Logo
Modules/Embedding/Available_embeddings

Ollama

To use Ollama embeddings, you need to import OllamaEmbedding from @llamaindex/ollama.

Note that you need to pull the embedding model first before using it.

In the example below, we're using the nomic-embed-text model, so you have to call:

ollama pull nomic-embed-text

Installation

npm install llamaindex @llamaindex/ollama
import { OllamaEmbedding } from "@llamaindex/ollama";
import { Document, Settings, VectorStoreIndex } from "llamaindex";
 
Settings.embedModel = new OllamaEmbedding({ model: "nomic-embed-text" });
 
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,
});

API Reference

Edit on GitHub

Last updated on

Previous

MixedbreadAI

Next

OpenAI

On this page