QuerySUTRA 0.3.1__py3-none-any.whl → 0.3.3__py3-none-any.whl

querysutra-0.3.1.dist-info/METADATA

@@ -1,429 +0,0 @@
-Metadata-Version: 2.4
-Name: QuerySUTRA
-Version: 0.3.1
-Summary: SUTRA: Structured-Unstructured-Text-Retrieval-Architecture - AI-powered data analysis with custom visualizations, fuzzy matching, and smart caching
-Home-page: https://github.com/yourusername/querysutra
-Author: Aditya Batta
-Author-email: 
-License: MIT
-Classifier: Development Status :: 4 - Beta
-Classifier: Intended Audience :: Developers
-Classifier: Topic :: Database
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Programming Language :: Python :: 3
-Requires-Python: >=3.8
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: pandas>=1.3.0
-Requires-Dist: numpy>=1.21.0
-Requires-Dist: openai>=1.0.0
-Requires-Dist: plotly>=5.0.0
-Requires-Dist: matplotlib>=3.3.0
-Requires-Dist: PyPDF2>=3.0.0
-Requires-Dist: python-docx>=0.8.11
-Requires-Dist: openpyxl>=3.0.0
-Provides-Extra: mysql
-Requires-Dist: sqlalchemy>=1.4.0; extra == "mysql"
-Requires-Dist: mysql-connector-python>=8.0.0; extra == "mysql"
-Provides-Extra: postgres
-Requires-Dist: sqlalchemy>=1.4.0; extra == "postgres"
-Requires-Dist: psycopg2-binary>=2.9.0; extra == "postgres"
-Provides-Extra: embeddings
-Requires-Dist: sentence-transformers>=2.0.0; extra == "embeddings"
-Provides-Extra: all
-Requires-Dist: sqlalchemy>=1.4.0; extra == "all"
-Requires-Dist: mysql-connector-python>=8.0.0; extra == "all"
-Requires-Dist: psycopg2-binary>=2.9.0; extra == "all"
-Requires-Dist: sentence-transformers>=2.0.0; extra == "all"
-Dynamic: home-page
-Dynamic: license-file
-Dynamic: requires-python
-
-# QuerySUTRA
-
-**SUTRA: Structured-Unstructured-Text-Retrieval-Architecture**
-
-Transform any data into structured, queryable databases with AI-powered entity extraction.
-
-## 🎯 Key Features
-
-✅ **Multi-Table Creation** - Automatically extracts entities and creates multiple related tables  
-✅ **Smart Entity Extraction** - Identifies people, contacts, events, organizations from unstructured data  
-✅ **Natural Language Queries** - Ask questions in plain English  
-✅ **Multiple Data Formats** - CSV, Excel, JSON, PDF, DOCX, TXT, SQL, DataFrames  
-✅ **Direct SQL Access** - Query without API costs  
-✅ **Auto Visualization** - Built-in charts and graphs  
-✅ **Cloud Export** - Save to MySQL, PostgreSQL, or local SQLite  
-
-## 📦 Installation
-
-```bash
-pip install QuerySUTRA
-
-# With MySQL support
-pip install QuerySUTRA[mysql]
-
-# With PostgreSQL support
-pip install QuerySUTRA[postgres]
-
-# With all database support
-pip install QuerySUTRA[all]
-```
-
-## 🚀 Quick Start
-
-```python
-from sutra import SUTRA
-
-# Initialize
-sutra = SUTRA(api_key="your-openai-key")
-
-# Upload any data - AI creates multiple structured tables!
-sutra.upload("employee_story.pdf")
-
-# View all created tables
-sutra.tables()
-# Output:
-# 📋 TABLES IN DATABASE
-# 1. employee_story_people (20 rows, 6 columns)
-#    Columns: id, name, address, city, email, phone
-# 2. employee_story_contacts (20 rows, 4 columns)
-#    Columns: id, person_id, email, phone
-# 3. employee_story_events (15 rows, 4 columns)
-#    Columns: id, host_id, description, city
-
-# View detailed schema
-sutra.schema()
-
-# Query with natural language
-result = sutra.ask("Show all people from New York")
-print(result.data)
-
-# With visualization
-result = sutra.ask("Show events by city", viz=True)
-
-# Direct SQL (no API cost!)
-result = sutra.sql("SELECT * FROM employee_story_people WHERE city='Dallas'")
-print(result.data)
-```
-
-## 📊 How It Works
-
-### From Unstructured PDF to Structured Tables
-
-**Input:** PDF with employee information
-
-**AI Automatically Creates:**
-```
-📋 Created 3 structured tables:
-  📊 employee_story_people: 20 rows, 6 columns
-     - id, name, address, city, email, phone
-  📊 employee_story_contacts: 20 rows, 4 columns
-     - id, person_id, email, phone  
-  📊 employee_story_events: 15 rows, 4 columns
-     - id, host_id, description, city
-```
-
-## 💡 Usage Examples
-
-### 1. Upload Different Formats
-
-```python
-# CSV file
-sutra.upload("sales_data.csv")
-
-# Excel file
-sutra.upload("quarterly_report.xlsx")
-
-# PDF document (AI extracts entities!)
-sutra.upload("company_directory.pdf")
-
-# Word document
-sutra.upload("meeting_notes.docx")
-
-# Text file
-sutra.upload("log_data.txt")
-
-# DataFrame
-import pandas as pd
-df = pd.DataFrame({'name': ['Alice', 'Bob'], 'score': [95, 87]})
-sutra.upload(df, name="test_scores")
-```
-
-### 2. View Your Data
-
-```python
-# List all tables with details
-sutra.tables()
-
-# Show schema with data types
-sutra.schema()
-
-# Show schema for specific table
-sutra.schema("employee_story_people")
-
-# Preview data
-sutra.peek("employee_story_people", n=10)
-```
-
-### 3. Query Your Data
-
-```python
-# Natural language (uses OpenAI)
-result = sutra.ask("What are the top 5 sales by region?")
-print(result.data)
-
-# With visualization
-result = sutra.ask("Show sales trends by month", viz=True)
-
-# Interactive mode (asks if you want viz)
-result = sutra.interactive("Compare revenue across quarters")
-
-# Direct SQL (free, no API!)
-result = sutra.sql("SELECT city, COUNT(*) as count FROM employee_story_people GROUP BY city")
-print(result.data)
-```
-
-### 4. Export Your Database
-
-```python
-# Export to MySQL (local or cloud)
-sutra.save_to_mysql(
-    host="localhost",
-    user="root",
-    password="password",
-    database="my_database"
-)
-
-# Export to PostgreSQL
-sutra.save_to_postgres(
-    host="mydb.amazonaws.com",
-    user="admin",
-    password="password",
-    database="production_db"
-)
-
-# Export to SQLite file
-sutra.export_db("backup.db", format="sqlite")
-
-# Export to SQL dump
-sutra.export_db("schema.sql", format="sql")
-
-# Export to JSON
-sutra.export_db("data.json", format="json")
-
-# Export to Excel (all tables as sheets)
-sutra.export_db("data.xlsx", format="excel")
-
-# Complete backup
-sutra.backup("./backups")
-```
-
-## 🔥 Advanced Features
-
-### Entity Extraction
-
-QuerySUTRA automatically identifies and extracts:
-
-- 👥 **People** - Names, addresses, contact info
-- 📧 **Contacts** - Emails, phone numbers  
-- 📅 **Events** - Meetings, activities, locations
-- 🏢 **Organizations** - Companies, departments
-- 📍 **Locations** - Cities, addresses, coordinates
-
-### Multiple Table Relationships
-
-```python
-# AI creates relational structure
-sutra.upload("company_data.pdf")
-
-# Result:
-# people table with person_id
-# contacts table with foreign key to person_id
-# events table with host_id linking to people
-```
-
-### Query Across Tables
-
-```python
-# Natural language handles joins automatically
-result = sutra.ask("Show all events hosted by people from Dallas")
-
-# Or write SQL joins manually
-result = sutra.sql("""
-    SELECT e.description, p.name, p.city
-    FROM employee_story_events e
-    JOIN employee_story_people p ON e.host_id = p.id
-    WHERE p.city = 'Dallas'
-""")
-```
-
-## 📈 Visualization
-
-```python
-# Auto-detect best chart type
-result = sutra.ask("Show revenue by product", viz=True)
-
-# Interactive charts with Plotly
-# - Bar charts for categorical data
-# - Line charts for time series  
-# - Tables for detailed data
-# - Pie charts for distributions
-```
-
-## 🌐 Cloud Database Integration
-
-### AWS RDS MySQL
-```python
-sutra.save_to_mysql(
-    host="mydb.xxxx.us-east-1.rds.amazonaws.com",
-    user="admin",
-    password="password",
-    database="production",
-    port=3306
-)
-```
-
-### Google Cloud SQL
-```python
-sutra.save_to_postgres(
-    host="35.123.456.789",
-    user="postgres",
-    password="password",
-    database="analytics"
-)
-```
-
-### Heroku Postgres
-```python
-sutra.save_to_postgres(
-    host="ec2-xx-xxx-xxx-xxx.compute-1.amazonaws.com",
-    user="username",
-    password="password",
-    database="dbname",
-    port=5432
-)
-```
-
-## ⚡ Performance Tips
-
-```python
-# Use direct SQL for complex queries (faster, no API cost)
-result = sutra.sql("SELECT * FROM data WHERE status='active'")
-
-# Cache is automatic for repeated questions
-result1 = sutra.ask("Show total sales")  # Calls API
-result2 = sutra.ask("Show total sales")  # From cache ⚡
-
-# Export results for reuse
-result.data.to_csv("results.csv")
-```
-
-## 🔒 API Key Security
-
-```python
-# Option 1: Pass directly (not recommended for production)
-sutra = SUTRA(api_key="sk-...")
-
-# Option 2: Environment variable (recommended)
-import os
-os.environ["OPENAI_API_KEY"] = "sk-..."
-sutra = SUTRA()
-
-# Option 3: .env file
-# Create .env file with: OPENAI_API_KEY=sk-...
-from dotenv import load_dotenv
-load_dotenv()
-sutra = SUTRA()
-```
-
-## 🎓 Complete Example
-
-```python
-from sutra import SUTRA
-import pandas as pd
-
-# Initialize
-sutra = SUTRA(api_key="your-openai-key")
-
-# Upload PDF - creates multiple tables
-sutra.upload("employee_directory.pdf")
-
-# View what was created
-tables_info = sutra.tables()
-print(f"Created {len(tables_info)} tables")
-
-# View detailed schema
-sutra.schema()
-
-# Query specific table
-result = sutra.ask("How many people are in each city?", 
-                   table="employee_directory_people")
-print(result.data)
-
-# Visualize
-result = sutra.ask("Show distribution of people by city", viz=True)
-
-# Export to MySQL
-sutra.save_to_mysql("localhost", "root", "password", "company_db")
-
-# Backup everything
-sutra.backup("./backups")
-
-# Close connection
-sutra.close()
-```
-
-## 📚 Method Reference
-
-### Core Methods
-
-| Method | Description |
-|--------|-------------|
-| `upload(data, name)` | Upload any data format, creates multiple tables |
-| `tables()` | List all tables with row/column counts |
-| `schema(table)` | Show detailed schema with data types |
-| `peek(table, n)` | Preview first n rows |
-| `ask(question, viz)` | Natural language query |
-| `sql(query, viz)` | Direct SQL query |
-| `interactive(question)` | Query with viz prompt |
-
-### Export Methods
-
-| Method | Description |
-|--------|-------------|
-| `export_db(path, format)` | Export database (sqlite/sql/json/excel) |
-| `save_to_mysql(...)` | Save to MySQL database |
-| `save_to_postgres(...)` | Save to PostgreSQL database |
-| `backup(path)` | Complete backup with timestamp |
-
-## 🐛 Troubleshooting
-
-**Q: Only one table created instead of multiple?**  
-A: Make sure you have OpenAI API key set. Without it, falls back to simple parsing.
-
-**Q: "No API key" error?**  
-A: Set your OpenAI key: `sutra = SUTRA(api_key="sk-...")`
-
-**Q: PDF extraction failed?**  
-A: Install PyPDF2: `pip install PyPDF2`
-
-**Q: MySQL export error?**  
-A: Install extras: `pip install QuerySUTRA[mysql]`
-
-## 📄 License
-
-MIT License - see LICENSE file
-
-## 🤝 Contributing
-
-Contributions welcome! Open an issue or submit a PR.
-
-## 📞 Support
-
-- Issues: [GitHub Issues](https://github.com/yourusername/querysutra/issues)
-- Email: your@email.com
-
----
-
-**Made with ❤️ by Aditya Batta**