Getting Started#

Step 1: Install EVA#

EVA supports Python (versions >= 3.8). To install EVA, we recommend using the pip package manager:

pip install evadb

Launch EVA server#

EVA is based on a client-server architecture. To launch the EVA server using the pip package, run the following command on the terminal:

eva_server &

Step 2: Start a Jupyter Notebook Client#

Here is an illustrative Jupyter notebook focusing on MNIST image classification using EVA. The notebook works on Google Colab.

Connect to the EVA server#

Connect to the EVA server in the notebook using the following code:

# allow nested asyncio calls for client to connect with server
import nest_asyncio
from eva.server.db_api import connect

# hostname and port of the server where EVA is running
connection = connect(host = '', port = 8803)

# cursor allows the notebook client to send queries to the server
cursor = connection.cursor()

Load video for analysis#

Download the MNIST video for analysis.

!wget -nc

Use the LOAD statement to load a video onto a table in EVA server.

cursor.execute('LOAD VIDEO "mnist.mp4" INTO MNISTVideoTable;')
response = cursor.fetch_all()

Step 3: Run an AI Query on the loaded video#

User-defined functions (UDFs) allow us to combine SQL with AI models. These functions wrap around AI models. In this query, we use the MnistImageClassifier UDF that wraps around a model trained for classifying MNIST images.

cursor.execute("""SELECT data, MnistImageClassifier(data).label
                  FROM MNISTVideoTable
                  WHERE id = 30;""")
response = cursor.fetch_all()

Visualize the output#

The output of the query is visualized in the notebook.