README
- ::addWeaviateStore::add
- ::clearWeaviateStore::clear
- ::createWeaviateStore::create
- ::deleteWeaviateStore::delete
- ::lenWeaviateStore::len
- ::newWeaviateStore::new
- ::searchWeaviateStore::search

moonweavte

A Weaviate vector store for moonbitstack/moonrag, over its REST API.

moonrag

weavte

vector-store

vector-database

moonbit

Download zip

Author

moonbitstack

Version

0.1.0

License

Apache-2.0

Repository

github.com/moonbitstack/moonrag

Last updated

9 hours ago

Downloads

#moonweavte

A Weaviate vector store for moonrag, over its REST API. Native only: it opens sockets, so it is not built for js or wasm.

moon add moonbitstack/moonweavte

let store = @moonweavte.WeaviateStore::new("http://127.0.0.1:8080", embedder, dimension=256)

It implements moonrag's VectorStore. Like the in-memory, SQLite and MySQL stores it recomputes the cosine in this process and ranks by the same Filter::matches, so its results agree with the other backends rather than trusting the server.

See this store's page, the guide and the API.

WeaviateStore

source

pub struct WeaviateStore {
  base : String
  class_name : String
  embedder : &@moonbitstack/moonrag.Embedder
Embedder
  dimension : Int
  counter : Int
}

impl VectorStore for WeaviateStore

async fn add(self : WeaviateStore, documents : Array[@moonbitstack/moonrag.Document
Document]) -> Array[String]

source

Embed documents, store them, and return the ids they are stored under.

async fn delete(self : WeaviateStore, ids : ArrayView[String]) -> Unit

source

Delete the objects stored under ids. An id not present is not an error.

async fn search(self : WeaviateStore, vector : ArrayView[Double], limit~ : Int, filter? : @moonbitstack/moonrag.Filter
Filter) -> Array[@moonbitstack/moonrag.Scored
Scored]

source

The best limit documents for vector, best first. Every object is read back with its vector, then filtered, scored and ranked here.

WeaviateStore::add

source

async fn WeaviateStore::add(self : WeaviateStore, documents : Array[@moonbitstack/moonrag.Document
Document]) -> Array[String]

WeaviateStore::clear

source

async fn WeaviateStore::clear(self : WeaviateStore) -> Unit

Remove every stored object, leaving the class.

WeaviateStore::create

source

async fn WeaviateStore::create(self : WeaviateStore) -> Unit

Create the class this store needs. Safe on every start: an existing class answers 422, which is not an error here.

WeaviateStore::delete

source

async fn WeaviateStore::delete(self : WeaviateStore, ids : ArrayView[String]) -> Unit

WeaviateStore::len

source

async fn WeaviateStore::len(self : WeaviateStore) -> Int64

The number of stored objects.

WeaviateStore::new

source

fn WeaviateStore::new(base : String, embedder : &@moonbitstack/moonrag.Embedder
Embedder, dimension~ : Int, class_name? : String) -> WeaviateStore raise

A store over the Weaviate server at base (for example http://127.0.0.1:8080), in class class_name.

WeaviateStore::search

source

async fn WeaviateStore::search(self : WeaviateStore, vector : ArrayView[Double], limit~ : Int, filter? : @moonbitstack/moonrag.Filter
Filter) -> Array[@moonbitstack/moonrag.Scored
Scored]