to integrate Weaviate in any application of your choice, and a console to visualize your data.
- Website
-
https://weaviate.io
Externe link voor Weaviate
- Branche
- Technologie, informatie en internet
- Bedrijfsgrootte
- 51 - 200 medewerkers
- Hoofdkantoor
- Amsterdam, North Holland
- Type
- Particuliere onderneming
- Opgericht
- 2019
Locaties
-
Primair
Amsterdam, North Holland, NL
Medewerkers van Weaviate
Updates
-
What is an AI-native application? An AI-native application leverages AI as the core framework, allowing seamless application creation and management without traditional programming. In the 100th Weaviate Podcast, Lucas Negritto shares this new approach where the LLM (Language Learning Model) handles everything from state management to routing, transforming how applications are built. YouTube: https://lnkd.in/e8xJJ9Rc Spotify: https://lnkd.in/egqdfcqj
-
Weaviate heeft dit gerepost
-
Want to super-power your RAG systems? In this short Victoria Slocum covers two ways to use generative queries in Weaviate: 1️⃣ Single Prompt Search: This create a seperate LLM call for each object retrieved from the database individually. You can customize responses by defining object properties within the prompt. Imagine translating retrieved information into Spanish – you'd need a separate AI call for each item. 2️⃣ Grouped Task Search: This generates a single response using all retrieved objects and their properties. This is ideal for systems like RAG (Retrieval-Augmented Generation) where the AI needs all the context at once. By saving generated results directly back into the database, we can create a generative feedback loop to reuse the material and make our RAG system even more powerful ✨ Read more: https://lnkd.in/eZjzCfjM Or watch the full video: https://lnkd.in/eEXrEfVG
-
Retrieval Augmented Generation (RAG) is one of the most promising AI use cases, as it enables teams across all industries to leverage the power of LLMs with their own data. But it's one thing to develop a prototype - another to use RAG in production. In our upcoming online hands-on session, Zain Hasan will cover best practices, options, and strategies to overcome some of the challenges when bringing RAG applications effectively to production. Come and Join - we are excited to welcome you 🤗
Deze content is hier niet beschikbaar
Open deze content en meer in de LinkedIn-app
-
We’re excited to share that Weaviate was included in Sifted’s B2B SaaS Rising 100 rising startups of 2024! See the full list: https://lnkd.in/eRzhnNcu
-
🥳 That’s a wrap for this edition of Hack Night at GitHub! It was a blast hacking with all of you and seeing your demos. Congrats to all the prize winners! 🎉 We’re hosting another Hack Night in August. It’s going to be another fun one. If you missed this Hack Night, come to our next one on August 13th . It’s time for RAG Hack Night at GitHub! https://lu.ma/p13pkknm
-
We’re excited to share the full list of speakers for our upcoming event AI [in Prod] in Chicago! Join us to gain insights from experts building enterprise-grade AI applications, meet fellow builders, and learn how to take your own projects to the next level with our hands-on training. Space is limited! Request a ticket here: https://lnkd.in/dGx9A6V7 Benjamin Barrett • Etienne Dilocker • Aisis Julian • Anthony Loss • Zain Hasan • Sebastian Witalec • Innovative Solutions • Morningstar • Amazon Web Services (AWS) Partners
-
Want higher search accuracy? 🎯 Vector search is fast and accurate, but reranking models can boost it even more! Here's how: • Overfetching: Fetch more results than needed (e.g., fetch 50 to get the top 10). • Reranking: A reranker evaluates and reorders the results based on relevance. Ready to try? Choose a reranking model, like Cohere’s rerank-v3.0 models, Voyage AI’s rerank-1 model, or the open source rerankers by mixedbread.ai. Integrated with Weaviate, these models are easy to use with just one line of code! Learn more: https://lnkd.in/eakjTh_J