Embedding Models
You can provide your own embedding model to generate embeddings for the data. There are more than 20+ embedding models supported by QvikChat through LangChain. To check the list of available embedding models, refer to this page Embedding models (opens in a new tab).
To use an embedding model, simply provide the instance to the getDataRetriever method. The below example shows how you can use an OpenAI embedding model to generate embeddings for the data.
// import embedding model
import { getDataRetriever } from "@oconva/qvikchat/data-retrievers";
import { OpenAIEmbeddings } from "@langchain/openai";
// Index data and get retriever
const dataRetriever = await getDataRetriever({
filePath: "test.csv",
generateEmbeddings: true,
embeddingModel: new OpenAIEmbeddings({
apiKey: process.env.OPENAI_API_KEY, // checks for OPENAI_API_KEY in .env file by default if not provided
batchSize: 512, // Default value if omitted is 512. Max is 2048
model: "text-embedding-3-large", // model name
}),
});If you wish to use a Google Gen AI or an OpenAI embedding model, you can use the getEmbeddingModel method to get the embedding model instance.
import { getDataRetriever } from "@oconva/qvikchat/data-retrievers";
import { getEmbeddingModel } from "@oconva/qvikchat/embedding-models";
import { FaissStore } from "@langchain/community/vectorstores/faiss";
// Index data and get retriever
const dataRetriever = await getDataRetriever({
filePath: "test.csv",
generateEmbeddings: true,
vectorStore: new FaissStore(getEmbeddingModel(), {
index: "test-index",
}),
});