structx 0.4.8__tar.gz

structx-0.4.8/LICENSE

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

structx-0.4.8/PKG-INFO

@@ -0,0 +1,313 @@
+Metadata-Version: 2.4
+Name: structx
+Version: 0.4.8
+Summary: Structured data extraction from text using LLMs and dynamic model generation
+Author-email: blacksuan19 <py@blacksuan19.dev>
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Framework :: AsyncIO
+Classifier: Framework :: Pydantic
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Database
+Classifier: Topic :: Documentation
+Classifier: Topic :: Internet :: WWW/HTTP :: Dynamic Content
+Classifier: Topic :: Office/Business
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Software Development :: Libraries
+Classifier: Topic :: Text Processing :: Linguistic
+Classifier: Topic :: Text Processing :: Markup
+Classifier: Topic :: Text Processing
+Classifier: Topic :: Utilities
+Classifier: Typing :: Typed
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: instructor
+Requires-Dist: litellm
+Requires-Dist: loguru
+Requires-Dist: omegaconf
+Requires-Dist: openpyxl>=3.1.5
+Requires-Dist: pandas
+Requires-Dist: pydantic
+Requires-Dist: tabulate>=0.9.0
+Requires-Dist: tenacity
+Requires-Dist: tqdm
+Provides-Extra: dev
+Requires-Dist: black; extra == "dev"
+Requires-Dist: bumpver; extra == "dev"
+Requires-Dist: pip-tools; extra == "dev"
+Requires-Dist: wheel; extra == "dev"
+Provides-Extra: pdf
+Requires-Dist: pypdf2; extra == "pdf"
+Requires-Dist: instructor[multimodal]; extra == "pdf"
+Requires-Dist: weasyprint; extra == "pdf"
+Requires-Dist: markdown; extra == "pdf"
+Provides-Extra: docx
+Requires-Dist: python-docx; extra == "docx"
+Requires-Dist: docling; extra == "docx"
+Requires-Dist: markdown; extra == "docx"
+Requires-Dist: weasyprint; extra == "docx"
+Provides-Extra: docs
+Requires-Dist: pypdf2; extra == "docs"
+Requires-Dist: python-docx; extra == "docs"
+Requires-Dist: instructor[multimodal]; extra == "docs"
+Requires-Dist: docling; extra == "docs"
+Requires-Dist: weasyprint; extra == "docs"
+Requires-Dist: markdown; extra == "docs"
+Provides-Extra: unstructured
+Requires-Dist: unstructured[all-docs]; extra == "unstructured"
+Provides-Extra: docling
+Requires-Dist: docling; extra == "docling"
+Requires-Dist: markdown; extra == "docling"
+Requires-Dist: weasyprint; extra == "docling"
+Provides-Extra: advanced
+Requires-Dist: pypdf2; extra == "advanced"
+Requires-Dist: python-docx; extra == "advanced"
+Requires-Dist: instructor[multimodal]; extra == "advanced"
+Requires-Dist: docling; extra == "advanced"
+Requires-Dist: weasyprint; extra == "advanced"
+Requires-Dist: markdown; extra == "advanced"
+Requires-Dist: unstructured[all-docs]; extra == "advanced"
+Provides-Extra: mkdocs
+Requires-Dist: mkdocs; extra == "mkdocs"
+Requires-Dist: mkdocs-material; extra == "mkdocs"
+Requires-Dist: mkdocstrings[markdown]; extra == "mkdocs"
+Requires-Dist: mkdocstrings[python]; extra == "mkdocs"
+Requires-Dist: mkdocs-git-revision-date-localized-plugin; extra == "mkdocs"
+Requires-Dist: mkdocs-material[imaging]; extra == "mkdocs"
+Requires-Dist: mkdocs-mermaid2-plugin; extra == "mkdocs"
+Dynamic: license-file
+
+# structx
+
+Advanced structured data extraction from any document using LLMs with multimodal
+support.
+
+[![Documentation](https://img.shields.io/badge/docs-mkdocs-blue.svg?style=for-the-badge)](https://structx.blacksuan19.dev "Documentation")
+[![PyPI](https://img.shields.io/badge/PyPi-0.4.8-blue?style=for-the-badge)](https://pypi.org/project/structx "Package")
+[![GitHub Actions](https://img.shields.io/badge/github%20actions-%232671E5.svg?style=for-the-badge&logo=githubactions&logoColor=white)](# "Build with GitHub Actions")
+
+`structx` is a powerful Python library for extracting structured data from any
+document or text using Large Language Models (LLMs). It features an innovative
+multimodal PDF processing pipeline that converts any document to PDF and uses
+instructor's vision capabilities for superior extraction quality.
+
+## 🔔 Package rename notice (PyPI)
+
+The PyPI distribution has been renamed from `structx-llm` to `structx`
+(September 2025).
+
+- Imports are unchanged: continue using `import structx`
+- Extras are unchanged: `structx[docs]`, `structx[pdf]`, `structx[docx]`
+- Please update your environments and requirement files to use the new name
+
+Upgrade commands:
+
+```bash
+pip uninstall -y structx-llm
+pip install -U structx
+```
+
+If you previously pinned `structx-llm` in requirements or lock files, replace it
+with `structx`.
+
+## ✨ Key Features
+
+### 🎯 **Advanced Document Processing**
+
+- **� Multimodal PDF Pipeline**: Converts any document (TXT, DOCX, etc.) to PDF
+  for optimal extraction
+- **🖼️ Vision-Enabled Extraction**: Native instructor multimodal support for
+  PDFs and images
+- **🔄 Smart Format Detection**: Automatic processing mode selection for best
+  results
+- **📊 Universal File Support**: CSV, Excel, JSON, Parquet, PDF, DOCX, TXT,
+  Markdown, and more
+
+### 🚀 **Intelligent Data Extraction**
+
+- **🔄 Dynamic Model Generation**: Create type-safe Pydantic models from natural
+  language queries
+- **🎯 Automatic Schema Inference**: Intelligent schema generation and
+  refinement
+- **📊 Complex Data Structures**: Support for nested and hierarchical data
+- **🔄 Natural Language Refinement**: Improve models with conversational
+  instructions
+
+### ⚡ **Performance & Reliability**
+
+- **🚀 High-Performance Processing**: Multi-threaded and async operations
+- **🔄 Robust Error Handling**: Automatic retry mechanism with exponential
+  backoff
+- **📈 Token Usage Tracking**: Detailed step-by-step metrics for cost monitoring
+- **� Flexible Configuration**: Configurable extraction using OmegaConf
+- **🔌 Multiple LLM Providers**: Support through litellm integration
+
+## Installation
+
+```bash
+# Core package with basic extraction capabilities
+pip install structx
+```
+
+### 📄 Enhanced Document Processing (Recommended)
+
+For the best experience with all document types including advanced multimodal
+PDF processing:
+
+```bash
+# Complete document processing support
+pip install structx[docs]
+
+# Individual components
+pip install structx[pdf]   # PDF processing with multimodal support
+pip install structx[docx]  # Advanced DOCX conversion via docling
+```
+
+### 🔧 What Each Extra Provides
+
+- **`[docs]`**: Complete multimodal document processing pipeline
+  - PDF conversion from any document type
+  - Instructor multimodal vision support
+  - Advanced DOCX processing via docling
+  - Enhanced extraction quality
+- **`[pdf]`**: PDF-specific processing
+
+  - Multimodal PDF support via instructor
+  - PDF generation capabilities
+  - Basic PDF text extraction fallback
+
+- **`[docx]`**: Advanced DOCX support
+  - Document conversion via docling
+  - Structure preservation
+  - Markdown-based processing pipeline
+
+## Quick Start
+
+### Basic Text Extraction
+
+```python
+from structx import Extractor
+
+# Initialize extractor
+extractor = Extractor.from_litellm(
+    model="gpt-4o",
+    api_key="your-api-key",
+    max_retries=3,      # Automatically retry on transient errors
+    min_wait=1,         # Start with 1 second wait
+    max_wait=10         # Maximum 10 seconds between retries
+)
+
+# Extract from text
+result = extractor.extract(
+    data="System check on 2024-01-15 detected high CPU usage (92%) on server-01.",
+    query="extract incident date and details"
+)
+
+# Access results
+print(f"Extracted {result.success_count} items")
+print(result.data[0].model_dump_json(indent=2))
+```
+
+### 📄 Document Processing with Multimodal Support
+
+```python
+# Process a PDF invoice directly with vision capabilities
+result = extractor.extract(
+    data="scripts/example_input/S0305SampleInvoice.pdf",      # Direct multimodal processing
+    query="extract the invoice number, total amount, and line items"
+)
+
+# Convert a DOCX contract and process with multimodal support
+result = extractor.extract(
+    data="scripts/example_input/free-consultancy-agreement.docx", # Auto-converted to PDF -> multimodal
+    query="extract parties, effective date, and payment terms"
+)
+```
+
+### 📊 Token Usage Monitoring
+
+```python
+# Check token usage for cost monitoring
+usage = result.get_token_usage()
+if usage:
+    print(f"Total tokens: {usage.total_tokens}")
+    print(f"By step: {[(s.name, s.tokens) for s in usage.steps]}")
+```
+
+## 🚀 Why Multimodal PDF Processing?
+
+The innovative multimodal approach provides significant advantages over
+traditional text-based extraction:
+
+- **📄 Context Preservation**: Full document layout and structure are maintained
+- **🎯 Higher Accuracy**: Vision models can interpret tables, charts, and
+  complex layouts
+- **🔄 No Chunking Issues**: Eliminates problems with information split across
+  chunks
+- **📊 Universal Format**: Any document type becomes processable through PDF
+  conversion
+- **🖼️ Visual Understanding**: Handles documents with visual elements,
+  formatting, and structure
+
+## 📚 Documentation
+
+For comprehensive documentation, examples, and guides, visit our
+[documentation site](https://structx.blacksuan19.dev).
+
+- [Getting Started](https://structx.blacksuan19.dev/getting-started)
+- [Basic Extraction](https://structx.blacksuan19.dev/guides/basic-extraction)
+- [Unstructured Text Processing](https://structx.blacksuan19.dev/guides/unstructured-text)
+- [Async Operations](https://structx.blacksuan19.dev/guides/async-operations)
+- [Multiple Queries](https://structx.blacksuan19.dev/guides/multiple-queries)
+- [Custom Models](https://structx.blacksuan19.dev/guides/custom-models)
+- [Token Usage Tracking](https://structx.blacksuan19.dev/guides/token-tracking)
+- [API Reference](https://structx.blacksuan19.dev/api/extractor)
+
+## Examples
+
+Check out our [example gallery](https://structx.blacksuan19.dev/examples) for
+real-world use cases,
+
+## 📁 Supported File Formats
+
+### 📊 Structured Data (Direct Processing)
+
+- **CSV**: Comma-separated values with custom delimiters
+- **Excel**: .xlsx/.xls with sheet selection and custom options
+- **JSON**: JavaScript Object Notation with nested support
+- **Parquet**: Columnar storage format for large datasets
+- **Feather**: Fast binary format for data frames
+
+### 📄 Unstructured Documents (Multimodal Pipeline)
+
+| Format   | Extensions                                    | Processing Method                     | Quality    |
+| -------- | --------------------------------------------- | ------------------------------------- | ---------- |
+| **PDF**  | `.pdf`                                        | Direct multimodal processing          | ⭐⭐⭐⭐⭐ |
+| **Word** | `.docx`, `.doc`                               | Docling → Markdown → PDF → Multimodal | ⭐⭐⭐⭐⭐ |
+| **Text** | `.txt`, `.md`, `.py`, `.log`, `.xml`, `.html` | Styled PDF → Multimodal               | ⭐⭐⭐⭐   |
+
+### 🔄 Processing Modes
+
+- **Multimodal PDF** (default): Best quality, preserves layout and context
+- **Simple Text**: Fallback mode with chunking for memory-constrained
+  environments
+- **Simple PDF**: Basic PDF text extraction without vision capabilities
+
+## Contributing
+
+Contributions are welcome! Please read our
+[Contributing Guidelines](https://structx.blacksuan19.dev/contributing) for
+details.
+
+## License
+
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file
+for details.

structx-0.4.8/README.md

@@ -0,0 +1,226 @@
+# structx
+
+Advanced structured data extraction from any document using LLMs with multimodal
+support.
+
+[![Documentation](https://img.shields.io/badge/docs-mkdocs-blue.svg?style=for-the-badge)](https://structx.blacksuan19.dev "Documentation")
+[![PyPI](https://img.shields.io/badge/PyPi-0.4.8-blue?style=for-the-badge)](https://pypi.org/project/structx "Package")
+[![GitHub Actions](https://img.shields.io/badge/github%20actions-%232671E5.svg?style=for-the-badge&logo=githubactions&logoColor=white)](# "Build with GitHub Actions")
+
+`structx` is a powerful Python library for extracting structured data from any
+document or text using Large Language Models (LLMs). It features an innovative
+multimodal PDF processing pipeline that converts any document to PDF and uses
+instructor's vision capabilities for superior extraction quality.
+
+## 🔔 Package rename notice (PyPI)
+
+The PyPI distribution has been renamed from `structx-llm` to `structx`
+(September 2025).
+
+- Imports are unchanged: continue using `import structx`
+- Extras are unchanged: `structx[docs]`, `structx[pdf]`, `structx[docx]`
+- Please update your environments and requirement files to use the new name
+
+Upgrade commands:
+
+```bash
+pip uninstall -y structx-llm
+pip install -U structx
+```
+
+If you previously pinned `structx-llm` in requirements or lock files, replace it
+with `structx`.
+
+## ✨ Key Features
+
+### 🎯 **Advanced Document Processing**
+
+- **� Multimodal PDF Pipeline**: Converts any document (TXT, DOCX, etc.) to PDF
+  for optimal extraction
+- **🖼️ Vision-Enabled Extraction**: Native instructor multimodal support for
+  PDFs and images
+- **🔄 Smart Format Detection**: Automatic processing mode selection for best
+  results
+- **📊 Universal File Support**: CSV, Excel, JSON, Parquet, PDF, DOCX, TXT,
+  Markdown, and more
+
+### 🚀 **Intelligent Data Extraction**
+
+- **🔄 Dynamic Model Generation**: Create type-safe Pydantic models from natural
+  language queries
+- **🎯 Automatic Schema Inference**: Intelligent schema generation and
+  refinement
+- **📊 Complex Data Structures**: Support for nested and hierarchical data
+- **🔄 Natural Language Refinement**: Improve models with conversational
+  instructions
+
+### ⚡ **Performance & Reliability**
+
+- **🚀 High-Performance Processing**: Multi-threaded and async operations
+- **🔄 Robust Error Handling**: Automatic retry mechanism with exponential
+  backoff
+- **📈 Token Usage Tracking**: Detailed step-by-step metrics for cost monitoring
+- **� Flexible Configuration**: Configurable extraction using OmegaConf
+- **🔌 Multiple LLM Providers**: Support through litellm integration
+
+## Installation
+
+```bash
+# Core package with basic extraction capabilities
+pip install structx
+```
+
+### 📄 Enhanced Document Processing (Recommended)
+
+For the best experience with all document types including advanced multimodal
+PDF processing:
+
+```bash
+# Complete document processing support
+pip install structx[docs]
+
+# Individual components
+pip install structx[pdf]   # PDF processing with multimodal support
+pip install structx[docx]  # Advanced DOCX conversion via docling
+```
+
+### 🔧 What Each Extra Provides
+
+- **`[docs]`**: Complete multimodal document processing pipeline
+  - PDF conversion from any document type
+  - Instructor multimodal vision support
+  - Advanced DOCX processing via docling
+  - Enhanced extraction quality
+- **`[pdf]`**: PDF-specific processing
+
+  - Multimodal PDF support via instructor
+  - PDF generation capabilities
+  - Basic PDF text extraction fallback
+
+- **`[docx]`**: Advanced DOCX support
+  - Document conversion via docling
+  - Structure preservation
+  - Markdown-based processing pipeline
+
+## Quick Start
+
+### Basic Text Extraction
+
+```python
+from structx import Extractor
+
+# Initialize extractor
+extractor = Extractor.from_litellm(
+    model="gpt-4o",
+    api_key="your-api-key",
+    max_retries=3,      # Automatically retry on transient errors
+    min_wait=1,         # Start with 1 second wait
+    max_wait=10         # Maximum 10 seconds between retries
+)
+
+# Extract from text
+result = extractor.extract(
+    data="System check on 2024-01-15 detected high CPU usage (92%) on server-01.",
+    query="extract incident date and details"
+)
+
+# Access results
+print(f"Extracted {result.success_count} items")
+print(result.data[0].model_dump_json(indent=2))
+```
+
+### 📄 Document Processing with Multimodal Support
+
+```python
+# Process a PDF invoice directly with vision capabilities
+result = extractor.extract(
+    data="scripts/example_input/S0305SampleInvoice.pdf",      # Direct multimodal processing
+    query="extract the invoice number, total amount, and line items"
+)
+
+# Convert a DOCX contract and process with multimodal support
+result = extractor.extract(
+    data="scripts/example_input/free-consultancy-agreement.docx", # Auto-converted to PDF -> multimodal
+    query="extract parties, effective date, and payment terms"
+)
+```
+
+### 📊 Token Usage Monitoring
+
+```python
+# Check token usage for cost monitoring
+usage = result.get_token_usage()
+if usage:
+    print(f"Total tokens: {usage.total_tokens}")
+    print(f"By step: {[(s.name, s.tokens) for s in usage.steps]}")
+```
+
+## 🚀 Why Multimodal PDF Processing?
+
+The innovative multimodal approach provides significant advantages over
+traditional text-based extraction:
+
+- **📄 Context Preservation**: Full document layout and structure are maintained
+- **🎯 Higher Accuracy**: Vision models can interpret tables, charts, and
+  complex layouts
+- **🔄 No Chunking Issues**: Eliminates problems with information split across
+  chunks
+- **📊 Universal Format**: Any document type becomes processable through PDF
+  conversion
+- **🖼️ Visual Understanding**: Handles documents with visual elements,
+  formatting, and structure
+
+## 📚 Documentation
+
+For comprehensive documentation, examples, and guides, visit our
+[documentation site](https://structx.blacksuan19.dev).
+
+- [Getting Started](https://structx.blacksuan19.dev/getting-started)
+- [Basic Extraction](https://structx.blacksuan19.dev/guides/basic-extraction)
+- [Unstructured Text Processing](https://structx.blacksuan19.dev/guides/unstructured-text)
+- [Async Operations](https://structx.blacksuan19.dev/guides/async-operations)
+- [Multiple Queries](https://structx.blacksuan19.dev/guides/multiple-queries)
+- [Custom Models](https://structx.blacksuan19.dev/guides/custom-models)
+- [Token Usage Tracking](https://structx.blacksuan19.dev/guides/token-tracking)
+- [API Reference](https://structx.blacksuan19.dev/api/extractor)
+
+## Examples
+
+Check out our [example gallery](https://structx.blacksuan19.dev/examples) for
+real-world use cases,
+
+## 📁 Supported File Formats
+
+### 📊 Structured Data (Direct Processing)
+
+- **CSV**: Comma-separated values with custom delimiters
+- **Excel**: .xlsx/.xls with sheet selection and custom options
+- **JSON**: JavaScript Object Notation with nested support
+- **Parquet**: Columnar storage format for large datasets
+- **Feather**: Fast binary format for data frames
+
+### 📄 Unstructured Documents (Multimodal Pipeline)
+
+| Format   | Extensions                                    | Processing Method                     | Quality    |
+| -------- | --------------------------------------------- | ------------------------------------- | ---------- |
+| **PDF**  | `.pdf`                                        | Direct multimodal processing          | ⭐⭐⭐⭐⭐ |
+| **Word** | `.docx`, `.doc`                               | Docling → Markdown → PDF → Multimodal | ⭐⭐⭐⭐⭐ |
+| **Text** | `.txt`, `.md`, `.py`, `.log`, `.xml`, `.html` | Styled PDF → Multimodal               | ⭐⭐⭐⭐   |
+
+### 🔄 Processing Modes
+
+- **Multimodal PDF** (default): Best quality, preserves layout and context
+- **Simple Text**: Fallback mode with chunking for memory-constrained
+  environments
+- **Simple PDF**: Basic PDF text extraction without vision capabilities
+
+## Contributing
+
+Contributions are welcome! Please read our
+[Contributing Guidelines](https://structx.blacksuan19.dev/contributing) for
+details.
+
+## License
+
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file
+for details.

structx-0.4.8/pyproject.toml

@@ -0,0 +1,112 @@
+[build-system]
+requires = ["setuptools>=45", "wheel", "pip>=21.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "structx"
+version = "0.4.8"
+description = "Structured data extraction from text using LLMs and dynamic model generation"
+authors = [{ name = "blacksuan19", email = "py@blacksuan19.dev" }]
+license-files = ["LICENSE"]
+readme = "README.md"
+requires-python = ">=3.10"
+classifiers = [
+    "Development Status :: 5 - Production/Stable",
+    "Framework :: AsyncIO",
+    "Framework :: Pydantic",
+    "Intended Audience :: Developers",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3",
+    "Topic :: Database",
+    "Topic :: Documentation",
+    "Topic :: Internet :: WWW/HTTP :: Dynamic Content",
+    "Topic :: Office/Business",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Scientific/Engineering :: Information Analysis",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+    "Topic :: Software Development :: Libraries",
+    "Topic :: Text Processing :: Linguistic",
+    "Topic :: Text Processing :: Markup",
+    "Topic :: Text Processing",
+    "Topic :: Utilities",
+    "Typing :: Typed",
+]
+
+dependencies = [
+    "instructor",
+    "litellm",
+    "loguru",
+    "omegaconf",
+    "openpyxl>=3.1.5",
+    "pandas",
+    "pydantic",
+    "tabulate>=0.9.0", # required for pandas .to_markdown()
+    "tenacity",
+    "tqdm",
+]
+
+[project.optional-dependencies]
+dev = ["black", "bumpver", "pip-tools", "wheel"]
+pdf = [
+    "pypdf2",                 # PDF text extraction fallback
+    "instructor[multimodal]", # Multimodal PDF processing
+    "weasyprint",             # PDF generation from HTML/markdown
+    "markdown",               # Markdown processing for conversion
+]
+docx = [
+    "python-docx", # Basic DOCX support 
+    "docling",     # Advanced DOCX conversion via docling
+    "markdown",    # Markdown processing
+    "weasyprint",  # PDF generation
+]
+docs = [
+    "pypdf2",                 # PDF text extraction
+    "python-docx",            # DOCX support
+    "instructor[multimodal]", # Multimodal processing
+    "docling",                # Advanced document conversion
+    "weasyprint",             # PDF generation from HTML/markdown
+    "markdown",               # Markdown processing and extensions
+]
+# Legacy support - kept for backward compatibility
+unstructured = ["unstructured[all-docs]"]
+docling = ["docling", "markdown", "weasyprint"]
+advanced = [
+    "pypdf2",
+    "python-docx",
+    "instructor[multimodal]",
+    "docling",
+    "weasyprint",
+    "markdown",
+    "unstructured[all-docs]",
+]
+mkdocs = [
+    "mkdocs",
+    "mkdocs-material",
+    "mkdocstrings[markdown]",
+    "mkdocstrings[python]",
+    "mkdocs-git-revision-date-localized-plugin",
+    "mkdocs-material[imaging]",
+    "mkdocs-mermaid2-plugin",
+]
+
+[tool.bumpver]
+current_version = "0.4.8"
+version_pattern = "MAJOR.MINOR.PATCH"
+commit_message = "Bump version {old_version} -> {new_version}"
+commit = true
+tag = true
+push = true
+
+
+[tool.bumpver.file_patterns]
+"pyproject.toml" = ['current_version = "{version}"', 'version = "{version}"']
+"structx/__init__.py" = ['__version__ = "{version}"']
+"README.md" = ["PyPi-{version}"]
+
+[tool.setuptools.packages.find]
+# Only package the library code under structx; exclude MkDocs overrides and others
+include = ["structx*"]

structx-0.4.8/setup.cfg

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