What is a 𝗩𝗲𝗰𝘁𝗼𝗿 𝗗𝗮𝘁𝗮𝗯𝗮𝘀𝗲?

What is a 𝗩𝗲𝗰𝘁𝗼𝗿 𝗗𝗮𝘁𝗮𝗯𝗮𝘀𝗲?

With the rise of Foundational Models, Vector Databases skyrocketed in popularity. The truth is that a Vector Database is also useful outside of a Large Language Model context.

When it comes to Machine Learning, we often deal with Vector Embeddings. Vector Databases were created to perform specifically well when working with them:

➡️ Storing.
➡️ Updating.
➡️ Retrieving.

When we talk about retrieval, we refer to retrieving set of vectors that are most similar to a query in a form of a vector that is embedded in the same Latent space. This retrieval procedure is called Approximate Nearest Neighbour (ANN) search.

A query here could be in a form of an object like an image for which we would like to find similar images. Or it could be a question for which we want to retrieve relevant context that could later be transformed into an answer via a LLM.

Let’s look into how one would interact with a Vector Database:

𝗪𝗿𝗶𝘁𝗶𝗻𝗴/𝗨𝗽𝗱𝗮𝘁𝗶𝗻𝗴 𝗗𝗮𝘁𝗮.

1. Choose a ML model to be used to generate Vector Embeddings.
2. Embed any type of information: text, images, audio, tabular. Choice of ML model used for embedding will depend on the type of data.
3. Get a Vector representation of your data by running it through the Embedding Model.
4. Store additional metadata together with the Vector Embedding. This data would later be used to pre-filter or post-filter ANN search results.
5. Vector DB indexes Vector Embedding and metadata separately. There are multiple methods that can be used for creating vector indexes, some of them: Random Projection, Product Quantization, Locality-sensitive Hashing.
6. Vector data is stored together with indexes for Vector Embeddings and metadata connected to the Embedded objects.

𝗥𝗲𝗮𝗱𝗶𝗻𝗴 𝗗𝗮𝘁𝗮.

7. A query to be executed against a Vector Database will usually consist of two parts:

➡️ Data that will be used for ANN search. e.g. an image for which you want to find similar ones.
➡️ Metadata query to exclude Vectors that hold specific qualities known beforehand. E.g. given that you are looking for similar images of apartments - exclude apartments in a specific location.

8. You execute Metadata Query against the metadata index. It could be done before or after the ANN search procedure.
9. You embed the data into the Latent space with the same model that was used for writing the data to the Vector DB.
10. ANN search procedure is applied and a set of Vector embeddings are retrieved. Popular similarity measures for ANN search include: Cosine Similarity, Euclidean Distance, Dot Product.

Some popular Vector Databases: Qdrant, Pinecone, Weviate, Milvus, Faiss, Vespa.





Reference-
Attached white paper has instructions on attaching Persistent volume mounted on VAST storage to Milvus

    • Popular Articles

    • CP Plus Camera and NVR Configuration

      NVR Configuration The CP Plus Pro Series of NVRs have been meticulously designed for providing you with upgraded performance and higher recording quality in your IP video surveillance solution. The robust processor that has been inculcated in this ...

    • Kerberos Authentication – Overview

      What is Kerberos? Kerberos is a secure authentication method used in our Active Directory (AD) environment (mbuzztech.com). It allows users to: Access multiple systems without re-entering passwords (Single Sign-On – SSO) Log in once Where We Use It ...

    • How to Remove and Reinstall NVIDIA Drivers on Ubuntu

      This article provides step by step guide to completely remove existing NVIDIA drivers and reinstall specific version of the NVIDIA driver on the Ubuntu system Prerequisites Administrative (sudo) access to the Ubuntu system. Internet access to ...

    • Personal Computers and Servers - Classification and Point of Contact

      We can classify the computers that MBUZZ handles based on their form-factor as below: Tower Workstations, Desktops, Gaming PCs and SFF (Small form factor) PCs fall under this category. These are computers people would use on a desk and rarely move. ...

    • M.2 SSD Tier List

      The sequential read and write speeds, which are usually the most advertised number, are not a proper benchmark of real-world performance or the quality of an SSD. This article categorizes and tiers SSDs based on factors like the type of NAND flash, ...