Google Vision API Document Text multiple images in base64 String

Question

I use the Google Vision API OCR (Document Text Detection) to get the text from a scanned document (base64 String). It works perfekt for one image. But how can I send more than one image, e.g. the second page of a document.

I´ve tried to merge the base64 strings but it do not work.

var base64ImagesArrayConcarved = base64ImagesArray.join('')

Answer 1

Cloud Vision API has the method files.asyncBatchAnnotate. which enables sending a bunch of files in the same request. To add individual files use async file annotation requests. An example of including two images in a batch request is the following:

{
  "requests":[
    {
      "inputConfig": {
        "gcsSource": {
          "uri": "gs://<your bucket name>/image1.jpg"
        },
        "mimeType": "image/jpg"
      },
      "features": [
        {
          "type": "DOCUMENT_TEXT_DETECTION"
        }
      ],
      "outputConfig": {
        "gcsDestination": {
          "uri": "gs://<your bucket name>/output/"
        }
      }
    },
    {
      "inputConfig": {
        "gcsSource": {
          "uri": "gs://<your bucket name>/image2.jpg"
        },
        "mimeType": "image/jpg"
      },
      "features": [
        {
          "type": "DOCUMENT_TEXT_DETECTION"
        }
      ],
      "outputConfig": {
        "gcsDestination": {
          "uri": "gs://<your bucket name>/output/"
        }
      }
    }
  ]
}

If you specifically are working with pdf files, I found this post that explains how to send a request using also asyncBatchAnnotate.