lvv 0.4.2

A pipeline for embedding datasets with LLMs (Ollama/OpenAI) and loading them into a Qdrant vector database, with caching and job queuing.
Documentation 
1
2
3
4
5
6
7
8

pub mod sink;
pub mod vector_database;
pub use qdrant_client::qdrant::Distance;
pub use sink::{QdrantSink, Sink, SinkContext};
pub use vector_database::QdrantDatabase;

#[cfg(feature = "postgres")]
pub use sink::PostgresSink;