To wrap up 2023, here are some vector database resources and a sneak peek into the new year! ๐
๐Open Source Advent
There are still a few days left of Zillizโs Open Source Advent! Did you know that the projects can be done in 30 minutes? Check all the projects in our Contest Discord.
Get your points submitted here by January 2nd, 2024 for a chance to win swag! Winners will be announced on January 8th, 2024. Good luck!
๐ Zilliz Cloud Pipelines - high-quality vector transformation made easy and fast
Zilliz Cloud Pipelines is a one-stop solution designed to simplify and streamline the transformation of unstructured data into optimized vector embeddings.
With Zilliz Cloud Pipelines, developers can:
- Use an ingestion pipeline to process unstructured data into searchable vector embeddings
- Use a search pipeline to enable semantic search by converting query text into vector embeddings
- Use a deletion pipeline to efficiently remove all chunks of a specified document from a collection
โถ๏ธ Read Blog
๐ท Watch Demo
๐ฆ Notebook using Pipelines inside LlamaIndex
Get started for free here.
๐ Choosing a vector database based on your needs
Check out this new article on InfoWorld How to evaluate a vector database by Li Liu, Principal Engineer at Zilliz. He deep-dives into the top 3 metrics when assessing a vector database: scalability, functionality, and performance. Read about these crucial metrics and learn more here.
๐ Looking ahead to 2024
Share your 2024 AI resolutions on this LinkedIn post ๐
๐๏ธ Mark your Calendars for January 2024 Events
January 11 - Vector Database 101: A Crash Course (virtual)
Hear from Developer Advocate Yujian Tang at our crash course webinar on January 11 covering vector database use cases and more!
Crash Course topics include:
- Why unstructured data is hard to work with
- An overview of common use cases that benefit from vector databases
- How to get your unstructured data into a vector database
- What to consider when evaluating and building your own vector database
- How to avoid common mistakes when getting started with a vector database
Register here.
January 16 - Unstructured Data Meetup SF (in-person)
Zilliz will be back at GitHub in San Francisco for our monthly Unstructured Data Meetup on January 16! Join us to learn about the following topics:
โถ๏ธ How to extract Tabular Data from PDFs for RAG Pipelines using Milvus with Jack Retterer
โถ๏ธ Vector Search in the Age of OpenAI Assistants using Milvus with Christy Bergman
โถ๏ธ Are CPUs Enough? A Review Of Vector Search Running On Novel Hardware with George Williams
Register here: https://lu.ma/vq31dazy
See you in the new year! ๐
Top comments (0)