Opensource OCR API for your app - [AI series]
OCR API - extract text from images
OCR can be used to extract texts from images, photos, and videos as well. Useful information can be found in such formats.
Let's see how simple it is to create an OCR microservice with RYAX,
and extract text from any image !
For that, we'll use Tesseract, the open source library published by Google,.
And ice on the cake, we'll use our chatGPT integration to generate the code
There's no code to write !
But aligned with our low-code philosophy, the code is still customizable, allowing any updates and an easy maintenance.
Read our tutorials on how to boost your application with opensource generative AI
>>> Let's start
First, let's create the action in Ryax, taking a video file in input and extracting the text
Click on "New run"
After few seconds, the workflow is fully executed , creating an action ready-to-use in others Ryax workflows.
By the way, the generated action code is directly available on GitLab, and customizable if needed
Now, let's use this new action just generated in another workflow, to extract texts from an image and generate an API callable for this function.
This new workflow has 2 steps :
- an HTTP POST API JSON step, to get the file to transcript
- the new action created "Extract text from image using opensource library"
Then click on "DEPLOY" to deploy it and make it available as API
It's that simple !
That's it !
The workflow is ready to use, through the UI, with a form, or through an API
If you're using API, we recommand to secure it by creating API key.