v4.0.0

---

Features

This version of the Typescript client introduces two new endpoints: Rerank and Import.

Rerank

Rerank provides users the ability to rerank documents in descending relevance-order against a given query. Reranking documents is a common "second-pass" ranking strategy broadly used in retrieval applications.

Example code:

import { Pinecone } from '@pinecone-database/pinecone';
const pc = new Pinecone();
const rerankingModel = 'bge-reranker-v2-m3';
const myQuery = 'What are some good Turkey dishes for Thanksgiving?';

// Option 1: Documents as an array of strings
const myDocsStrings = [
  'I love turkey sandwiches with pastrami',
  'A lemon brined Turkey with apple sausage stuffing is a classic Thanksgiving main',
  'My favorite Thanksgiving dish is pumpkin pie',
  'Turkey is a great source of protein',
];

// Option 1 response
const response = await pc.inference.rerank(
  rerankingModel,
  myQuery,
  myDocsStrings
);
console.log(response);
// {
// model: 'bge-reranker-v2-m3',
// data: [
//   { index: 1, score: 0.5633179, document: [Object] },
//   { index: 2, score: 0.02013874, document: [Object] },
//   { index: 3, score: 0.00035419367, document: [Object] },
//   { index: 0, score: 0.00021485926, document: [Object] }
// ],
// usage: { rerankUnits: 1 }
// }

// Option 2: Documents as an array of objects
const myDocsObjs = [
  {
    title: 'Turkey Sandwiches',
    body: 'I love turkey sandwiches with pastrami',
  },
  {
    title: 'Lemon Turkey',
    body: 'A lemon brined Turkey with apple sausage stuffing is a classic Thanksgiving main',
  },
  {
    title: 'Thanksgiving',
    body: 'My favorite Thanksgiving dish is pumpkin pie',
  },
  {
    title: 'Protein Sources',
    body: 'Turkey is a great source of protein',
  },
];

// Option 2: Options object declaring which custom key to rerank on
// Note: If no custom key is passed via `rankFields`, each doc must contain a `text` key, and that will act as the default)
const rerankOptions = {
  topN: 3,
  returnDocuments: false,
  rankFields: ['body'],
  parameters: {
    inputType: 'passage',
    truncate: 'END',
  },
};

// Option 2 response
const response = await pc.inference.rerank(
  rerankingModel,
  myQuery,
  myDocsObjs,
  rerankOptions
);
console.log(response);
// {
// model: 'bge-reranker-v2-m3',
// data: [
//   { index: 1, score: 0.5633179, document: undefined },
//   { index: 2, score: 0.02013874, document: undefined },
//   { index: 3, score: 0.00035419367, document: undefined },
// ],
// usage: { rerankUnits: 1 }
//}

Import

Import is a long-running, asynchronous operation that gives users the ability to import vectors directly from object storage (e.g. S3) into a Pinecone index. It is intended to be used with large-scale jobs. For small-scale jobs (e.g. <1000 vectors), we recommend continuing to use upsert.

Example code:

import { Pinecone } from '@pinecone-database/pinecone';

const pc = new Pinecone();
const indexName = 'sample-index';

await pc.createIndex({
  name: indexName,
  dimension: 10,
  spec: {
    serverless: {
      cloud: 'aws',
      region: 'eu-west-1',
    },
  },
});

const index = pc.Index(indexName);

const storageURI = 's3://my-bucket/my-directory/';

await index.startImport(storageURI, 'continue'); // "Continue" will avoid aborting the operation if errors are encountered.

// {
//   "id": "import-id"
// }

---

Housekeeping

• Added a section to the README outlining how to use the Typescript client with a proxy server
• Re-architected test suite to be more efficient (primarily: centralization and sharing of test indexes)

---

Full Changelog: 3.0.3...v4.0.0