Struct MilvusVectorStore 

pub struct MilvusVectorStore<M> { /* private fields */ }

Represents a vector store implementation using Milvus - https://milvus.io/ as the backend.

Implementations

impl<M> MilvusVectorStore<M>

where M: EmbeddingModel,

pub fn new( model: M, base_url: String, database_name: String, collection_name: String, ) -> Self

Creates a new instance of MilvusVectorStore.

Arguments

• model - Embedding model instance
• base_url - The URL of where your Milvus instance is located. Alternatively if you’re using the Milvus offering provided by Zilliz, your cluster endpoint.
• database_name - The name of your database
• collection_name - The name of your collection

pub fn auth(self, username: String, password: String) -> Self

Forms the auth token for Milvus from your username and password. Required if using a Milvus instance that requires authentication.

Trait Implementations

impl<Model> InsertDocuments for MilvusVectorStore<Model>

where Model: EmbeddingModel + Send + Sync,

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

Insert precomputed embeddings for each document.

impl<M> VectorStoreIndex for MilvusVectorStore<M>

where M: EmbeddingModel,

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

Search for the top n nearest neighbors to the given query within the Milvus vector store. Returns a vector of tuples containing the score, ID, and payload of the nearest neighbors.

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

Search for the top n nearest neighbors to the given query within the Milvus vector store. Returns a vector of tuples containing the score and ID of the nearest neighbors.

type Filter = Filter

The filter type for this backend.

impl<M> VectorStoreIndexDyn for MilvusVectorStore<M>

where M: EmbeddingModel + Sync + Send,

fn top_n_ids<'a>( &'a self, req: VectorSearchRequest<CoreFilter<Value>>, ) -> WasmBoxedFuture<'a, Result<Vec<(f64, String)>, VectorStoreError>>

Implement the top_n_ids method of the VectorStoreIndex trait for MongoDbVectorIndex.

fn top_n<'a>( &'a self, req: VectorSearchRequest<CoreFilter<Value>>, ) -> WasmBoxedFuture<'a, TopNResults>

Returns the top N documents for a JSON-serializable request.