agsamantha/node_modules/@langchain/community/dist/embeddings/tensorflow.d.ts

60 lines
2.3 KiB
TypeScript
Raw Normal View History

2024-10-02 15:15:21 -05:00
import { load } from "@tensorflow-models/universal-sentence-encoder";
import { Embeddings, type EmbeddingsParams } from "@langchain/core/embeddings";
/**
* Interface that extends EmbeddingsParams and defines additional
* parameters specific to the TensorFlowEmbeddings class.
*/
export interface TensorFlowEmbeddingsParams extends EmbeddingsParams {
}
/**
* Class that extends the Embeddings class and provides methods for
* generating embeddings using the Universal Sentence Encoder model from
* TensorFlow.js.
* @example
* ```typescript
* const embeddings = new TensorFlowEmbeddings();
* const store = new MemoryVectorStore(embeddings);
*
* const documents = [
* "A document",
* "Some other piece of text",
* "One more",
* "And another",
* ];
*
* await store.addDocuments(
* documents.map((pageContent) => new Document({ pageContent }))
* );
* ```
*/
export declare class TensorFlowEmbeddings extends Embeddings {
constructor(fields?: TensorFlowEmbeddingsParams);
_cached: ReturnType<typeof load>;
/**
* Private method that loads the Universal Sentence Encoder model if it
* hasn't been loaded already. It returns a promise that resolves to the
* loaded model.
* @returns Promise that resolves to the loaded Universal Sentence Encoder model.
*/
private load;
private _embed;
/**
* Method that takes a document as input and returns a promise that
* resolves to an embedding for the document. It calls the _embed method
* with the document as the input and processes the result to return a
* single embedding.
* @param document Document to generate an embedding for.
* @returns Promise that resolves to an embedding for the input document.
*/
embedQuery(document: string): Promise<number[]>;
/**
* Method that takes an array of documents as input and returns a promise
* that resolves to a 2D array of embeddings for each document. It calls
* the _embed method with the documents as the input and processes the
* result to return the embeddings.
* @param documents Array of documents to generate embeddings for.
* @returns Promise that resolves to a 2D array of embeddings for each input document.
*/
embedDocuments(documents: string[]): Promise<number[][]>;
}