Logo
Modules/Models/Embedding

Gemini

To use Gemini embeddings, you need to import GeminiEmbedding from @llamaindex/google.

Installation

npm i llamaindex @llamaindex/google
pnpm add llamaindex @llamaindex/google
yarn add llamaindex @llamaindex/google
bun add llamaindex @llamaindex/google
import { Document, Settings, VectorStoreIndex } from "llamaindex";
import { GeminiEmbedding, GEMINI_MODEL } from "@llamaindex/google";

// Update Embed Model
Settings.embedModel = new GeminiEmbedding();

const document = new Document({ text: essay, id_: "essay" });

const index = await VectorStoreIndex.fromDocuments([document]);

const queryEngine = index.asQueryEngine();

const query = "What is the meaning of life?";

const results = await queryEngine.query({
  query,
});

Per default, GeminiEmbedding is using the gemini-pro model. You can change the model by passing the model parameter to the constructor. For example:

import { GEMINI_MODEL, GeminiEmbedding } from "@llamaindex/google";

Settings.embedModel = new GeminiEmbedding({
  model: GEMINI_MODEL.GEMINI_PRO_LATEST,
});

API Reference

Edit on GitHub

Last updated on