Struct MongoDbVectorIndex 

pub struct MongoDbVectorIndex<C, M>
where
    C: Send + Sync,
    M: EmbeddingModel,
{ /* private fields */ }

A vector index for a MongoDB collection.

Example

use rig_mongodb::{MongoDbVectorIndex, SearchParams};
use rig::{providers::openai, vector_store::VectorStoreIndex, client::{ProviderClient, EmbeddingsClient}};

#[derive(serde::Deserialize, serde::Serialize, Debug)]
struct WordDefinition {
    #[serde(rename = "_id")]
    id: String,
    definition: String,
    embedding: Vec<f64>,
}

let mongodb_client = mongodb::Client::with_uri_str("mongodb://localhost:27017").await?; // <-- replace with your mongodb uri.
let openai_client = openai::Client::from_env();

let collection = mongodb_client.database("db").collection::<WordDefinition>(""); // <-- replace with your mongodb collection.

let model = openai_client.embedding_model(openai::TEXT_EMBEDDING_ADA_002); // <-- replace with your embedding model.
let index = MongoDbVectorIndex::new(
    collection,
    model,
    "vector_index", // <-- replace with the name of the index in your mongodb collection.
    SearchParams::new(), // <-- field name in `Document` that contains the embeddings.
)
.await?;

// Query the index
let definitions = index
    .top_n::<WordDefinition>("My boss says I zindle too much, what does that mean?", 1)
    .await?;

Implementations

impl<C, M> MongoDbVectorIndex<C, M>

where M: EmbeddingModel, C: Send + Sync,

pub async fn new( collection: Collection<C>, model: M, index_name: &str, search_params: SearchParams, ) -> Result<Self, VectorStoreError>

Create a new MongoDbVectorIndex.

The index (of type “vector”) must already exist for the MongoDB collection. See the MongoDB documentation for more information on creating indexes.

Trait Implementations

impl<C, M> InsertDocuments for MongoDbVectorIndex<C, M>

where C: Send + Sync, M: EmbeddingModel + Send + Sync,

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

Insert documents into the vector store.

impl<C, M> VectorStoreIndex for MongoDbVectorIndex<C, M>

where C: Sync + Send, M: EmbeddingModel + Sync + Send,

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

Implement the top_n method of the VectorStoreIndex trait for MongoDbVectorIndex.

VectorSearchRequest similarity search threshold filter gets ignored here because it is already present and can already be added in the MongoDB vector store struct.

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

Implement the top_n_ids method of the VectorStoreIndex trait for MongoDbVectorIndex.