pyrtex 0.1.2__tar.gz

pyrtex-0.1.2/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 CaptainTrojan
+
+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.

pyrtex-0.1.2/PKG-INFO

@@ -0,0 +1,224 @@
+Metadata-Version: 2.4
+Name: pyrtex
+Version: 0.1.2
+Summary: A Python library for batch text extraction and processing using Google Cloud Vertex AI
+Author-email: CaptainTrojan <your-email@example.com>
+License: MIT
+Project-URL: Homepage, https://github.com/CaptainTrojan/pyrtex
+Project-URL: Repository, https://github.com/CaptainTrojan/pyrtex
+Project-URL: Issues, https://github.com/CaptainTrojan/pyrtex/issues
+Project-URL: Documentation, https://github.com/CaptainTrojan/pyrtex#readme
+Project-URL: Changelog, https://github.com/CaptainTrojan/pyrtex/releases
+Keywords: ai,vertex-ai,google-cloud,text-extraction,batch-processing,gemini,pydantic
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pydantic>=2.0.0
+Requires-Dist: pydantic-settings>=2.0.0
+Requires-Dist: jinja2>=3.0.0
+Requires-Dist: google-cloud-aiplatform>=1.40.0
+Requires-Dist: google-cloud-storage>=2.10.0
+Requires-Dist: google-cloud-bigquery>=3.11.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: pytest-mock>=3.10.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
+Requires-Dist: black>=23.0.0; extra == "dev"
+Requires-Dist: isort>=5.12.0; extra == "dev"
+Requires-Dist: flake8>=6.0.0; extra == "dev"
+Requires-Dist: bump2version>=1.0.0; extra == "dev"
+Requires-Dist: build>=0.10.0; extra == "dev"
+Requires-Dist: twine>=4.0.0; extra == "dev"
+Dynamic: license-file
+
+# PyRTex
+
+[![CI](https://github.com/CaptainTrojan/pyrtex/actions/workflows/ci.yml/badge.svg)](https://github.com/CaptainTrojan/pyrtex/actions/workflows/ci.yml)
+[![Python 3.9+](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/downloads/)
+
+A simple Python library for batch text extraction and processing using Google Cloud Vertex AI.
+
+PyRTex makes it easy to process multiple documents, images, or text snippets with Gemini models and get back structured, type-safe results using Pydantic models.
+
+## ✨ Features
+
+- **🚀 Simple API**: Just 3 steps - configure, submit, get results
+- **📦 Batch Processing**: Process multiple inputs efficiently  
+- **🔒 Type Safety**: Pydantic models for structured output
+- **🎨 Flexible Templates**: Jinja2 templates for prompt engineering
+- **☁️ GCP Integration**: Seamless Vertex AI and BigQuery integration
+- **🧪 Testing Mode**: Simulate without GCP costs
+
+## 📦 Installation
+
+Install from PyPI (recommended):
+```bash
+pip install pyrtex
+```
+
+Or install from source:
+```bash
+git clone https://github.com/CaptainTrojan/pyrtex.git
+cd pyrtex
+pip install -e .
+```
+
+For development:
+```bash
+pip install -e .[dev]
+```
+
+## 🚀 Quick Start
+
+```python
+from pydantic import BaseModel
+from pyrtex import Job
+
+# Define your data structures
+class TextInput(BaseModel):
+    content: str
+
+class Analysis(BaseModel):
+    summary: str
+    sentiment: str
+    key_points: list[str]
+
+# Create a job
+job = Job[Analysis](
+    model="gemini-2.0-flash-lite-001",
+    output_schema=Analysis,
+    prompt_template="Analyze this text: {{ content }}",
+    simulation_mode=True  # Set to False for real processing
+)
+
+# Add your data
+job.add_request("doc1", TextInput(content="Your text here"))
+job.add_request("doc2", TextInput(content="Another document"))
+
+# Process and get results
+for result in job.submit().wait().results():
+    if result.was_successful:
+        print(f"Summary: {result.output.summary}")
+        print(f"Sentiment: {result.output.sentiment}")
+    else:
+        print(f"Error: {result.error}")
+```
+
+## 📋 Core Workflow
+
+PyRTex uses a simple 3-step workflow:
+
+### 1. Configure & Add Data
+```python
+job = Job[YourSchema](model="gemini-2.0-flash-lite-001", ...)
+job.add_request("key1", YourModel(data="value1"))
+job.add_request("key2", YourModel(data="value2"))
+```
+
+### 2. Submit & Wait  
+```python
+job.submit().wait()  # Can be chained
+```
+
+### 3. Get Results
+```python
+for result in job.results():
+    if result.was_successful:
+        # Use result.output (typed!)
+    else:
+        # Handle result.error
+```
+
+## ⚙️ Configuration
+
+For production use, set your GCP project:
+
+```bash
+export GOOGLE_PROJECT_ID="your-project-id"
+```
+
+Then use `simulation_mode=False` for real processing.
+
+## 📚 Examples
+
+The `examples/` directory contains complete working examples:
+
+```bash
+cd examples
+
+# Generate sample files
+python generate_sample_data.py
+
+# Extract contact info from business cards
+python 01_simple_text_extraction.py
+
+# Parse product catalogs  
+python 02_pdf_product_parsing.py
+
+# Extract invoice data from PDFs
+python 03_image_description.py
+```
+
+### Example Use Cases
+
+- **📇 Business Cards**: Extract contact information
+- **📄 Documents**: Process PDFs, images (PNG, JPEG)  
+- **🛍️ Product Catalogs**: Parse pricing and inventory
+- **🧾 Invoices**: Extract structured financial data
+- **📊 Batch Processing**: Handle multiple files efficiently
+
+## 🧪 Development
+
+### Running Tests
+
+```bash
+# All tests (mocked, safe)
+./test_runner.sh
+
+# Specific test types
+./test_runner.sh --unit
+./test_runner.sh --integration
+./test_runner.sh --flake
+
+# Real GCP tests (costs money!)
+./test_runner.sh --real --project-id your-project-id
+```
+
+Windows users:
+```cmd
+test_runner.bat --unit
+test_runner.bat --flake
+```
+
+### Code Quality
+
+- **flake8**: Linting
+- **black**: Code formatting  
+- **isort**: Import sorting
+- **pytest**: Testing with coverage
+
+## 🤝 Contributing
+
+1. Fork the repository
+2. Create a feature branch
+3. Make your changes
+4. Run tests: `./test_runner.sh`
+5. Submit a pull request
+
+## 📄 License
+
+MIT License - see [LICENSE](LICENSE) for details.
+
+## 🆘 Support
+
+- **Issues**: [GitHub Issues](https://github.com/CaptainTrojan/pyrtex/issues)
+- **Examples**: Check the `examples/` directory
+- **Testing**: Use `simulation_mode=True` for development

pyrtex-0.1.2/README.md

@@ -0,0 +1,183 @@
+# PyRTex
+
+[![CI](https://github.com/CaptainTrojan/pyrtex/actions/workflows/ci.yml/badge.svg)](https://github.com/CaptainTrojan/pyrtex/actions/workflows/ci.yml)
+[![Python 3.9+](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/downloads/)
+
+A simple Python library for batch text extraction and processing using Google Cloud Vertex AI.
+
+PyRTex makes it easy to process multiple documents, images, or text snippets with Gemini models and get back structured, type-safe results using Pydantic models.
+
+## ✨ Features
+
+- **🚀 Simple API**: Just 3 steps - configure, submit, get results
+- **📦 Batch Processing**: Process multiple inputs efficiently  
+- **🔒 Type Safety**: Pydantic models for structured output
+- **🎨 Flexible Templates**: Jinja2 templates for prompt engineering
+- **☁️ GCP Integration**: Seamless Vertex AI and BigQuery integration
+- **🧪 Testing Mode**: Simulate without GCP costs
+
+## 📦 Installation
+
+Install from PyPI (recommended):
+```bash
+pip install pyrtex
+```
+
+Or install from source:
+```bash
+git clone https://github.com/CaptainTrojan/pyrtex.git
+cd pyrtex
+pip install -e .
+```
+
+For development:
+```bash
+pip install -e .[dev]
+```
+
+## 🚀 Quick Start
+
+```python
+from pydantic import BaseModel
+from pyrtex import Job
+
+# Define your data structures
+class TextInput(BaseModel):
+    content: str
+
+class Analysis(BaseModel):
+    summary: str
+    sentiment: str
+    key_points: list[str]
+
+# Create a job
+job = Job[Analysis](
+    model="gemini-2.0-flash-lite-001",
+    output_schema=Analysis,
+    prompt_template="Analyze this text: {{ content }}",
+    simulation_mode=True  # Set to False for real processing
+)
+
+# Add your data
+job.add_request("doc1", TextInput(content="Your text here"))
+job.add_request("doc2", TextInput(content="Another document"))
+
+# Process and get results
+for result in job.submit().wait().results():
+    if result.was_successful:
+        print(f"Summary: {result.output.summary}")
+        print(f"Sentiment: {result.output.sentiment}")
+    else:
+        print(f"Error: {result.error}")
+```
+
+## 📋 Core Workflow
+
+PyRTex uses a simple 3-step workflow:
+
+### 1. Configure & Add Data
+```python
+job = Job[YourSchema](model="gemini-2.0-flash-lite-001", ...)
+job.add_request("key1", YourModel(data="value1"))
+job.add_request("key2", YourModel(data="value2"))
+```
+
+### 2. Submit & Wait  
+```python
+job.submit().wait()  # Can be chained
+```
+
+### 3. Get Results
+```python
+for result in job.results():
+    if result.was_successful:
+        # Use result.output (typed!)
+    else:
+        # Handle result.error
+```
+
+## ⚙️ Configuration
+
+For production use, set your GCP project:
+
+```bash
+export GOOGLE_PROJECT_ID="your-project-id"
+```
+
+Then use `simulation_mode=False` for real processing.
+
+## 📚 Examples
+
+The `examples/` directory contains complete working examples:
+
+```bash
+cd examples
+
+# Generate sample files
+python generate_sample_data.py
+
+# Extract contact info from business cards
+python 01_simple_text_extraction.py
+
+# Parse product catalogs  
+python 02_pdf_product_parsing.py
+
+# Extract invoice data from PDFs
+python 03_image_description.py
+```
+
+### Example Use Cases
+
+- **📇 Business Cards**: Extract contact information
+- **📄 Documents**: Process PDFs, images (PNG, JPEG)  
+- **🛍️ Product Catalogs**: Parse pricing and inventory
+- **🧾 Invoices**: Extract structured financial data
+- **📊 Batch Processing**: Handle multiple files efficiently
+
+## 🧪 Development
+
+### Running Tests
+
+```bash
+# All tests (mocked, safe)
+./test_runner.sh
+
+# Specific test types
+./test_runner.sh --unit
+./test_runner.sh --integration
+./test_runner.sh --flake
+
+# Real GCP tests (costs money!)
+./test_runner.sh --real --project-id your-project-id
+```
+
+Windows users:
+```cmd
+test_runner.bat --unit
+test_runner.bat --flake
+```
+
+### Code Quality
+
+- **flake8**: Linting
+- **black**: Code formatting  
+- **isort**: Import sorting
+- **pytest**: Testing with coverage
+
+## 🤝 Contributing
+
+1. Fork the repository
+2. Create a feature branch
+3. Make your changes
+4. Run tests: `./test_runner.sh`
+5. Submit a pull request
+
+## 📄 License
+
+MIT License - see [LICENSE](LICENSE) for details.
+
+## 🆘 Support
+
+- **Issues**: [GitHub Issues](https://github.com/CaptainTrojan/pyrtex/issues)
+- **Examples**: Check the `examples/` directory
+- **Testing**: Use `simulation_mode=True` for development

pyrtex-0.1.2/pyproject.toml

@@ -0,0 +1,152 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "pyrtex"
+version = "0.1.2"
+description = "A Python library for batch text extraction and processing using Google Cloud Vertex AI"
+readme = "README.md"
+requires-python = ">=3.9"
+license = {text = "MIT"}
+keywords = ["ai", "vertex-ai", "google-cloud", "text-extraction", "batch-processing", "gemini", "pydantic"]
+authors = [
+    {name = "CaptainTrojan", email = "your-email@example.com"},
+]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+]
+dependencies = [
+    "pydantic>=2.0.0",
+    "pydantic-settings>=2.0.0",
+    "jinja2>=3.0.0",
+    "google-cloud-aiplatform>=1.40.0",
+    "google-cloud-storage>=2.10.0",
+    "google-cloud-bigquery>=3.11.0",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=7.0.0",
+    "pytest-mock>=3.10.0",
+    "pytest-cov>=4.0.0",
+    "black>=23.0.0",
+    "isort>=5.12.0",
+    "flake8>=6.0.0",
+    "bump2version>=1.0.0",
+    "build>=0.10.0",
+    "twine>=4.0.0",
+]
+
+[project.urls]
+Homepage = "https://github.com/CaptainTrojan/pyrtex"
+Repository = "https://github.com/CaptainTrojan/pyrtex"
+Issues = "https://github.com/CaptainTrojan/pyrtex/issues"
+Documentation = "https://github.com/CaptainTrojan/pyrtex#readme"
+Changelog = "https://github.com/CaptainTrojan/pyrtex/releases"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-dir]
+"" = "src"
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+markers = [
+    "incurs_costs: marks tests that will incur small GCP costs",
+    "slow: marks tests that take a long time to run",
+]
+addopts = [
+    "--strict-markers",
+    "--strict-config",
+    "--cov=src/pyrtex",
+    "--cov-report=term-missing",
+    "--cov-report=html",
+]
+filterwarnings = [
+    "ignore::DeprecationWarning",
+    "ignore::PendingDeprecationWarning",
+]
+
+[tool.coverage.run]
+source = ["src/pyrtex"]
+omit = [
+    "*/tests/*",
+    "*/test_*",
+]
+
+[tool.coverage.report]
+exclude_lines = [
+    "pragma: no cover",
+    "def __repr__",
+    "raise AssertionError",
+    "raise NotImplementedError",
+    "if __name__ == .__main__.:",
+    "if TYPE_CHECKING:",
+]
+
+[tool.black]
+line-length = 88
+target-version = ['py38']
+include = '\.pyi?$'
+extend-exclude = '''
+/(
+  # directories
+  \.eggs
+  | \.git
+  | \.hg
+  | \.mypy_cache
+  | \.tox
+  | \.venv
+  | build
+  | dist
+)/
+'''
+
+[tool.flake8]
+max-line-length = 88
+extend-ignore = [
+    "E203",  # whitespace before ':' (conflicts with black)
+    "E501",  # line too long (handled by black)
+    "W503",  # line break before binary operator (conflicts with black)
+]
+exclude = [
+    ".git",
+    "__pycache__",
+    "build",
+    "dist",
+    ".eggs",
+    "*.egg-info",
+    ".venv",
+    ".tox",
+]
+
+[tool.isort]
+profile = "black"
+multi_line_output = 3
+line_length = 88
+known_first_party = ["pyrtex"]
+src_paths = ["src", "tests"]
+
+[tool.mypy]
+python_version = "3.8"
+warn_return_any = true
+warn_unused_configs = true
+disallow_untyped_defs = true
+disallow_incomplete_defs = true
+check_untyped_defs = true
+disallow_untyped_decorators = true
+no_implicit_optional = true
+warn_redundant_casts = true
+warn_unused_ignores = true
+warn_no_return = true
+warn_unreachable = true
+strict_equality = true

pyrtex-0.1.2/setup.cfg

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

pyrtex-0.1.2/src/pyrtex/__init__.py

@@ -0,0 +1,26 @@
+# src/pyrtex/__init__.py
+
+"""
+Pyrtex - A Python library for batch text extraction and processing using
+Google Cloud Vertex AI.
+
+This library provides a simple interface for submitting batch jobs to Google
+Cloud Vertex AI for text extraction, document processing, and structured data
+extraction tasks.
+"""
+
+from .client import Job
+from .config import GenerationConfig, InfrastructureConfig
+from .exceptions import ConfigurationError, JobFailedError
+from .models import BatchResult, T
+
+__version__ = "0.1.2"
+__all__ = [
+    "Job",
+    "InfrastructureConfig",
+    "GenerationConfig",
+    "BatchResult",
+    "T",
+    "ConfigurationError",
+    "JobFailedError",
+]