Epsilla Cloud

Get your cloud hosted Epsilla vector database up and running within 1 minute.

1. Sign up Epsilla Cloud

Create an Epsilla Cloud account at https://cloud.epsilla.com/, then sign in.

2. Get your project API Key

Navigate to the 'Configurations' tab within the project, create a new API Key, and keep it at a secure place.

3. Create a vector database, then create a table

Navigate to the 'Resource' tab, and click 'Create Vector Database'.

Give the database a name, and click 'Create'. It takes a few seconds to spin up a vector database.

Within the newly created database, create a new table. Give the table a name. Adjust the table schema according to your business logic, then click 'Create'.

4. Use GUI to CRUD data to the table.

Epsilla automatically generates sample queries for the table. Start with inserting some sample data:

Then query the table with top K semantic similarity search.

Switch between Shell, Python, and JavaScript tags, and click the 'Copy' button to copy the curl command, Python code snippet, and JavaScript code snippet of the query.

Copying the code snippet is the easiest way to integrate with your application as it already has the project_id and db_id prefilled.

Remember to replace "YOUR-API-KEY" part with the API Key you get earlier.

5. Connect to Epsilla

First, install Epsilla Python/JavaScript client.

Python

pip3 install --upgrade pyepsilla

JavaScript

Then connect to the created database.

Python

from pyepsilla import cloud
client = cloud.Client(
  project_id="PROJECT-ID",     # Copied from the GUI code snippet
  api_key="YOUR-API-KEY"       # Replace with your API Key
)
db = client.vectordb(db_id="DB-ID") # Copied from the GUI code snippet

JavaScript

6. Insert new records

You can insert multiple records in a batch.

Python

status_code, response = db.insert(table_name="MyTable", 
  records=[
    {"ID": 1, "Doc": "Berlin", "Embedding": [0.05, 0.61, 0.76, 0.74]},
    {"ID": 2, "Doc": "London", "Embedding": [0.19, 0.81, 0.75, 0.11]},
    {"ID": 3, "Doc": "Moscow", "Embedding": [0.36, 0.55, 0.47, 0.94]},
    {"ID": 4, "Doc": "San Francisco", "Embedding": [0.18, 0.01, 0.85, 0.80]},
    {"ID": 5, "Doc": "Shanghai", "Embedding": [0.24, 0.18, 0.22, 0.44]}
  ]
)

JavaScript

cURL

6. Search

Python

status_code, response = db.query(
  table_name="MyTable",
  query_field="Embedding",
  query_vector=[0.35, 0.55, 0.47, 0.94],
  limit=2
)

JavaScript

cURL

7. Delete a table and delete a database

Use the GUI to delete a table and delete a database.