Azure AI Document Intelligence vs. Google App Engine

Azure AI Document Intelligence is mainly used in document data filling. If the template is the same, only the inside data content will be different. There, we use a text-based OCR process to fill the data in the same template with different, accurate data means the manual work will be reduced and time saved. And used in an image and text combined bot if the user query through text from the knowledge based document it brings the output which is used in information technology and services.

Incentivized

App Engine is such a good resource for our team both internally and externally. You have complete control over your app, how it runs, when it runs, and more while Google handles the back-end, scaling, orchestration, and so on. If you are serving a tool, system, or web page, it's perfect. If you are serving something back-end, like an automation or ETL workflow, you should be a little considerate or careful with how you are structuring that job. For instance, the Standard environment in Google App Engine will present you with a resource limit for your server calls. If your operations are known to take longer than, say, 10 minutes or so, you may be better off moving to the Flexible environment (which may be a little more expensive but certainly a little more powerful and a little less limited) or even moving that workflow to something like Google Compute Engine or another managed service.

Incentivized

• From the Image the OCR technology use to store embedding properly
• From the images the OCR technology automatically capturing text is brilliant
• Also for creating Azure AI Document Intelligence endpoint and keys it is very easy to do

Incentivized

• Quick to develop, quick to deploy. You can be up and running on Google App Engine in no time.
• Flexible. We use Java for some services and Node.js for others.
• Great security features. We have been consistently impressed with the security and authentication features of Google App Engine.

Incentivized

• Azure AI Document Intelligence should have used to store image based embedding for multiple languages
• Images storing part is a different area in our case and only for a few images that part can be increased
• Cost is high which should be reduced so more users will come and more technology through this will come

Incentivized

• There is a slight learning curve to getting used to code on Google App Engine.
• Google Cloud Datastore is Google's NoSQL database in the cloud that your applications can use. NoSQL databases, by design, cannot give handle complex queries on the data. This means that sometimes you need to think carefully about your data structures - so that you can get the results you need in your code.
• Setting up billing is a little annoying. It does not seem to save billing information to your account so you can re-use the same information across different Cloud projects. Each project requires you to re-enter all your billing information (if required)

Incentivized

App Engine is a solid choice for deployments to Google Cloud Platform that do not want to move entirely to a Kubernetes-based container architecture using a different Google product. For rapid prototyping of new applications and fairly straightforward web application deployments, we'll continue to leverage the capabilities that App Engine affords us.

Incentivized

Azure AI Document Intelligence mainly meets our business requirements. Actually, what we need is image and text-based multimodal, and we store data in pgvector PostgreSQL vector embedding those data. For that, we need text and image combined embedding, which we can get from Azure AI Document Intelligence. Which is working good for us and improved accuracy not 100% but 70% accuracy we are getting at least through Azure AI Document Intelligence.

Incentivized

Google App Engine is very intuitive. It has the common programming language most would use. Google is a dependable name and I have not had issues with their servers being down....ever. You can safely use their service and store your data on their servers without worrying about downtime or loss of data.

Incentivized

Good amount of documentation available for Google App Engine and in general there is large developer community around Google App Engine and other products it interacts with. Lastly, Google support is great in general. No issues so far with them.

Incentivized

Azure AI Search, we used to bring image and text relevant to the user query, but it did not work properly, and the accuracy was very poor compared to Azure AI Document Intelligence. Azure Blob Storage we used to store images and bring in frontend there also accuracy low, so we went for embedding through Azure AI Document Intelligence. Azure AI Content Safety for text content, but it is very costly, so we went for Azure AI Document Intelligence.

Incentivized

We were on another much smaller cloud provider and decided to make the switch for several reasons - stability, breadth of services, and security. In reviewing options, GCP provided the best mixtures of meeting our needs while also balancing the overall cost of the service as compared to the other major players in Azure and AWS.

Incentivized

• Significant reduction in manual processing cost by 40-60%
• Improved data accuracy and reduce work
• Scalability is good without cost increase

Incentivized

• Effective employee adoption through ease of use.
• Effective integration to other java based frameworks.
• Time to market is very quick. Build, test, deploy and use.
• The GAE Whitelist for java is an important resource to know what works and what does not. So use it. It would also be nice for Google to expand on items that are allowed on GAE platform.

Incentivized