Getting Started - Snow Leopard

This documentation is specific to the Snow Leopard Cloud. With Snow Leopard Cloud, you can build AI Agents that use accurate data directly from multiple sytems of record, without needing any initial MCP setup or tuning. Get started for free! Sign up, create an instance, connect your data, and start querying! Snow Leopard automatically creates a semantic understanding of the connected data sources for very high accuracy out of the box, so you don’t need to spend time defining ontology and business rules, creating evals or context engineering. You can also give feedback to Snow Leopard, in plain natural language, help it better understand your internal business logic and internal business metrics and definitions, for highest data retrieval accuracy! Feedback can be given at any time for any connected data source.

If you want to deploy Snow Leopard on-prem or within your enterprise VPC, contact us! You can also check out our Enterprise documentation.

To get started with Snow Leopard Cloud you need to:

Sign up at cloud.snowleopard.ai
Create an instance
Add your data sources and authorize Snow Leopard to connect to them
Use our SDKs or the API directly

See details below. Visit cloud.snowleopard.ai to create your account.

Creating an Instance

An instance is an isolated environment that holds your data source connections and API keys. An AI agent can talk to a given instance via the instance’s API key, and can ask for data from any of the data sources connected to that instance. From the Instances page, click Create Instance. Once created, click through to the new instance to see its data source configuration and settings.

Adding a Data Source

You can add one or more data sources (with one or more schemas) to your instance. Snow Leopard has a built-in planner and router for real-time federation. At query time, it will automatically route the query (or sub-queries as necessary) to the right data source(s) to generate the correct response. As soon as you connect a data source (eg: a database), Snow Leopard’s Automatic Semantic Engine generates a semantic understanding of that data source automatically, within minutes. This semantic understanding is called annotations in Snow Leopard. Once annotations are ready, you or your agent can immediately start querying data from that data source, in addition to any other data sources already connected to that instance. You can fine-tune the annotations by providing feedback in plain text (eg: business definitions, metrics, business logic) to Snow Leopard. See the Feedback section for more details. From the instance page, click Add Data Source and follow the prompts:

Enter a name for the data source.
Select the type of data source.

Currently supported:

Google BigQuery

Enter your Google Cloud Project ID.
Authorize Snow Leopard using OAuth.

Snow Leopard will configure the data source to read from all datasets accessible to the OAuth user that have at least one table in the given Project ID.

MySQL

Enter the host, database name, and username/password credentials for your database.

Snow Leopard will configure the data source to read from all databases accessible with the given credentials that have at least one table in the database.

PostgreSQL

Enter the host, database name, and username/password credentials for your database.

Snow Leopard will configure the data source to read from all schemas accessible with the given credentials that have at least one table or view in the database.

Neon

Enter the host, database name, and username/password credentials for your database.
Use direct connections to your Neon database.

Snow Leopard will configure the data source to read from all schemas accessible with the given credentials that have at least one table or view in the database.

Supabase

Enter the host, database name, and username/password credentials for your database.
Use Supabase’s Shared Pooler (Supavisor) to connect your database to Snow Leopard

Snow Leopard will configure the data source to read from all schemas accessible with the given credentials that have at least one table or view in the database.

COMING SOON: Salesforce, Snowflake, Microsoft SQLServer, DuckDB. Don’t see a data source you want to use? Contact us!

API Keys

API keys are created per instance. You or your agent needs an API key to query data from any/all data sources connected to that instance.

From the instance page, click the Keys tab.
Click Create Key.
Enter a name for the key.
Click Create.

The key is displayed only once. Copy and save it at creation time if you want it for later use.

Authentication

All API endpoints are authenticated using API keys, also known as Bearer Tokens. Pass your key as a Bearer token in the Authorization header of every request:

Authorization: Bearer {api_key}

API keys are scoped to a specific instance. See API Keys above for how to create them.

Connection Info

From the instance page, click the Connection Info tab to find the instance’s base URL. It will look like:

https://api.snowleopard.ai/v1/instances/<instance_id>

You will need both the instance_id (visible in this URL) and your API key to make requests.

Using the API

There are currently multiple ways of interacting with the Snow Leopard API:

Python SDK (pypi)
TypeScript SDK (npm)
REST endpoints

from snowleopard import SnowLeopardClient

client = SnowLeopardClient(api_key="{api_key}")
response = client.retrieve(
    instance_id="{instance_id}",
    user_query="How many users signed up last month?"
)
print(response.data)

from snowleopard import AsyncSnowLeopardClient

async def main():
    client = AsyncSnowLeopardClient(api_key="{api_key}")
    response = await client.retrieve(
        instance_id="{instance_id}",
        user_query="How many users signed up last month?"
    )
    print(response.data)

import { SnowLeopardClient } from '@snowleopard-ai/client';

const client = new SnowLeopardClient({
    apiKey: 'your-api-key'
});

const response = await client.retrieve({
    instanceId: 'your-instance-id',
    userQuery: 'How many users signed up last month?'
});

console.log(response.data);
await client.close();

curl --request POST \
  --url https://api.snowleopard.ai/v1/instances/{instance_id}/retrieve \
  --header 'Authorization: Bearer {api_key}' \
  --header 'Content-Type: application/json' \
  --data '{"userQuery": "How many users signed up last month?"}'

​Sign Up

​Creating an Instance

​Adding a Data Source

​API Keys

​Authentication

​Connection Info

​Using the API

Sign Up

Creating an Instance

Adding a Data Source

API Keys

Authentication

Connection Info

Using the API