Redshift

The RedshiftTools toolkit enables an Agent to interact with Amazon Redshift data warehouses.

RedshiftTools enable an Agent to interact with Amazon Redshift data warehouses.

Prerequisites

The following example requires the redshift_connector library.

1uv pip install -U redshift-connector

You will also need an Amazon Redshift cluster or Redshift Serverless endpoint. For IAM authentication, ensure your AWS credentials are configured.

Example

The following agent will list all tables in the database.

1from kern.agent import Agent
2from kern.tools.redshift import RedshiftTools
3
4# Initialize RedshiftTools with connection details
5redshift_tools = RedshiftTools(
6    host="your-cluster.abc123.us-east-1.redshift.amazonaws.com",
7    database="dev",
8    user="your-username",
9    password="your-password",
10    table_schema="public",
11)
12
13# Create an agent with the RedshiftTools
14agent = Agent(tools=[redshift_tools])
15
16# Example: Ask the agent to list tables
17agent.print_response(
18    "List the tables in the database and describe the sales table"
19)

Toolkit Params

Parameter	Type	Default	Description
`host`	`Optional[str]`	`None`	Redshift cluster endpoint. Uses `REDSHIFT_HOST`.
`port`	`int`	`5439`	Port for the database connection.
`database`	`Optional[str]`	`None`	Database name. Uses `REDSHIFT_DATABASE`.
`user`	`Optional[str]`	`None`	Username for standard authentication.
`password`	`Optional[str]`	`None`	Password for standard authentication.
`iam`	`bool`	`False`	Enable IAM authentication.
`cluster_identifier`	`Optional[str]`	`None`	Cluster identifier for IAM auth. Uses `REDSHIFT_CLUSTER_IDENTIFIER`.
`region`	`Optional[str]`	`None`	AWS region for IAM auth. Uses `AWS_REGION`.
`db_user`	`Optional[str]`	`None`	Database user for IAM auth. Uses `REDSHIFT_DB_USER`.
`access_key_id`	`Optional[str]`	`None`	AWS access key for IAM auth. Uses `AWS_ACCESS_KEY_ID`.
`secret_access_key`	`Optional[str]`	`None`	AWS secret key for IAM auth. Uses `AWS_SECRET_ACCESS_KEY`.
`session_token`	`Optional[str]`	`None`	AWS session token for IAM auth. Uses `AWS_SESSION_TOKEN`.
`profile`	`Optional[str]`	`None`	AWS profile for IAM auth. Uses `AWS_PROFILE`.
`ssl`	`bool`	`True`	Enable SSL for the connection.
`table_schema`	`str`	`public`	Schema name to search for tables.

Toolkit Functions

Function	Description
`show_tables`	Retrieves and displays a list of tables in the configured schema. Returns the list of tables.
`describe_table`	Describes the structure of a specified table by returning its columns, data types, and nullability. Parameters include `table` (str) to specify the table name. Returns the table description.
`summarize_table`	Summarizes a table by computing aggregates such as min, max, average, standard deviation, and non-null counts for numeric columns, or unique values and average length for text columns. Parameters include `table` (str) to specify the table name. Returns the summary of the table.
`inspect_query`	Inspects an SQL query by returning the query plan using EXPLAIN. Parameters include `query` (str) to specify the SQL query. Returns the query plan.
`run_query`	Executes a read-only SQL query and returns the result. Parameters include `query` (str) to specify the SQL query. Returns the result of the query execution.
`export_table_to_path`	Exports a specified table in CSV format to a given path. Parameters include `table` (str) to specify the table name and `path` (str) to specify where to save the file. Returns the result of the export operation.

You can use include_tools or exclude_tools to modify the list of tools the agent has access to. Learn more about selecting tools.

Developer Resources

View Example