Seonglae ChoVector Similarity
Bridges the gap between Information retrieval and Memory retention in LLM
Useful traditional database is Postgres Vector or Redis Search
Bottleneck is Disk System IO capacity
Vector Databases
Vector Database Notion
Architecture
Building a Vector Database for Scalable Similarity Search
The first one in a blog series to take a closer look at the thought process and design principles behind the building of the most popular open-source vector database.
https://milvus.io/blog/deep-dive-1-milvus-architecture-overview.md
What is a Vector Database? | Pinecone
Complex data is growing at break-neck speed. These are unstructured forms of data that include documents, images, videos, and plain text on the web. Many organizations would benefit from storing and analyzing complex data, but complex data can be difficult for traditional databases built with structured data in mind.
https://www.pinecone.io/learn/vector-database/
Semantic Search in Vector Database for Conversational AI
Semantic search is a type of search that is based on the meaning of words and their relationships to one another. It is a way of searching…
https://kumar-vodex.medium.com/semantic-search-in-vector-database-in-conversational-ai-b34c89a9974
We should consider embeddings as derived data (like DB Index) instead of independent data
Vector Databases Are the Wrong Abstraction
Today’s vector databases disconnect embeddings from their source data. We should treat embeddings more like database indexes—here’s how.
https://www.timescale.com/blog/vector-databases-are-the-wrong-abstraction/
