doctra 0.1.0__tar.gz → 0.2.0__tar.gz

{doctra-0.1.0/doctra.egg-info → doctra-0.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: doctra
-Version: 0.1.0
+Version: 0.2.0
 Summary: Parse, extract, and analyze documents with ease
 Home-page: https://github.com/AdemBoukhris457/Doctra
 Author: Adem Boukhris
@@ -241,6 +241,8 @@ Provides-Extra: openai
 Requires-Dist: openai>=1.0.0; extra == "openai"
 Provides-Extra: gemini
 Requires-Dist: google-generativeai>=0.3.0; extra == "gemini"
+Provides-Extra: anthropic
+Requires-Dist: anthropic>=0.40.0; extra == "anthropic"
 Provides-Extra: dev
 Requires-Dist: pytest>=6.0; extra == "dev"
 Requires-Dist: pytest-cov>=2.0; extra == "dev"
@@ -256,13 +258,13 @@ Dynamic: requires-python
 
 # 🚀 **Doctra - Document Parser Library** 📑🔎
 
-![Doctra_Logo.png](assets/Doctra_Logo.png)
+![Doctra Logo](https://raw.githubusercontent.com/AdemBoukhris457/Doctra/main/assets/Doctra_Logo.png)
 
 <div align="center">
 
-[![GitHub Stars](https://img.shields.io/github/stars/AdemBoukhris457/Doctra?style=social)](https://github.com/AdemBoukhris457/Doctra/stargazers)
-[![GitHub Forks](https://img.shields.io/github/forks/AdemBoukhris457/Doctra?style=social)](https://github.com/AdemBoukhris457/Doctra/forks)
-
+[![stars](https://img.shields.io/github/stars/AdemBoukhris457/Doctra.svg)](https://github.com/AdemBoukhris457/Doctra)
+[![forks](https://img.shields.io/github/forks/AdemBoukhris457/Doctra.svg)](https://github.com/AdemBoukhris457/Doctra)
+[![PyPI version](https://img.shields.io/pypi/v/doctra)](https://pypi.org/project/doctra/)
 </div>
 
 ## 📋 Table of Contents
@@ -329,7 +331,7 @@ parser = StructuredPDFParser()
 # Parser with VLM for structured data extraction
 parser = StructuredPDFParser(
     use_vlm=True,
-    vlm_provider="openai",  # or "gemini"
+    vlm_provider="openai",  # or "gemini" or "anthropic" or "openrouter"
     vlm_api_key="your_api_key_here"
 )
 
@@ -344,7 +346,7 @@ parser = StructuredPDFParser(
     # VLM Settings
     use_vlm=True,
     vlm_provider="openai",
-    vlm_model="gpt-4o",
+    vlm_model="gpt-5",
     vlm_api_key="your_api_key",
     
     # Layout Detection Settings
@@ -406,7 +408,7 @@ parser = ChartTablePDFParser(
     # VLM Settings
     use_vlm=True,
     vlm_provider="openai",
-    vlm_model="gpt-4o",
+    vlm_model="gpt-5",
     vlm_api_key="your_api_key",
     
     # Layout Detection Settings
@@ -545,7 +547,7 @@ parser = StructuredPDFParser(
     use_vlm=True,
     vlm_provider="openai",
     vlm_api_key="your_openai_api_key",
-    vlm__model="gpt-4o",
+    vlm__model="gpt-5",
     layout_model_name="PP-DocLayout_plus-L",
     dpi=300,  # Higher DPI for better quality
     min_score=0.5,  # Higher confidence threshold
@@ -623,4 +625,4 @@ parser.display_pages_with_boxes("document.pdf")
 - **Pandas**: Data manipulation
 - **OpenPyXL**: Excel file generation
 - **Google Generative AI**: For Gemini VLM integration
-- **OpenAI**: For GPT-4 VLM integration
+- **OpenAI**: For GPT-5 VLM integration