Add new features to a ComputerVision/OCR WebApp that get data from Resumes/CVs

Job ID: 34165088

Budget: $250 – $750 USD

Hello everybody,
First of all, I hope you are well and safe.
About 1-2 year ago we hired an Agency to develop a software that will be capable (through a wizard import) of extracting text from pdf,docx/images files and saving the output in a database.
Basically the software get data from CV/resumes(European Format, Indeed Format, LinkedIN format) using OCR and ComputerVision.
To achieve that, the agency performed a Model Training on 7k resumes using Google Colab.
The main technologies used are:
Node.js
MongoDB
Docker
React
Python
Tesseract OCR
OpenCV
So why we want to work with another agency?
We need to move next level, we need more professional agency to work together. We need to work side-by-side using GANTT schema, following certain deadlines.
We need your help to mantain this software and to add other more features.
Now the main question is:
What does the old agency have to give us so that you can do the job well? We're about to break off so please be specific about the things we need to work on.
Do we need source code? Can we use the main code on our server or its only a compiled version?
Do we need GoogleColab account to continue model training and for not waste all job done?
Please read full brief before post a bid.
Please note this is a Long term job.
Who wants to help us?
Thanks for your kindly attention
Related categories: Machine Learning (ML) OCR Node.js React.js OpenCV