Create and Test a Document AI Processor

sudo apt-get update
sudo apt-get install jq -y

sudo apt-get install python3-pip -y

export PROJECT_ID=$(gcloud config get-value core/project)

export SA_NAME="document-ai-service-account"
gcloud iam service-accounts create $SA_NAME --display-name $SA_NAME

gcloud projects add-iam-policy-binding ${PROJECT_ID} \
--member="serviceAccount:$SA_NAME@${PROJECT_ID}.iam.gserviceaccount.com" \
--role="roles/documentai.apiUser"

gcloud iam service-accounts keys create key.json \
--iam-account  $SA_NAME@${PROJECT_ID}.iam.gserviceaccount.com

export GOOGLE_APPLICATION_CREDENTIALS="$PWD/key.json"

gsutil cp gs://cloud-training/gsp924/health-intake-form.pdf .

echo '{"inlineDocument": {"mimeType": "application/pdf","content": "' > temp.json
base64 health-intake-form.pdf >> temp.json
echo '"}}' >> temp.json
cat temp.json | tr -d \\n > request.json


sleep 60

export LOCATION="us"
export PROJECT_ID=$(gcloud config get-value core/project)
curl -X POST \
-H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
https://${LOCATION}-documentai.googleapis.com/v1beta3/projects/${PROJECT_ID}/locations/${LOCATION}/processors/${PROCESSOR_ID}:process > output.json


sleep 60

cat output.json | jq -r ".document.text"


gsutil cp gs://cloud-training/gsp924/synchronous_doc_ai.py .

python3 -m pip install --upgrade google-cloud-documentai google-cloud-storage prettytable

export PROJECT_ID=$(gcloud config get-value core/project)
export GOOGLE_APPLICATION_CREDENTIALS="$PWD/key.json"

python3 synchronous_doc_ai.py \
--project_id=$PROJECT_ID \
--processor_id=$PROCESSOR_ID \
--location=us \
--file_name=health-intake-form.pdf | tee results.txt