DocArray is a type agnostic Python library for effortless processing and manipulation of data by Jina AI. It can also be thought of as a single data structure for all kinds of data.
- Python is all you need to know
- One-stop solution for all your data processing needs
- Scalable data structure for all your ML needs
- Portable and easy to integrate in production
A simple nocode interface to build a search prototype on your own data in just three simple steps.
- Plug in the data
- Generate Embeddings with a click of a button
- Use out-of-the-box search functionality to check the results
🍴 Clone the docarray-nocode repository using the following command
git clone https://github.com/Shubhamsaboo/docarray-nocode.gitYou need to have Python 3.7+ installed, and then you can create a python virtual environment using pip or conda depending on your python setup.
After installing and activating the virtual environment (The commands will differ for windows and Linux installations which is clearly specified in the respective documentation), you can run the following command to install the required dependencies:
pip install -r requirements.txtAfter installing the required dependencies, you can bring up the main application to validate that it's working in your local environment. To bring up the application, you can run the following command:
streamlit run app.py🏁 Note - For now, it only supports text data. Moving forward, I will be adding support to other data types as well!