dsl-spa 0.0.1__tar.gz

dsl_spa-0.0.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 superwise-brian
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

dsl_spa-0.0.1/PKG-INFO

@@ -0,0 +1,45 @@
+Metadata-Version: 2.4
+Name: dsl-spa
+Version: 0.0.1
+Summary: A tool for building Structured Agentic Pipelines
+Author-email: superwise-brian <brian.mcclannahan@superwise.ai>
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/superwise-ai/dsl-spa
+Project-URL: Issues, https://github.com/superwise-ai/dsl-spa/issues
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# Domain Specific Language - Structured Pipeline Agent
+
+DSL-SPA is an open-source Python library for connecting LLM Agents to ETL and other common tasks.  With this tool, you can connect LLM Agents to complex Data Pipelines.
+
+Key Features of DSL-SPA
+
+- Building SQL Queries - construct sql queries from fields extracted by Agents
+
+- Applying Data Transformations - selectively apply data transformations based on Agent instructions
+
+- Generating Unstructured Text Summaries - generate summaries of query results and data transformations 
+
+- Generating Visualizations - generate vega-lite visualizations of query results and data transformations
+
+## Getting Started
+
+
+Get started with dsl-spa by installing the Python library via pip
+
+```
+pip install dsl-spa
+```
+
+A standard pipeline can be imported with
+
+```
+from dsl-spa.pipeline import StandardPipeline
+```
+
+For more details on constructing a pipeline, reference [Building a Pipeline](https://github.com/superwise-ai/dsl-spa/blob/main/docs/Creating_a_Pipeline_Schema.md).

dsl_spa-0.0.1/README.md

@@ -0,0 +1,30 @@
+# Domain Specific Language - Structured Pipeline Agent
+
+DSL-SPA is an open-source Python library for connecting LLM Agents to ETL and other common tasks.  With this tool, you can connect LLM Agents to complex Data Pipelines.
+
+Key Features of DSL-SPA
+
+- Building SQL Queries - construct sql queries from fields extracted by Agents
+
+- Applying Data Transformations - selectively apply data transformations based on Agent instructions
+
+- Generating Unstructured Text Summaries - generate summaries of query results and data transformations 
+
+- Generating Visualizations - generate vega-lite visualizations of query results and data transformations
+
+## Getting Started
+
+
+Get started with dsl-spa by installing the Python library via pip
+
+```
+pip install dsl-spa
+```
+
+A standard pipeline can be imported with
+
+```
+from dsl-spa.pipeline import StandardPipeline
+```
+
+For more details on constructing a pipeline, reference [Building a Pipeline](https://github.com/superwise-ai/dsl-spa/blob/main/docs/Creating_a_Pipeline_Schema.md).

dsl_spa-0.0.1/pyproject.toml

@@ -0,0 +1,23 @@
+[project]
+name = "dsl-spa"
+version = "0.0.1"
+authors = [
+  { name="superwise-brian", email="brian.mcclannahan@superwise.ai" },
+]
+description = "A tool for building Structured Agentic Pipelines"
+readme = "README.md"
+requires-python = ">=3.9"
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Operating System :: OS Independent",
+]
+license = "MIT"
+license-files = ["LICEN[CS]E*"]
+
+[project.urls]
+Homepage = "https://github.com/superwise-ai/dsl-spa"
+Issues = "https://github.com/superwise-ai/dsl-spa/issues"
+
+[build-system]
+requires = ["setuptools >= 77.0.3","pandas >= 2.0.0","altair >= 5.3.0","SQLAlchemy >= 2.0.0"]
+build-backend = "setuptools.build_meta"

dsl_spa-0.0.1/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

dsl_spa-0.0.1/src/dsl_spa/pipeline/connector.py

@@ -0,0 +1,142 @@
+import pandas as pd
+import sqlalchemy as sa
+from sqlalchemy.engine import URL
+from sqlalchemy.engine.url import make_url
+import os
+import json
+
+class Connector:
+    """Base Connector Class. Any connector should inherit from this class or a sub class.
+    """
+    
+    def connect(self):
+        """Connects to the external connection
+        """
+        raise NotImplementedError("This method must be implemented in a subclass")
+    
+class DatabaseConnector(Connector):
+    """Database Connector. Includes a query method to query a database.
+    """
+    def __init__(self):
+        self.engine = None
+    
+    def query(self, query_string: str) -> pd.DataFrame:
+        """Runs the query_string query using self.engine.
+
+        Args:
+            query_string (str): Query string to query
+
+        Returns:
+            pd.DataFrame: Pandas Dataframe of query data
+        """
+        raise NotImplementedError("This method must be implemented in a subclass")
+    
+class MSSQLConnector(DatabaseConnector):
+    """Microsoft SQL Database Connector.
+    """
+    def __init__(self, uid: str, password: str, host: str, database: str, driver: str):
+        """Creates a Microsoft SQL Connector
+
+        Args:
+            uid (str): Username
+            password (str): Password
+            host (str): Database Host Server
+            database (str): Database Name
+            driver (str): Name of ODBC Driver
+        """
+        super().__init__()
+        self.uid = uid
+        self.password = password
+        self.host = host
+        self.database = database
+        self.driver = driver
+        
+    def connect(self):
+        """Connects to the external connection
+        """
+        connection_url = URL.create(
+            "mssql+pyodbc",
+            username=self.uid,
+            password=self.password,
+            host=self.host,
+            database=self.database,
+            query={"driver": self.driver},
+        )
+        self.engine = sa.create_engine(connection_url)
+        
+    def query(self, sql_query: str):
+        return pd.read_sql_query(sql_query, self.engine)
+    
+class BigQueryConnector(DatabaseConnector):
+    """Big Query Database Connector.
+    """
+    
+    def __init__(self, url: str, account_type: str, project_id: str, location: str = None):
+        """Creates a Big Query Connector
+
+        Args:
+            url (str): GCP connection URL
+            account_type (str): GCP account type
+            project_id (str): GCP Project ID
+            location (str, optional): GCP Server location. Defaults to None.
+        """
+        super().__init__()
+        self.url = url
+        self.location = location
+        self.account_type = account_type
+        self.project_id = project_id
+        
+    def connect(self):
+        """Connects to the external connection
+        """
+        credentials_dict = {
+            "type": self.account_type,
+            "project_id": self.project_id
+        }
+        credentials_info = None
+        if "credentials_base64" in make_url(self.url).query:
+            credentials_info = json.dumps(credentials_dict)
+
+        if self.location is None:
+            self.engine = sa.create_engine(self.url, credentials_info=credentials_info)
+        else:
+            self.engine = sa.create_engine(self.url, location=self.location, credentials_info=credentials_info)
+        
+    def query(self, sql_query: str):
+        """Runs the query_string query using self.engine.
+
+        Args:
+            query_string (str): Query string to query
+
+        Returns:
+            pd.DataFrame: Pandas Dataframe of query data
+        """
+        return pd.read_sql_query(sql_query, self.engine)
+    
+class LocalCSVConnector(Connector):
+    
+    def __init__(self, folder: str):
+        """Creates a local CSV connector given the folder location of the CSVs.
+
+        Args:
+            folder (str): Location of CSV directory
+        """
+        self.folder = folder
+        self.df = None
+        
+    def connect(self):
+        """Does nothing since the CSV is local.
+        """
+        pass
+    
+    def query(self, csv_name: str):
+        """Runs the query_string query using self.engine.
+
+        Args:
+            query_string (str): Query string to query
+
+        Returns:
+            pd.DataFrame: Pandas Dataframe of query data
+        """
+        file_location = os.path.join(self.folder,csv_name)
+        return pd.read_csv(file_location)