doctra 0.2.0__tar.gz → 0.3.1__tar.gz

{doctra-0.2.0/doctra.egg-info → doctra-0.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: doctra
-Version: 0.2.0
+Version: 0.3.1
 Summary: Parse, extract, and analyze documents with ease
 Home-page: https://github.com/AdemBoukhris457/Doctra
 Author: Adem Boukhris
@@ -234,6 +234,9 @@ Requires-Dist: opencv-python>=4.5.0
 Requires-Dist: pandas>=1.3.0
 Requires-Dist: openpyxl>=3.0.0
 Requires-Dist: tesseract>=0.1.3
+Requires-Dist: pytesseract>=0.3.10
+Requires-Dist: pdf2image>=1.16.0
+Requires-Dist: anthropic>=0.40.0
 Requires-Dist: outlines>=0.0.34
 Requires-Dist: tqdm>=4.62.0
 Requires-Dist: matplotlib>=3.5.0
@@ -241,8 +244,6 @@ 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"
@@ -295,6 +296,31 @@ cd Doctra
 pip install .
 ```
 
+### System Dependencies
+
+Doctra requires **Poppler** for PDF processing. Install it based on your operating system:
+
+#### Ubuntu/Debian
+```bash
+sudo apt install poppler-utils
+```
+
+#### macOS
+```bash
+brew install poppler
+```
+
+#### Windows
+Download and install from [Poppler for Windows](http://blog.alivate.com.au/poppler-windows/) or use conda:
+```bash
+conda install -c conda-forge poppler
+```
+
+#### Google Colab
+```bash
+!sudo apt install poppler-utils
+```
+
 ## ⚡ Quick Start
 
 ```python
@@ -626,3 +652,40 @@ parser.display_pages_with_boxes("document.pdf")
 - **OpenPyXL**: Excel file generation
 - **Google Generative AI**: For Gemini VLM integration
 - **OpenAI**: For GPT-5 VLM integration
+
+## 🖥️ Web Interface (Gradio)
+
+You can try Doctra in a simple web UI powered by Gradio.
+
+### Run locally
+
+```bash
+pip install -U gradio
+python gradio_app.py
+```
+
+Then open the printed URL (default `http://127.0.0.1:7860`).
+
+Notes:
+- If using VLM, set the API key field in the UI or export `VLM_API_KEY`.
+- Outputs are saved under `outputs/<pdf_stem>/` and previewed in the UI.
+
+### Deploy on Hugging Face Spaces
+
+1) Create a new Space (type: Gradio, SDK: Python).
+
+2) Add these files to the Space repo:
+   - Your package code (or install from PyPI).
+   - `gradio_app.py` (entry point).
+   - `requirements.txt` with at least:
+
+```text
+doctra
+gradio
+```
+
+3) Set a secret named `VLM_API_KEY` if you want VLM features.
+
+4) In Space settings, set `python gradio_app.py` as the run command (or rely on auto-detect).
+
+The Space will build and expose the same interface for uploads and processing.