LangGraph - Snow Leopard

This guide shows you how to add Snow Leopard data retrieval to a LangGraph workflow.

Prerequisites

Python 3.10+
OpenAI API key (or another supported model provider)
Snow Leopard Cloud API key
A Snow Leopard Cloud instance with at least one data source connected
Your instance ID, from the instance’s Connection Info tab

Don’t have data? Load the sample Northwind dataset into a PostgreSQL database that Snow Leopard Cloud can reach, such as a hosted Neon or Supabase database. Run the dataset’s northwind.sql script against your database, then add the database as a data source in your instance.

Start from scratch

Clone and run the complete working example:

git clone https://github.com/SnowLeopard-AI/snowy-examples.git
cd snowy-examples/quickstart/langgraph

Install dependencies:

pip install langgraph langchain langchain-openai snowleopard python-dotenv

Set your environment variables:

export OPENAI_API_KEY=your-openai-key
export SNOWLEOPARD_API_KEY=your-snowleopard-key
export SNOWLEOPARD_INSTANCE_ID=your-instance-id

Run the example:

python langgraph_quickstart.py

Bring your own agent

Already have a LangGraph workflow? Add Snow Leopard data retrieval with these steps.

1. Install dependencies

pip install snowleopard

2. Add Snow Leopard fields to your state

Add fields to your graph state to store query results:

from typing_extensions import TypedDict

class GraphState(TypedDict):
    user_question: str
    query_result: str  # Add this field for Snow Leopard results
    # ... your other state fields

3. Create a Snow Leopard query node

Create a node that calls Snow Leopard to retrieve data:

from snowleopard import SnowLeopardClient

client = SnowLeopardClient(api_key="{your-snowleopard-api-key}")

def query_database(state: GraphState) -> GraphState:
    """Query the database using Snow Leopard."""
    response = client.retrieve(
        instance_id="{your-instance-id}",
        user_query=state["user_question"]
    )
    state["query_result"] = str(response)
    return state

4. Add the node to your workflow

Add the query node and connect it to your existing workflow:

from langgraph.graph import StateGraph

workflow = StateGraph(GraphState)

# Add the Snow Leopard query node
workflow.add_node("query", query_database)

# Connect it to your workflow
workflow.set_entry_point("query")
workflow.add_edge("query", "your_next_node")

Next steps

View the full example on GitHub
See our full API documentation to learn about the Retrieve and Response endpoints
Improve accuracy by giving Snow Leopard feedback about your business logic and terminology
See this quickstart in action with the Financial Coach recipe

​Prerequisites

​Start from scratch

​Bring your own agent

​1. Install dependencies

​2. Add Snow Leopard fields to your state

​3. Create a Snow Leopard query node

​4. Add the node to your workflow

​Next steps

Prerequisites

Start from scratch

Bring your own agent

1. Install dependencies

2. Add Snow Leopard fields to your state

3. Create a Snow Leopard query node

4. Add the node to your workflow

Next steps