Build Your First Question Answering Application With Vector Search Engine Weaviate
Event Details
| Location | Room 2 (Classroom A) | |
| Date | May 2, 2022 | |
| Time | 5:00 PM to 6:30 PM |
In machine learning, e.g. recommendation tools or data classification, data is often represented as high-dimensional vectors. These vectors are stored in so-called vector databases. With vector databases you can efficiently run searching, ranking and recommendation algorithms. In addition, you can link vectors to create a knowledge graph (e.g. https://github.com/semi-technologies/biggraph-wikidata-search-with-weaviate).
This session is all about vector databases. If you are a data scientist or data/software engineer this session would be interesting for you. You will learn how you can easily run your favourite ML models with the vector database Weaviate. You’ll get an overview of what a vector database like Weaviate can offer: such as making data relations, semantic search, question answering, data classification, named entity recognition, multimodal search, and much more. After this session, you are able to load in your own data and query it with your preferred ML model!
1: What is a vector database?
You’ll learn the basic principles of vector databases. How data is stored, retrieved, and how that differs from other database types (SQL, knowledge graphs, etc).
2: Performing your first semantic search with the vector database Weaviate.
In this phase, you will learn how to set up a Weaviate vector database, how to make a data schema, how to make relations within data, how to load in data, and how to query data. You can follow along with examples or you can use your own dataset.
3: Advanced search with the vector database Weaviate.
Finally, we will cover other functionalities of Weaviate: multi-modal search, data classification, connecting custom ML models, etc.