跳到主要内容

Jina AI Reranker

The Jina AI Reranker is a postprocessor that uses the Jina AI Reranker API to rerank the results of a search query.

Setup​

Firstly, you will need to install the llamaindex package.

pnpm install llamaindex

Now, you will need to sign up for an API key at Jina AI. Once you have your API key you can import the necessary modules and create a new instance of the JinaAIReranker class.

import {
  JinaAIReranker,
  Document,
  OpenAI,
  VectorStoreIndex,
  Settings,
} from "llamaindex";

Load and index documents​

For this example, we will use a single document. In a real-world scenario, you would have multiple documents to index.

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

Settings.llm = new OpenAI({ model: "gpt-3.5-turbo", temperature: 0.1 });

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

Increase similarity topK to retrieve more results​

The default value for similarityTopK is 2. This means that only the most similar document will be returned. To retrieve more results, you can increase the value of similarityTopK.

const retriever = index.asRetriever();
retriever.similarityTopK = 5;

Create a new instance of the JinaAIReranker class​

Then you can create a new instance of the JinaAIReranker class and pass in the number of results you want to return. The Jina AI Reranker API key is set in the JINAAI_API_KEY environment variable.

export JINAAI_API_KEY=<YOUR API KEY>
const nodePostprocessor = new JinaAIReranker({
  topN: 5,
});

Create a query engine with the retriever and node postprocessor​

const queryEngine = index.asQueryEngine({
  retriever,
  nodePostprocessors: [nodePostprocessor],
});

// log the response
const response = await queryEngine.query("Where did the author grown up?");