Struct HelixDBVectorStore 

pub struct HelixDBVectorStore<C, E> { /* private fields */ }

A client for easily carrying out Rig-related vector store operations.

If you are unsure what type to use for the client, helix_rs::HelixDB is the typical default.

Usage:

let openai_model =
    rig::providers::openai::Client::from_env().embedding_model("text-embedding-ada-002");

let helixdb_client = HelixDB::new(None, Some(6969), None);
let vector_store = HelixDBVectorStore::new(helixdb_client, openai_model.clone());

Implementations

impl<C, E> HelixDBVectorStore<C, E>

where C: HelixDBClient + Send, E: EmbeddingModel,

pub fn new(client: C, model: E) -> Self

pub fn client(&self) -> &C

Trait Implementations

impl<C, E> InsertDocuments for HelixDBVectorStore<C, E>

where C: HelixDBClient + Send + Sync, E: EmbeddingModel + Send + Sync,

async fn insert_documents<Doc: Serialize + Embed + Send>( &self, documents: Vec<(Doc, OneOrMany<Embedding>)>, ) -> Result<(), VectorStoreError>

impl<C, E> VectorStoreIndex for HelixDBVectorStore<C, E>

where C: HelixDBClient + Send + Sync, E: EmbeddingModel + Send + Sync,

type Filter = Filter<Value>

The filter type for this backend.

async fn top_n<T: for<'a> Deserialize<'a> + Send>( &self, req: VectorSearchRequest<HelixDBFilter>, ) -> Result<Vec<(f64, String, T)>, VectorStoreError>

Returns the top N most similar documents as (score, id, document) tuples.

async fn top_n_ids( &self, req: VectorSearchRequest<HelixDBFilter>, ) -> Result<Vec<(f64, String)>, VectorStoreError>

Returns the top N most similar document IDs as (score, id) tuples.