Bulk

edit

With the bulk API, you can perform multiple index/delete operations in a single API call. The bulk API significantly increases indexing speed.

You can also use the bulk helper.

'use strict'

require('array.prototype.flatmap').shim()
const { Client } = require('@elastic/elasticsearch')
const client = new Client({
  cloud: { id: '<cloud-id>' },
  auth: { apiKey: 'base64EncodedKey' }
})

async function run () {
  await client.indices.create({
    index: 'tweets',
    operations: {
      mappings: {
        properties: {
          id: { type: 'integer' },
          text: { type: 'text' },
          user: { type: 'keyword' },
          time: { type: 'date' }
        }
      }
    }
  }, { ignore: [400] })

  const dataset = [{
    id: 1,
    text: 'If I fall, don\'t bring me back.',
    user: 'jon',
    time: new Date()
  }, {
    id: 2,
    text: 'Winter is coming',
    user: 'ned',
    time: new Date()
  }, {
    id: 3,
    text: 'A Lannister always pays his debts.',
    user: 'tyrion',
    time: new Date()
  }, {
    id: 4,
    text: 'I am the blood of the dragon.',
    user: 'daenerys',
    time: new Date()
  }, {
    id: 5, // change this value to a string to see the bulk response with errors
    text: 'A girl is Arya Stark of Winterfell. And I\'m going home.',
    user: 'arya',
    time: new Date()
  }]

  const operations = dataset.flatMap(doc => [{ index: { _index: 'tweets' } }, doc])

  const bulkResponse = await client.bulk({ refresh: true, operations })

  if (bulkResponse.errors) {
    const erroredDocuments = []
    // The items array has the same order of the dataset we just indexed.
    // The presence of the `error` key indicates that the operation
    // that we did for the document has failed.
    bulkResponse.items.forEach((action, i) => {
      const operation = Object.keys(action)[0]
      if (action[operation].error) {
        erroredDocuments.push({
          // If the status is 429 it means that you can retry the document,
          // otherwise it's very likely a mapping error, and you should
          // fix the document before to try it again.
          status: action[operation].status,
          error: action[operation].error,
          operation: operations[i * 2],
          document: operations[i * 2 + 1]
        })
      }
    })
    console.log(erroredDocuments)
  }

  const count = await client.count({ index: 'tweets' })
  console.log(count)
}

run().catch(console.log)