praisonaiagents 0.0.23__py3-none-any.whl → 0.0.24__py3-none-any.whl

praisonaiagents/tools/duckdb_tools.py

@@ -0,0 +1,268 @@
+"""Tools for working with DuckDB databases.
+
+Usage:
+from praisonaiagents.tools import duckdb_tools
+df = duckdb_tools.query("SELECT * FROM my_table")
+
+or
+from praisonaiagents.tools import query_db, create_table, load_data
+df = query_db("SELECT * FROM my_table")
+"""
+
+import logging
+from typing import List, Dict, Any, Optional, Union, TYPE_CHECKING
+from importlib import util
+import json
+
+if TYPE_CHECKING:
+    import duckdb
+    import pandas as pd
+
+class DuckDBTools:
+    """Tools for working with DuckDB databases."""
+    
+    def __init__(self, database: str = ':memory:'):
+        """Initialize DuckDBTools.
+        
+        Args:
+            database: Path to database file or ':memory:' for in-memory database
+        """
+        self.database = database
+        self._conn = None
+
+    def _get_duckdb(self) -> Optional['duckdb']:
+        """Get duckdb module, installing if needed"""
+        if util.find_spec('duckdb') is None:
+            error_msg = "duckdb package is not available. Please install it using: pip install duckdb"
+            logging.error(error_msg)
+            return None
+        import duckdb
+        return duckdb
+
+    def _get_pandas(self) -> Optional['pd']:
+        """Get pandas module, installing if needed"""
+        if util.find_spec('pandas') is None:
+            error_msg = "pandas package is not available. Please install it using: pip install pandas"
+            logging.error(error_msg)
+            return None
+        import pandas as pd
+        return pd
+
+    def _get_connection(self) -> Optional['duckdb.DuckDBPyConnection']:
+        """Get or create database connection"""
+        if self._conn is None:
+            duckdb = self._get_duckdb()
+            if duckdb is None:
+                return None
+            try:
+                self._conn = duckdb.connect(self.database)
+            except Exception as e:
+                error_msg = f"Error connecting to database {self.database}: {str(e)}"
+                logging.error(error_msg)
+                return None
+        return self._conn
+
+    def execute_query(
+        self,
+        query: str,
+        params: Optional[Union[tuple, dict]] = None,
+        return_df: bool = True
+    ) -> Union[List[Dict[str, Any]], Dict[str, str]]:
+        """Execute a SQL query.
+        
+        Args:
+            query: SQL query to execute
+            params: Query parameters
+            return_df: If True, return results as DataFrame records
+            
+        Returns:
+            Query results as list of dicts, or error dict
+        """
+        try:
+            conn = self._get_connection()
+            if conn is None:
+                return {"error": "Could not connect to database"}
+
+            if params:
+                result = conn.execute(query, params)
+            else:
+                result = conn.execute(query)
+
+            if return_df:
+                pd = self._get_pandas()
+                if pd is None:
+                    return {"error": "pandas package not available"}
+                df = result.df()
+                return df.to_dict('records')
+            else:
+                return [dict(row) for row in result.fetchall()]
+
+        except Exception as e:
+            error_msg = f"Error executing query: {str(e)}"
+            logging.error(error_msg)
+            return {"error": error_msg}
+
+    def load_csv(
+        self,
+        table_name: str,
+        filepath: str,
+        schema: Optional[Dict[str, str]] = None,
+        if_exists: str = 'replace'
+    ) -> bool:
+        """Load a CSV file into a table.
+        
+        Args:
+            table_name: Name of table to create
+            filepath: Path to CSV file
+            schema: Optional column definitions
+            if_exists: What to do if table exists ('fail', 'replace', 'append')
+            
+        Returns:
+            bool: Success status
+        """
+        try:
+            conn = self._get_connection()
+            if conn is None:
+                return False
+
+            # Check if table exists
+            exists = conn.execute(f"""
+                SELECT name FROM sqlite_master 
+                WHERE type='table' AND name='{table_name}'
+            """).fetchone() is not None
+
+            if exists:
+                if if_exists == 'fail':
+                    raise ValueError(f"Table {table_name} already exists")
+                elif if_exists == 'replace':
+                    conn.execute(f"DROP TABLE IF EXISTS {table_name}")
+                elif if_exists != 'append':
+                    raise ValueError("if_exists must be 'fail', 'replace', or 'append'")
+
+            # Create table if needed
+            if not exists or if_exists == 'replace':
+                if schema:
+                    # Create table with schema
+                    columns = ', '.join(f"{k} {v}" for k, v in schema.items())
+                    conn.execute(f"CREATE TABLE {table_name} ({columns})")
+                else:
+                    # Infer schema from CSV
+                    conn.execute(f"""
+                        CREATE TABLE {table_name} AS 
+                        SELECT * FROM read_csv_auto('{filepath}')
+                        WHERE 1=0
+                    """)
+
+            # Load data
+            conn.execute(f"""
+                INSERT INTO {table_name}
+                SELECT * FROM read_csv_auto('{filepath}')
+            """)
+
+            return True
+
+        except Exception as e:
+            error_msg = f"Error loading CSV file {filepath}: {str(e)}"
+            logging.error(error_msg)
+            return False
+
+    def export_csv(
+        self,
+        query: str,
+        filepath: str,
+        params: Optional[Union[tuple, dict]] = None
+    ) -> bool:
+        """Export query results to CSV.
+        
+        Args:
+            query: SQL query to execute
+            filepath: Output file path
+            params: Optional query parameters
+            
+        Returns:
+            bool: Success status
+        """
+        try:
+            # Execute query and get results as DataFrame
+            results = self.execute_query(query, params)
+            if isinstance(results, dict) and 'error' in results:
+                return False
+
+            pd = self._get_pandas()
+            if pd is None:
+                return False
+
+            # Convert to DataFrame and save
+            df = pd.DataFrame(results)
+            df.to_csv(filepath, index=False)
+            return True
+
+        except Exception as e:
+            error_msg = f"Error exporting to CSV file {filepath}: {str(e)}"
+            logging.error(error_msg)
+            return False
+
+    def close(self):
+        """Close database connection."""
+        if self._conn:
+            self._conn.close()
+            self._conn = None
+
+# Create instance for direct function access
+_duckdb_tools = DuckDBTools()
+execute_query = _duckdb_tools.execute_query
+load_csv = _duckdb_tools.load_csv
+export_csv = _duckdb_tools.export_csv
+
+if __name__ == "__main__":
+    print("\n==================================================")
+    print("DuckDBTools Demonstration")
+    print("==================================================\n")
+    
+    # Create a temporary file for testing
+    import tempfile
+    import os
+    
+    with tempfile.NamedTemporaryFile(suffix='.csv', delete=False) as temp:
+        temp_file = temp.name
+        
+        # Create sample data
+        with open(temp_file, 'w') as f:
+            f.write("name,age,city\n")
+            f.write("Alice,25,New York\n")
+            f.write("Bob,30,San Francisco\n")
+            f.write("Charlie,35,Chicago\n")
+        
+        print("1. Loading CSV File")
+        print("------------------------------")
+        result = load_csv('users', temp_file)
+        print(f"CSV loaded successfully: {result}")
+        print()
+        
+        print("2. Executing Query")
+        print("------------------------------")
+        query = "SELECT * FROM users WHERE age > 25"
+        results = execute_query(query)
+        print("Query results:")
+        for row in results:
+            print(row)
+        print()
+        
+        print("3. Exporting Query Results")
+        print("------------------------------")
+        with tempfile.NamedTemporaryFile(suffix='.csv', delete=False) as temp2:
+            temp_file2 = temp2.name
+            result = export_csv(query, temp_file2)
+            print(f"Results exported successfully: {result}")
+            if result:
+                print("\nExported file contents:")
+                with open(temp_file2) as f:
+                    print(f.read())
+        
+        # Clean up temporary files
+        os.unlink(temp_file)
+        os.unlink(temp_file2)
+    
+    print("==================================================")
+    print("Demonstration Complete")
+    print("==================================================\n")

praisonaiagents/tools/duckduckgo_tools.py

@@ -0,0 +1,52 @@
+"""DuckDuckGo search functionality.
+
+Usage:
+from praisonaiagents.tools import internet_search
+results = internet_search("AI news")
+
+or 
+from praisonaiagents.tools import duckduckgo
+results = duckduckgo("AI news")
+"""
+
+from typing import List, Dict
+import logging
+from importlib import util
+import sys
+
+def internet_search(query: str) -> List[Dict]:
+    """Perform an internet search using DuckDuckGo."""
+    # Check if duckduckgo_search is installed
+    if util.find_spec("duckduckgo_search") is None:
+        error_msg = "DuckDuckGo search is not available. Please install duckduckgo_search package using: pip install duckduckgo_search"
+        logging.error(error_msg)
+        return [{"error": error_msg}]
+
+    try:
+        # Import only when needed
+        from duckduckgo_search import DDGS
+        results = []
+        ddgs = DDGS()
+        for result in ddgs.text(keywords=query, max_results=5):
+            results.append({
+                "title": result.get("title", ""),
+                "url": result.get("href", ""),
+                "snippet": result.get("body", "")
+            })
+        return results
+
+    except Exception as e:
+        error_msg = f"Error during DuckDuckGo search: {e}"
+        logging.error(error_msg)
+        return [{"error": error_msg}]
+
+# Make the module callable
+sys.modules[__name__].__call__ = internet_search
+
+if __name__ == "__main__":
+    # Example usage
+    results = internet_search("Python programming")
+    for result in results:
+        print(f"\nTitle: {result.get('title')}")
+        print(f"URL: {result.get('url')}")
+        print(f"Snippet: {result.get('snippet')}")

praisonaiagents/tools/excel_tools.py

@@ -0,0 +1,310 @@
+"""Tools for working with Excel files.
+
+Usage:
+from praisonaiagents.tools import excel_tools
+df = excel_tools.read_excel("data.xlsx")
+
+or
+from praisonaiagents.tools import read_excel, write_excel, merge_excel
+df = read_excel("data.xlsx")
+"""
+
+import logging
+from typing import List, Dict, Union, Optional, Any, TYPE_CHECKING, Tuple
+from importlib import util
+import json
+from pathlib import Path
+import tempfile
+import os
+
+if TYPE_CHECKING:
+    import pandas as pd
+    from openpyxl.styles import Font, PatternFill, Alignment, Border, Side
+    from openpyxl.chart import BarChart, LineChart, PieChart, Reference
+    from openpyxl.chart.label import DataLabelList
+
+class ExcelTools:
+    """Tools for working with Excel files."""
+    
+    def __init__(self):
+        """Initialize ExcelTools."""
+        pass
+
+    def _get_pandas(self) -> Optional['pd']:
+        """Get pandas module, installing if needed"""
+        if util.find_spec('pandas') is None:
+            error_msg = "pandas package is not available. Please install it using: pip install pandas"
+            logging.error(error_msg)
+            return None
+        if util.find_spec('openpyxl') is None:
+            error_msg = "openpyxl package is not available. Please install it using: pip install openpyxl"
+            logging.error(error_msg)
+            return None
+        import pandas as pd
+        return pd
+
+    def read_excel(
+        self,
+        filepath: str,
+        sheet_name: Optional[Union[str, int, List[Union[str, int]]]] = 0,
+        header: Optional[int] = 0,
+        usecols: Optional[List[str]] = None,
+        skiprows: Optional[Union[int, List[int]]] = None,
+        na_values: Optional[List[str]] = None,
+        dtype: Optional[Dict[str, str]] = None
+    ) -> Union[Dict[str, List[Dict[str, Any]]], List[Dict[str, Any]]]:
+        """Read an Excel file with advanced options.
+        
+        Args:
+            filepath: Path to Excel file
+            sheet_name: Sheet name(s) or index(es)
+            header: Row number(s) to use as column names
+            usecols: Columns to read
+            skiprows: Line numbers to skip
+            na_values: Additional strings to recognize as NA/NaN
+            dtype: Dict of column dtypes
+            
+        Returns:
+            Dict of sheet names to data if multiple sheets, else list of row dicts
+        """
+        try:
+            pd = self._get_pandas()
+            if pd is None:
+                return {"error": "Required packages not available"}
+
+            # Read Excel file
+            df = pd.read_excel(
+                filepath,
+                sheet_name=sheet_name,
+                header=header,
+                usecols=usecols,
+                skiprows=skiprows,
+                na_values=na_values,
+                dtype=dtype,
+                engine='openpyxl'
+            )
+            
+            # Convert to dict format
+            if isinstance(df, dict):
+                return {
+                    name: df[name].to_dict('records')
+                    for name in df.keys()
+                }
+            else:
+                return df.to_dict('records')
+                
+        except Exception as e:
+            error_msg = f"Error reading Excel file {filepath}: {str(e)}"
+            logging.error(error_msg)
+            return {"error": error_msg}
+
+    def write_excel(
+        self,
+        filepath: str,
+        data: Union[Dict[str, List[Dict[str, Any]]], List[Dict[str, Any]]],
+        sheet_name: Optional[str] = None,
+        index: bool = False,
+        header: bool = True,
+        mode: str = 'w'
+    ) -> bool:
+        """Write data to an Excel file.
+        
+        Args:
+            filepath: Path to Excel file
+            data: Data to write (dict of sheet names to data or list of row dicts)
+            sheet_name: Sheet name if data is a list
+            index: Whether to write row indices
+            header: Whether to write column headers
+            mode: Write mode ('w' for write, 'a' for append)
+            
+        Returns:
+            bool: Success status
+        """
+        try:
+            pd = self._get_pandas()
+            if pd is None:
+                return False
+
+            # Convert data to DataFrame(s)
+            if isinstance(data, dict):
+                if mode == 'a' and os.path.exists(filepath):
+                    book = pd.ExcelFile(filepath)
+                    with pd.ExcelWriter(filepath, engine='openpyxl') as writer:
+                        # Copy existing sheets
+                        for sheet in book.sheet_names:
+                            pd.read_excel(filepath, sheet_name=sheet).to_excel(
+                                writer, sheet_name=sheet, index=index, header=header
+                            )
+                        # Add new sheets
+                        for name, sheet_data in data.items():
+                            df = pd.DataFrame(sheet_data)
+                            df.to_excel(
+                                writer, sheet_name=name, index=index, header=header
+                            )
+                else:
+                    with pd.ExcelWriter(filepath, engine='openpyxl') as writer:
+                        for name, sheet_data in data.items():
+                            df = pd.DataFrame(sheet_data)
+                            df.to_excel(
+                                writer, sheet_name=name, index=index, header=header
+                            )
+            else:
+                if mode == 'a' and os.path.exists(filepath):
+                    book = pd.ExcelFile(filepath)
+                    with pd.ExcelWriter(filepath, engine='openpyxl') as writer:
+                        # Copy existing sheets
+                        for sheet in book.sheet_names:
+                            pd.read_excel(filepath, sheet_name=sheet).to_excel(
+                                writer, sheet_name=sheet, index=index, header=header
+                            )
+                        # Add new sheet
+                        df = pd.DataFrame(data)
+                        df.to_excel(
+                            writer,
+                            sheet_name=sheet_name or 'Sheet1',
+                            index=index,
+                            header=header
+                        )
+                else:
+                    df = pd.DataFrame(data)
+                    df.to_excel(
+                        filepath,
+                        sheet_name=sheet_name or 'Sheet1',
+                        index=index,
+                        header=header,
+                        engine='openpyxl'
+                    )
+            
+            return True
+            
+        except Exception as e:
+            error_msg = f"Error writing Excel file {filepath}: {str(e)}"
+            logging.error(error_msg)
+            return False
+
+    def merge_excel(
+        self,
+        files: List[str],
+        output_file: str,
+        how: str = 'inner',
+        on: Optional[Union[str, List[str]]] = None,
+        suffixes: Optional[Tuple[str, str]] = None
+    ) -> bool:
+        """Merge multiple Excel files.
+        
+        Args:
+            files: List of Excel files to merge
+            output_file: Output file path
+            how: Merge method ('inner', 'outer', 'left', 'right')
+            on: Column(s) to merge on
+            suffixes: Suffixes for overlapping columns
+            
+        Returns:
+            bool: Success status
+        """
+        try:
+            if len(files) < 2:
+                error_msg = "At least two files are required for merging"
+                logging.error(error_msg)
+                return False
+            
+            # Read first file
+            result = self.read_excel(files[0])
+            
+            # Merge with remaining files
+            for file in files[1:]:
+                df = self.read_excel(file)
+                if isinstance(df, dict):
+                    df = next(iter(df.values()))
+                
+                pd = self._get_pandas()
+                if pd is None:
+                    return False
+                
+                result = pd.merge(
+                    pd.DataFrame(result),
+                    pd.DataFrame(df),
+                    how=how,
+                    on=on,
+                    suffixes=suffixes or ('_1', '_2')
+                ).to_dict('records')
+            
+            # Write merged result
+            return self.write_excel(output_file, result)
+            
+        except Exception as e:
+            error_msg = f"Error merging Excel files: {str(e)}"
+            logging.error(error_msg)
+            return False
+
+# Create instance for direct function access
+_excel_tools = ExcelTools()
+read_excel = _excel_tools.read_excel
+write_excel = _excel_tools.write_excel
+merge_excel = _excel_tools.merge_excel
+
+if __name__ == "__main__":
+    print("\n==================================================")
+    print("ExcelTools Demonstration")
+    print("==================================================\n")
+    
+    # Create a temporary file for testing
+    with tempfile.NamedTemporaryFile(suffix='.xlsx', delete=False) as temp:
+        temp_file = temp.name
+        
+        print("1. Writing Excel File")
+        print("------------------------------")
+        data = [
+            {"name": "Alice", "age": 25, "city": "New York"},
+            {"name": "Bob", "age": 30, "city": "San Francisco"},
+            {"name": "Charlie", "age": 35, "city": "Chicago"}
+        ]
+        result = write_excel(temp_file, data, "People")
+        print(f"Data written successfully: {result}")
+        print()
+        
+        print("2. Reading Excel File")
+        print("------------------------------")
+        read_data = read_excel(temp_file)
+        print("Contents of Excel file:")
+        for row in read_data:
+            print(row)
+        print()
+        
+        print("3. Merging Excel Files")
+        print("------------------------------")
+        # Create a second file for merging
+        with tempfile.NamedTemporaryFile(suffix='.xlsx', delete=False) as temp2:
+            temp_file2 = temp2.name
+            data2 = [
+                {"name": "Alice", "salary": 75000},
+                {"name": "Bob", "salary": 85000},
+                {"name": "Charlie", "salary": 95000}
+            ]
+            write_excel(temp_file2, data2, "Salaries")
+            
+            # Merge files
+            with tempfile.NamedTemporaryFile(suffix='.xlsx', delete=False) as temp3:
+                temp_file3 = temp3.name
+                result = merge_excel(
+                    [temp_file, temp_file2],
+                    temp_file3,
+                    how='inner',
+                    on='name'
+                )
+                print(f"Files merged successfully: {result}")
+                if result:
+                    merged_data = read_excel(temp_file3)
+                    print("\nMerged contents:")
+                    for row in merged_data:
+                        print(row)
+                print()
+        
+        # Clean up temporary files
+        os.unlink(temp_file)
+        os.unlink(temp_file2)
+        os.unlink(temp_file3)
+    
+    print("==================================================")
+    print("Demonstration Complete")
+    print("==================================================\n")