A simple web application for a OpenAI-enabled document search. This repo uses Azure OpenAI Service for creating embeddings vectors from documents. For answering the question of a user, it retrieves the most relevant document and then uses GPT-3, GPT-3.5 or GPT-4 to extract the matching answer for the question.
Lightweight orchestration harness built for your AI agents. The unfiltered truth about where your project stands.
Key parameters and specifications
Key parameters and specifications
Parameter
Value
Language
Jupyter Notebook
Category
Applications
Subcategory
Object detection
Keywords
OCR
Stars
844
Forks
249
Contributors
5
Created date
2017-01-14
Updated date
2026-10-11
Stars in 1 day
0
Stars in 7 days
1
Rank
13,266
Previous rank
13,163
Rank change
-103
7-day stars rank
10,568
Previous 7-day stars rank
10,613
7-day stars rank change
45
Total stars rank
12,763
Previous total stars rank
12,748
Total stars rank change
-15
README summary
Handwriting OCR The project tries to create software for recognition of a handwritten text from photos (also for Czech language). It uses computer vision and machine learning. And it experiments with different approaches to the problem. It started as a school project which I got a chance to present on Intel ISEF 2018. Program Structure Proces of recognition is divided into 4 steps. The initial input is a photo of page with text. Detection of page and removal of background
2. Separation and recognition of characters (recognition of words) Main files combining all the steps are OCR. Naming of files goes by step representing - name of machine learning model. Clone the repository After downloading the repo, you have to download the datasets and models (for more info look into data and models folders). Requirements The project is created using Python 3. If you have it, you can run the installation as: Main libraries (all required libraries are in environment. 1
) Run With all required libraries installed and cloned repo, run in the directory of the project. Then you can work on the particular notebook. Contributing Best way how to get involved is through creating GitHub issues or solving one! If there aren't any issues you can contact me directly on email. License **MIT** Support the project If this project helped you or you want to support quick answers to questions and issues. Or you just think it is an interesting
project.
Frequently asked questions
How many stars and forks are recorded?
Breta01/handwriting-ocr has 844 stars and 249 forks.
What is the repository rank?
Breta01/handwriting-ocr is ranked 13,266.
What language and category are recorded?
Breta01/handwriting-ocr has 844 stars, uses Jupyter Notebook and belongs to Applications.
Which repository is closest in rank?
Breta01/handwriting-ocr is compared with BryceWG/BiBi-Keyboard, ranked 13,267 with 844 stars.
README
Handwriting OCR
The project tries to create software for recognition of a handwritten text from photos (also for Czech language). It uses computer vision and machine learning. And it experiments with different approaches to the problem. It started as a school project which I got a chance to present on Intel ISEF 2018.
Program Structure
Proces of recognition is divided into 4 steps. The initial input is a photo of page with text.
Detection of page and removal of background
Detection and separation of words
Normalization of words
Separation and recognition of characters (recognition of words)
Main files combining all the steps are OCR.ipynb or OCR-Evaluator.ipynb. Naming of files goes by step representing - name of machine learning model.
Main libraries (all required libraries are in environment.yml):
Numpy (1.13)
Tensorflow (1.4)
OpenCV (3.1)
Pandas (0.21)
Matplotlib (2.1)
Run
With all required libraries installed and cloned repo, run jupyter notebook in the directory of the project. Then you can work on the particular notebook.
Contributing
Best way how to get involved is through creating GitHub issues or solving one! If there aren't any issues you can contact me directly on email.
License
MIT
Support the project
If this project helped you or you want to support quick answers to questions and issues. Or you just think it is an interesting project. Please consider a small donation.
