docker fix

.huggingface.yml

@@ -1,3 +1,11 @@
+title: Agriscience
+emoji: 🌍
+colorFrom: green
+colorTo: blue
 sdk: gradio
 sdk_version: 5.38.0
-app_file: app.py
+app_file: app.py
+base: docker
+pinned: false
+license: mit
+short_description: This space is for the contract review project

Dockerfile

@@ -0,0 +1,35 @@
+FROM python:3.10-slim
+
+# Set environment variables
+ENV PYTHONUNBUFFERED=1
+ENV DEBIAN_FRONTEND=noninteractive
+
+# Install system dependencies (avoiding problematic packages)
+RUN apt-get update && apt-get install -y \
+    tesseract-ocr-all \
+    poppler-utils \
+    git \
+    wget \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create user for Hugging Face Spaces
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+
+# Set working directory
+WORKDIR $HOME/app
+
+# Copy requirements and install Python dependencies
+COPY --chown=user requirements.txt .
+RUN pip install --no-cache-dir --user -r requirements.txt
+
+# Copy application files
+COPY --chown=user . .
+
+# Expose port for Gradio
+EXPOSE 7860
+
+# Run the application
+CMD ["python", "app.py"]

README.md

@@ -1,14 +1,62 @@
----
-title: Agriscience
-emoji: 🌍
-colorFrom: green
-colorTo: blue
-sdk: docker
-sdk_version: 5.42.0
-app_file: app.py
-pinned: false
-license: mit
-short_description: This space is for the contract review project
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Agriscience Contract Auditor
+
+## 🎯 Overview
+A Gradio-based web application that audits employment contracts against labor laws from different countries using AI-powered analysis through Flowise.
+
+## 🔧 Features
+- **Multi-format support**: PDF, DOCX, TXT files
+- **Multilingual processing**: English and Arabic text extraction
+- **OCR capabilities**: Advanced Arabic PDF processing using Tesseract
+- **Country-specific analysis**: USA, Germany, UAE, Turkey, Jordan
+- **AI-powered auditing**: Connected to Flowise for intelligent contract analysis
+
+## 🚀 Deployment
+
+### Hugging Face Spaces
+This application is configured for deployment on Hugging Face Spaces using Docker.
+
+**Files:**
+- `Dockerfile`: Custom Docker configuration avoiding problematic system packages
+- `.huggingface.yml`: Hugging Face Spaces configuration
+- `requirements.txt`: Python dependencies
+- `packages.txt`: System packages (Tesseract OCR, Poppler)
+- `app.py`: Main Gradio application
+
+### Local Development
+```bash
+# Install system dependencies (Ubuntu/Debian)
+sudo apt-get update
+sudo apt-get install tesseract-ocr-all poppler-utils
+
+# Install Python dependencies
+pip install -r requirements.txt
+
+# Run the application
+python app.py
+```
+
+## 🔍 Technical Details
+
+### Dependencies
+- **Gradio**: Web interface framework
+- **multilingual-pdf2text**: Advanced PDF text extraction
+- **pdfplumber**: Standard PDF processing
+- **pytesseract**: OCR engine integration
+- **langdetect**: Language detection for smart processing
+
+### Architecture
+1. **File Upload**: Supports multiple formats
+2. **Text Extraction**: Smart extraction based on language detection
+3. **AI Analysis**: Sends extracted text to Flowise API
+4. **Results Display**: Formatted audit results in selected language
+
+## 🛠️ Configuration
+- **Flowise URL**: Configured for SIRA Flow application
+- **Supported Countries**: USA, Germany, UAE, Turkey, Jordan
+- **Response Languages**: English, Arabic
+
+## 📝 Usage
+1. Select target country for labor law compliance
+2. Choose response language (English/Arabic)
+3. Upload contract file (PDF/DOCX/TXT)
+4. Click "Audit Contract" to get AI-powered analysis

app.py

@@ -140,4 +140,9 @@ with gr.Blocks(title="Contract Auditor") as demo:
         outputs=output
     )
 
-demo.launch()
+if __name__ == "__main__":
+    demo.launch(
+        server_name="0.0.0.0",
+        server_port=7860,
+        show_error=True
+    )

requirements.txt

@@ -3,4 +3,5 @@ requests
 pdfplumber
 docx2txt
 langdetect
-pytesseract
+multilingual-pdf2text
+pytesseract