Picking a vector database: a comparison and guide for 2023
benchmark.vectorview.ai
Picking a vector database: a comparison and guide for 2023
LanceDB
LanceDB is an open-source vector database for AI that's designed to store, manage, query and retrieve embeddings on large-scale multi-modal data. The core of LanceDB is written in Rust 🦀 and is built on top of Lance, an open-source columnar data format designed for performant ML workloads and fast random access.
Both the database and the un... See more
LanceDB is an open-source vector database for AI that's designed to store, manage, query and retrieve embeddings on large-scale multi-modal data. The core of LanceDB is written in Rust 🦀 and is built on top of Lance, an open-source columnar data format designed for performant ML workloads and fast random access.
Both the database and the un... See more
LanceDB - LanceDB
latest research on text embeddings!
TLDR: Vector databases are NOT safe. Text embeddings can be inverted. We can do this exactly for sentence-length inputs and get very close with paragraphs...
TLDR: Vector databases are NOT safe. Text embeddings can be inverted. We can do this exactly for sentence-length inputs and get very close with paragraphs...
jack morris • Tweet
Vector stores come in when working with large documents, where the document needs to be chunked up in order to be passed to the LLM. These parts of the document would be stored as embeddings, which means that they are vector representations of the information.