Why?
From Wikipedia: "A vector database management system (VDBMS) or simply vector database or vector store is a database that can store vectors (fixed-length lists of numbers) along with other data items. Vector databases typically implement one or more Approximate Nearest Neighbor (ANN) algorithms, so that one can search the database with a query vector to retrieve the closest matching database records."
In order for LLMs to use existing and corpus for its reasoning and response generation, that corpus should be indexed in a semantically significant way.
What?
Create a Vector database and prompt it for retrieval-augemented generation (RAG) using Midokura data.
Progress is collected on the LLM page of the Advanced Development department confluence page
Why?
From Wikipedia: "A vector database management system (VDBMS) or simply vector database or vector store is a database that can store vectors (fixed-length lists of numbers) along with other data items. Vector databases typically implement one or more Approximate Nearest Neighbor (ANN) algorithms, so that one can search the database with a query vector to retrieve the closest matching database records."
In order for LLMs to use existing and corpus for its reasoning and response generation, that corpus should be indexed in a semantically significant way.