Feat/adapters/redshift

.github/workflows/ci.yml

@@ -0,0 +1,32 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  test-and-lint:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.12'
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r requirements.txt
+          pip install ruff pytest pytest-asyncio
+
+      - name: Run Lint
+        run: ruff src tests
+
+      - name: Run Tests
+        run: pytest -v

2.0.0

@@ -0,0 +1,64 @@
+Collecting redshift-connector
+  Obtaining dependency information for redshift-connector from https://files.pythonhosted.org/packages/e5/a6/f7100d4be4cc13536bb7e8e1edadfef324bf0e0c9fe0ceb128ad35558358/redshift_connector-2.1.10-py3-none-any.whl.metadata
+  Downloading redshift_connector-2.1.10-py3-none-any.whl.metadata (69 kB)
+     -------------------------------------- 69.7/69.7 kB 475.6 kB/s eta 0:00:00
+Collecting scramp<1.5.0,>=1.2.0 (from redshift-connector)
+  Obtaining dependency information for scramp<1.5.0,>=1.2.0 from https://files.pythonhosted.org/packages/69/bf/54b5d40bea1c1805175ead2d496c267f05eec87561687dd73ab76869d8d9/scramp-1.4.6-py3-none-any.whl.metadata
+  Downloading scramp-1.4.6-py3-none-any.whl.metadata (19 kB)
+Requirement already satisfied: pytz>=2020.1 in c:\users\ram caddysy\desktop\intugle1\data-tools\.venv\lib\site-packages (from redshift-connector) (2025.2)
+Collecting beautifulsoup4<5.0.0,>=4.7.0 (from redshift-connector)
+  Obtaining dependency information for beautifulsoup4<5.0.0,>=4.7.0 from https://files.pythonhosted.org/packages/94/fe/3aed5d0be4d404d12d36ab97e2f1791424d9ca39c2f754a6285d59a3b01d/beautifulsoup4-4.14.2-py3-none-any.whl.metadata
+  Downloading beautifulsoup4-4.14.2-py3-none-any.whl.metadata (3.8 kB)
+Collecting boto3<2.0.0,>=1.9.201 (from redshift-connector)
+  Obtaining dependency information for boto3<2.0.0,>=1.9.201 from https://files.pythonhosted.org/packages/3c/56/f47a80254ed4991cce9a2f6d8ae8aafbc8df1c3270e966b2927289e5a12f/boto3-1.41.5-py3-none-any.whl.metadata
+  Downloading boto3-1.41.5-py3-none-any.whl.metadata (6.8 kB)
+Requirement already satisfied: requests<3.0.0,>=2.23.0 in c:\users\ram caddysy\desktop\intugle1\data-tools\.venv\lib\site-packages (from redshift-connector) (2.32.5)
+Collecting lxml<6.0.0,>=4.6.5 (from redshift-connector)
+  Obtaining dependency information for lxml<6.0.0,>=4.6.5 from https://files.pythonhosted.org/packages/91/1e/05ddcb57ad2f3069101611bd5f5084157d90861a2ef460bf42f45cced944/lxml-5.4.0-cp312-cp312-win_amd64.whl.metadata
+  Downloading lxml-5.4.0-cp312-cp312-win_amd64.whl.metadata (3.6 kB)
+Collecting botocore<2.0.0,>=1.12.201 (from redshift-connector)
+  Obtaining dependency information for botocore<2.0.0,>=1.12.201 from https://files.pythonhosted.org/packages/4e/4e/21cd0b8f365449f1576f93de1ec8718ed18a7a3bc086dfbdeb79437bba7a/botocore-1.41.5-py3-none-any.whl.metadata
+  Downloading botocore-1.41.5-py3-none-any.whl.metadata (5.9 kB)
+Requirement already satisfied: packaging in c:\users\ram caddysy\desktop\intugle1\data-tools\.venv\lib\site-packages (from redshift-connector) (25.0)
+Collecting setuptools (from redshift-connector)
+  Obtaining dependency information for setuptools from https://files.pythonhosted.org/packages/a3/dc/17031897dae0efacfea57dfd3a82fdd2a2aeb58e0ff71b77b87e44edc772/setuptools-80.9.0-py3-none-any.whl.metadata
+  Using cached setuptools-80.9.0-py3-none-any.whl.metadata (6.6 kB)
+Collecting soupsieve>1.2 (from beautifulsoup4<5.0.0,>=4.7.0->redshift-connector)
+  Obtaining dependency information for soupsieve>1.2 from https://files.pythonhosted.org/packages/14/a0/bb38d3b76b8cae341dad93a2dd83ab7462e6dbcdd84d43f54ee60a8dc167/soupsieve-2.8-py3-none-any.whl.metadata
+  Downloading soupsieve-2.8-py3-none-any.whl.metadata (4.6 kB)
+Requirement already satisfied: typing-extensions>=4.0.0 in c:\users\ram caddysy\desktop\intugle1\data-tools\.venv\lib\site-packages (from beautifulsoup4<5.0.0,>=4.7.0->redshift-connector) (4.15.0)
+Collecting jmespath<2.0.0,>=0.7.1 (from boto3<2.0.0,>=1.9.201->redshift-connector)
+  Obtaining dependency information for jmespath<2.0.0,>=0.7.1 from https://files.pythonhosted.org/packages/31/b4/b9b800c45527aadd64d5b442f9b932b00648617eb5d63d2c7a6587b7cafc/jmespath-1.0.1-py3-none-any.whl.metadata
+  Downloading jmespath-1.0.1-py3-none-any.whl.metadata (7.6 kB)
+Collecting s3transfer<0.16.0,>=0.15.0 (from boto3<2.0.0,>=1.9.201->redshift-connector)
+  Obtaining dependency information for s3transfer<0.16.0,>=0.15.0 from https://files.pythonhosted.org/packages/5f/e1/5ef25f52973aa12a19cf4e1375d00932d7fb354ffd310487ba7d44225c1a/s3transfer-0.15.0-py3-none-any.whl.metadata
+  Downloading s3transfer-0.15.0-py3-none-any.whl.metadata (1.7 kB)
+Requirement already satisfied: python-dateutil<3.0.0,>=2.1 in c:\users\ram caddysy\desktop\intugle1\data-tools\.venv\lib\site-packages (from botocore<2.0.0,>=1.12.201->redshift-connector) (2.9.0.post0)
+Requirement already satisfied: urllib3!=2.2.0,<3,>=1.25.4 in c:\users\ram caddysy\desktop\intugle1\data-tools\.venv\lib\site-packages (from botocore<2.0.0,>=1.12.201->redshift-connector) (2.5.0)
+Requirement already satisfied: charset_normalizer<4,>=2 in c:\users\ram caddysy\desktop\intugle1\data-tools\.venv\lib\site-packages (from requests<3.0.0,>=2.23.0->redshift-connector) (3.4.4)
+Requirement already satisfied: idna<4,>=2.5 in c:\users\ram caddysy\desktop\intugle1\data-tools\.venv\lib\site-packages (from requests<3.0.0,>=2.23.0->redshift-connector) (3.11)
+Requirement already satisfied: certifi>=2017.4.17 in c:\users\ram caddysy\desktop\intugle1\data-tools\.venv\lib\site-packages (from requests<3.0.0,>=2.23.0->redshift-connector) (2025.11.12)
+Collecting asn1crypto>=1.5.1 (from scramp<1.5.0,>=1.2.0->redshift-connector)
+  Obtaining dependency information for asn1crypto>=1.5.1 from https://files.pythonhosted.org/packages/c9/7f/09065fd9e27da0eda08b4d6897f1c13535066174cc023af248fc2a8d5e5a/asn1crypto-1.5.1-py2.py3-none-any.whl.metadata
+  Downloading asn1crypto-1.5.1-py2.py3-none-any.whl.metadata (13 kB)
+Requirement already satisfied: six>=1.5 in c:\users\ram caddysy\desktop\intugle1\data-tools\.venv\lib\site-packages (from python-dateutil<3.0.0,>=2.1->botocore<2.0.0,>=1.12.201->redshift-connector) (1.17.0)
+Downloading redshift_connector-2.1.10-py3-none-any.whl (152 kB)
+   ---------------------------------------- 152.8/152.8 kB 4.5 MB/s eta 0:00:00
+Downloading beautifulsoup4-4.14.2-py3-none-any.whl (106 kB)
+   ---------------------------------------- 106.4/106.4 kB 6.4 MB/s eta 0:00:00
+Downloading boto3-1.41.5-py3-none-any.whl (139 kB)
+   ---------------------------------------- 139.3/139.3 kB 8.1 MB/s eta 0:00:00
+Downloading botocore-1.41.5-py3-none-any.whl (14.3 MB)
+   ---------------------------------------- 14.3/14.3 MB 21.1 MB/s eta 0:00:00
+Downloading lxml-5.4.0-cp312-cp312-win_amd64.whl (3.8 MB)
+   ---------------------------------------- 3.8/3.8 MB 20.4 MB/s eta 0:00:00
+Downloading scramp-1.4.6-py3-none-any.whl (12 kB)
+Using cached setuptools-80.9.0-py3-none-any.whl (1.2 MB)
+Downloading asn1crypto-1.5.1-py2.py3-none-any.whl (105 kB)
+   ---------------------------------------- 105.0/105.0 kB ? eta 0:00:00
+Downloading jmespath-1.0.1-py3-none-any.whl (20 kB)
+Downloading s3transfer-0.15.0-py3-none-any.whl (85 kB)
+   ---------------------------------------- 86.0/86.0 kB 5.0 MB/s eta 0:00:00
+Downloading soupsieve-2.8-py3-none-any.whl (36 kB)
+Installing collected packages: asn1crypto, soupsieve, setuptools, scramp, lxml, jmespath, botocore, beautifulsoup4, s3transfer, boto3, redshift-connector
+Successfully installed asn1crypto-1.5.1 beautifulsoup4-4.14.2 boto3-1.41.5 botocore-1.41.5 jmespath-1.0.1 lxml-5.4.0 redshift-connector-2.1.10 s3transfer-0.15.0 scramp-1.4.6 setuptools-80.9.0 soupsieve-2.8

docsite/docs/connectors/redshift.md

@@ -0,0 +1,95 @@
+# Amazon Redshift Adapter for Intugle
+
+This document explains how to use the **RedshiftAdapter** in Intugle to connect, profile, and work with Amazon Redshift data warehouses.
+
+## Overview
+
+The Redshift adapter enables Intugle to:
+
+* Connect to Redshift clusters.
+* Profile tables and columns.
+* Execute queries and create new tables/views.
+* Perform semantic searches and generate data products.
+
+## Installation
+
+Install the optional Redshift dependencies:
+
+```bash
+pip install "intugle[redshift]"
+```
+
+This installs:
+
+* `redshift-connector>=2.0.0`
+* Other necessary dependencies for Redshift integration
+
+## Configuration
+
+Configure your Redshift connection either in `profiles.yml` or via Python using `RedshiftConfig`.
+
+### Example Python Configuration:
+
+```python
+from intugle.adapters.types.redshift.models import RedshiftConfig
+from intugle.adapters.types.redshift.redshift import RedshiftAdapter
+
+cfg = RedshiftConfig(
+    host="your-cluster.xxxxxxxxxxxx.us-east-1.redshift.amazonaws.com",
+    port=5439,
+    user="your_username",
+    password="your_password",
+    database="dev",
+    schema="public",
+    ssl=True
+)
+
+adapter = RedshiftAdapter(cfg)
+```
+
+### IAM Authentication
+
+You can enable IAM-based authentication instead of username/password:
+
+```yaml
+redshift:
+  iam: true
+  cluster_id: "your-cluster-id"
+  region: "us-east-1"
+```
+
+## Using the Adapter
+
+### Connect to Redshift
+
+```python
+conn = adapter.connect()
+```
+
+### Profile Tables
+
+```python
+profile = adapter.profile(table_name="sales")
+print(profile)
+```
+
+### Execute Query
+
+```python
+result_df = adapter.to_df_from_query("SELECT * FROM sales LIMIT 10")
+```
+
+### Create Table from Query
+
+```python
+adapter.create_table_from_query(
+    table_name="new_sales",
+    query="SELECT * FROM sales WHERE amount > 100"
+)
+```
+## Notes
+
+* Redshift is largely PostgreSQL-compatible, but some SQL functions or data types may differ.
+* Use `ssl=True` in production for secure connections.
+* IAM authentication is optional but recommended for added security.
+* The adapter uses `redshift-connector` under the hood for database interactions.

pyproject.toml

@@ -83,6 +83,10 @@ streamlit = [
     "graphviz"
 ]
 
+redshift = [
+    "redshift-connector>=2.0.0"
+]
+
 
 [project.urls]
 "Homepage" = "https://github.com/Intugle/data-tools"

src/intugle/adapters/factory.py

@@ -1,5 +1,4 @@
 import importlib
-
 from typing import Any, Callable, Type, Union
 
 from .adapter import Adapter
@@ -11,6 +10,7 @@ class ModuleInterface:
     @staticmethod
     def register() -> None:
         """Register the necessary items in the environment factory."""
+        ...
 
 
 def import_module(name: str) -> ModuleInterface:
@@ -26,6 +26,9 @@ def import_module(name: str) -> ModuleInterface:
     "intugle.adapters.types.postgres.postgres",
     "intugle.adapters.types.sqlserver.sqlserver",
     "intugle.adapters.types.sqlite.sqlite",
+
+    # ✅ Added Redshift adapter plugin
+    "intugle.adapters.types.redshift.redshift",
 ]
 
 
@@ -49,7 +52,10 @@ def __init__(self, plugins: list[dict] = None):
                 plugin = import_module(_plugin)
                 plugin.register(self)
             except ImportError:
-                print(f"Warning: Could not load plugin '{_plugin}' due to missing dependencies. This adapter will not be available.")
+                print(
+                    f"Warning: Could not load plugin '{_plugin}' due to missing dependencies. "
+                    "This adapter will not be available."
+                )
                 pass
 
     @classmethod
@@ -77,12 +83,14 @@ def get_dataset_data_type(cls) -> Type[Any]:
             return Any
         if len(cls.config_types) == 1:
             return cls.config_types[0]
-        return Union[tuple(cls.config_types)]  # noqa: UP007
+        return Union[tuple(cls.config_types)]
 
     @classmethod
     def create(cls, df: Any) -> Adapter:
-        """Create a execution engine type"""
+        """Create an execution engine type"""
         for checker_fn, creator_fn in cls.dataframe_funcs.values():
             if checker_fn(df):
                 return creator_fn()
-        raise ValueError(f"No suitable dataframe type found for object of type {type(df)!r}")
+        raise ValueError(
+            f"No suitable dataframe type found for object of type {type(df)!r}"
+        )

src/intugle/adapters/types/redshift/__init__.py

@@ -0,0 +1,8 @@
+from .redshift import RedshiftAdapter
+from .models import RedshiftConfig, RedshiftDataConfig
+
+__all__ = [
+    "RedshiftAdapter",
+    "RedshiftConfig",
+    "RedshiftDataConfig",
+]

src/intugle/adapters/types/redshift/models.py

@@ -0,0 +1,62 @@
+from pydantic import BaseModel, Field, SecretStr
+from typing import Optional, List
+
+
+class RedshiftConfig(BaseModel):
+    """
+    Connection configuration for Amazon Redshift.
+    Mirrors the structure of PostgresConfig but adds Redshift-specific fields.
+    """
+
+    host: str = Field(..., description="Redshift cluster endpoint")
+    port: int = Field(default=5439, description="Default Redshift port")
+    database: str = Field(..., description="Database name")
+    user: Optional[str] = Field(None, description="Database user")
+    password: Optional[SecretStr] = Field(
+        None, description="Password for database user"
+    )
+
+    # Redshift-specific options
+    iam: bool = Field(
+        default=False,
+        description="Enable IAM authentication instead of username/password",
+    )
+    cluster_id: Optional[str] = Field(
+        default=None,
+        description="Cluster identifier (required for IAM auth)",
+    )
+    region: Optional[str] = Field(
+        default=None,
+        description="AWS region of the Redshift cluster (for IAM auth)",
+    )
+
+    ssl: bool = Field(default=True, description="Enable SSL for secure connection")
+    connect_timeout: int = Field(
+        default=10, description="Connection timeout in seconds"
+    )
+
+
+class RedshiftDataConfig(BaseModel):
+    """
+    Optional data configuration for Redshift operations.
+    Specifies schema and additional settings for Intugle data operations.
+    """
+
+    schema: str = Field(
+        default="public",
+        description="Default schema to operate in",
+    )
+
+    diststyle: Optional[str] = Field(
+        default=None,
+        description="Redshift table distribution style (AUTO, EVEN, KEY, ALL)",
+    )
+    distkey: Optional[str] = Field(
+        default=None,
+        description="Distribution key column name",
+    )
+    sortkeys: Optional[List[str]] = Field(
+        default=None,
+        description="Sort key columns for the table",
+    )
+