SnowflakeTableRetriever

Connect to a Snowflake database and execute SQL queries using ADBC and Polars. It returns the results as a Pandas DataFrame and optionally as a Markdown-formatted string.

For more information, see Polars documentation and ADBC documentation.

Key Features

• Executes SQL queries against a Snowflake database using ADBC and Polars.
• Returns query results as a Pandas DataFrame and as a Markdown-formatted table.
• Configurable login timeout.
• Supports passing the SQL query at runtime for dynamic data retrieval.

Configuration

1. Drag the SnowflakeTableRetriever component onto the canvas from the Component Library.
2. Click on the component to open the configuration panel.
3. On the General tab:
   • Set your Snowflake user, account, and api_key (password). Store the password as a secret called SNOWFLAKE_API_KEY. For instructions, see Add Secrets.
   • Set the database, db_schema, and warehouse for your Snowflake connection.
4. Go to the Advanced tab to configure login_timeout and return_markdown.

Connections

SnowflakeTableRetriever receives SQL queries at runtime. It outputs the query results as a dataframe (Pandas DataFrame) and optionally as a table (Markdown string). Connect it to components that process or format the query results.

Source Code

To check this component's source code, open snowflake_table_retriever.py in the Haystack Core Integrations repository.

Usage Examples

Basic Configuration

  SnowflakeTableRetriever:
    type: 
      snowflake.src.haystack_integrations.components.retrievers.snowflake.snowflake_table_retriever.SnowflakeTableRetriever
    init_parameters: {}

components:
  SnowflakeTableRetriever:
    type: snowflake.src.haystack_integrations.components.retrievers.snowflake.snowflake_table_retriever.SnowflakeTableRetriever
    init_parameters:

Parameters

Inputs

Parameter	Type	Description
query	str	The SQL query to execute.
return_markdown	Optional[bool]	Whether to return a Markdown-formatted string of the DataFrame. If not provided, uses the value set during initialization.

Outputs

Parameter	Type	Description
dataframe	DataFrame	A Pandas DataFrame with the query results.
table	str	A Markdown-formatted string representation of the DataFrame.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
user	str		User's login.
account	str		Snowflake account identifier.
api_key	Secret	Secret.from_env_var('SNOWFLAKE_API_KEY')	Snowflake account password.
database	Optional[str]	None	Name of the database to use.
db_schema	Optional[str]	None	Name of the schema to use.
warehouse	Optional[str]	None	Name of the warehouse to use.
login_timeout	Optional[int]	60	Timeout in seconds for login.
return_markdown	bool	True	Whether to return a Markdown-formatted string of the DataFrame.

Run Method Parameters

These are the parameters you can configure for the component's run() method. This means you can pass these parameters at query time through the API, in Playground, or when running a job. For details, see Modify Pipeline Parameters at Query Time.

Parameter	Type	Default	Description
query	str		The SQL query to execute.
return_markdown	Optional[bool]	None	Whether to return a Markdown-formatted string of the DataFrame. If not provided, uses the value set during initialization.

Related Information

• Add Secrets