Weaviate - The AI-first search engine 💡

Hi developers, data scientists, and all those interested in ML & AI 👋 I'm Bob, one of the co-founders of SeMI Technologies. I'm super excited to share the vector search engine Weaviate with you today on PH. We've created Weaviate because we believe that there was a need for a new type of search engine (or database) with machine learning at its core. The video above will give you an overview of the functionality of Weaviate, but you can also try it yourself by going to our Github or documentation. If you are a developer looking for a more detailed explanation of what Weaviate is: Weaviate is a low-latency vector search engine with out-of-the-box support for different media types (text, images, etc.). It offers Semantic Search, Question-Answer-Extraction, Classification, Customizable Models (PyTorch/TensorFlow/Keras), and more. Built from scratch in Go, Weaviate stores both objects and vectors, allowing for combining vector search with structured filtering with the fault-tolerance of a cloud-native database, all accessible through GraphQL, REST, and various language clients. You can follow us on Github, Twitter, or LinkedIn and you can join our Slack or Meetup groups. Github: https://github.com/semi-technolo... Slack: https://link.semi.technology/3d3... Documentation: https://www.semi.technology/deve... We love to hear what you think! Cheers

I've been watching the space for semantic document search for quite some time now. I've worked with many systems - Elastic Search, Jina, Haystack, GPT-3 semantic search... you name it. They are either limited in what they can do or how much data they can handle, are very expensive to run, hard to set up, or take a long time to process queries. That's why I've continually been searching for better solutions. And that's how I found Weaviate. This system is the first where I'm actually up and running within a day. It can search through Gigabytes of text within a fraction of a second. I don't need an expensive GPU server to get good search results. And setting up the database, ingesting documents and querying the index in Python just takes a few lines of code. It's a really clean and elegant solution. To me, using Weaviate feels like using Stripe. It's fast, it's fun, and it just works. And that is awesome, because it means that the search itself is taken care of, and I can focus on building on top of it.