Introduction I started seeing early in 2023, and my first thought was that it might be an attractive fit in the ecosystem or as a general replacement for the columnar file format. I was thinking too small, though. LanceDB Apache Iceberg Parquet It is an in-process multi-model serverless vector database written in Rust that is cloud-native and open-source. It’s not to be confused with the Lance columnar format (which I was doing), which is also written in Rust and a more appropriate comparison to Parquet but is fundamental to LanceDB. It is also compatible. Apache Arrow So, what we have is a SQL-compatible vector database that supports vectors, images, text, and videos with full-text search. It is also said to be very fast, but you’ll need to do your own tests to see how it does on your own stack. Why a Vector Database? Two letters, AI. A vector database is at the core of the data repository used to train Large Language Models (LLM). LanceDB has gone the extra mile to provide a GitHub repository with a few vector recipes that you can find . here So, you should store embeddings from a machine learning model, for example, to search for images using written descriptions. The challenge here is the “ ”; you can be fast or accurate but can’t be both; you have to pick one. LanceDB first went for speed, then did a lot of tuning to improve accuracy. Curse of dimensionality This leads to “Embeddings,” which are high-dimensional floating-point vector representations of a query or the data. You can embed anything using an appropriate embedding model or function. The position of the embedding in a vector space has semantic significance depending on the type of modal and training you are using. LanceDB supports “explicit” and “implicit” data vectorization methods. At this stage, we’re getting into some deep water concerning how this all works, and it is beyond the scope of what I’m trying to convey in this blog. I’ll share an image from the LanceDB docs that illustrates how similar entries cluster within a vector system. The LanceDB ecosystem provides all the latest and most commonly used tools for this space to make it as convenient as possible to get started. You can use Python and Javascript to process your data into LanceDB, using popular Python machine learning and columnar data packages. A native Typescript SDK is available to allow for vectorless search as part of serverless functions. What isn’t listed here is the new integrations, making that LLM work even easier. LangChain That’s not all though, so to put it in a list, we also see: Duckdb LangChain JS/TS LlamaIndex Voxel51 There is a great, recent blog, “ ” by Ayush Chaurasia, that I highly recommend. He gives a quick walkthrough using Nextjs, LanceDB, and Roboflow’s CLIP inference API. If you'd like to dive a little deeper, it’s a specific deep dive with example code. Serverless Multi-Modal search application Summary Obviously, LanceDB isn’t a general-purpose database, it has a very specific use case, and from what I can tell, it’s a solid solution for that use case. It is an extremely fast vector database that can be used specifically in AI applications. I can envision some really useful scenarios for building up your own LLM around product blogs and documentation with this, to enable users to write specific questions and get more tailored responses than trying to read through tons of blogs and docs. This could be the beginning of a tide shift in how we provide information to the public. Finally, a LanceDB Cloud is coming, and at the time of this writing, in October 2023, you can sign up to be notified about it at this . I’m excited to give that a try and run some tests on ideas that have been bouncing around in my head since ChatGPT started grabbing everyone's attention. link You can read the other “What the heck” articles at these links: (I was pretty out front on this one.) What The Heck Is DuckDB? (I was out front on this one, too.) What the Heck Is Malloy? (slower, but also growing) What the Heck is PRQL? (growing quickly) What the Heck is GlareDB? (interest is hot) What the Heck is SeaTunnel?

What the Heck Is LanceDB?

About Author

Comments

TOPICS

THIS ARTICLE WAS FEATURED IN

Related Stories

How to Add Real-Time Web Search to Your LLM

Building a RAG System That Runs Completely Offline

5 Surprising Ways Today's AI Fails to Actually "Think"

If Data Is the New Oil, We Already Built a Planet-Sized Spill

Why Your GenAI Strategy Demands an All-Inclusive Data Modernization

Hugging Face's FineVision: Messy Data is Better Than You Think

How to Add Real-Time Web Search to Your LLM

Building a RAG System That Runs Completely Offline

5 Surprising Ways Today's AI Fails to Actually "Think"

If Data Is the New Oil, We Already Built a Planet-Sized Spill

Why Your GenAI Strategy Demands an All-Inclusive Data Modernization

Hugging Face's FineVision: Messy Data is Better Than You Think

Light-Mode

Classic

Newspaper

Minty

Dark-Mode

Neon Noir

Minty

HN StartUps