Jerry/refactor (#2)

* cr

* cr

* cr

* cr

---------

Co-authored-by: Jerry Liu <jerryjliu98@gmail.com>

README.md

@@ -1,7 +1,15 @@
-# Invoice Processing App - Vibe Coding Example
+# Invoice Processing App - Vibe Coding a Web App
 
 This repository demonstrates how to "vibe code" a full-stack invoice processing application using Cursor/Claude Code from a simple starting file. This showcases building a complete Streamlit application with LlamaCloud's document extraction capabilities.
 
+## 🎯 What This Repository Is Capable Of
+
+This repository provides a complete end-to-end solution for building intelligent document processing applications:
+
+1. **Vibe Coding Templates to Create Full Web Applications**: Provides comprehensive prompts that can be used alongside coding assistants like cursor to one-shot transform simple scripts into production web applications
+2. **LlamaCloud Integration**: Automatically creates and configures LlamaExtract extraction agents using predefined Pydantic schemas for structured data extraction
+7. **Sample scripts**: Sample scripts that can be used as context for coding assistants while generating new streamlit apps!
+
 ## 🚀 Quick Start - Vibe Coding Your Own App
 
 This repository demonstrates **vibe coding** - rapidly building applications through iterative AI-assisted development. The goal is to transform a simple script into a full-featured application using Cursor/Claude Code.
@@ -120,7 +128,7 @@ Try the full prompt first - you might be surprised how much gets built in a sing
 ## 🔧 Features
 
 ### Current Application (`app.py`)
-- 📄 **Multi-format Support**: PDF, Word documents (.docx), images (JPG, PNG, etc.), and other common document formats
+- 📄 **Multi-format Support**: JPG, JPEG, PNG, BMP, TIFF
 - 🎨 **Professional UI**: Custom CSS styling and responsive design
 - 📊 **Data Visualization**: Structured invoice data display
 - 📈 **Analytics**: Processing metrics and status tracking
@@ -139,7 +147,7 @@ See `sample_data/sample_schema.py` for the complete Pydantic model definitions.
 
 ## 📝 Usage
 
-1. **Upload Invoice**: Drag and drop or select an invoice document (PDF, Word, or image)
+1. **Upload Invoice**: Drag and drop or select an invoice image
 2. **Extract Data**: Click the extraction button to process with LlamaCloud
 3. **View Results**: See structured data in formatted tables and JSON
 4. **Track History**: View processed invoices in the history tab
@@ -158,8 +166,8 @@ agent_name = "your-agent-name"
 ### Common Issues
 - **API Key**: Ensure your LlamaCloud API key is valid and in `.env`
 - **Dependencies**: Run `pip install -r requirements.txt`
-- **File Formats**: Supports PDF, Word documents, images, and other common document formats
-- **File Size**: Keep documents under 10MB for best performance
+- **File Formats**: Only image formats are supported
+- **File Size**: Keep images under 10MB for best performance
 
 ## 🤝 Contributing
 

sample.py

@@ -20,11 +20,11 @@ PROJECT_ID = os.getenv("LLAMA_CLOUD_PROJECT_ID", "your-project-id-here")
 ORGANIZATION_ID = os.getenv("LLAMA_CLOUD_ORGANIZATION_ID", "your-organization-id-here")
 AGENT_NAME = os.getenv("LLAMA_CLOUD_AGENT_NAME", "your-agent-name-here")
 
-# Sample document path
-SAMPLE_DOCUMENT = "sample_data/batch1-0274.jpg"
+# Sample image path
+SAMPLE_IMAGE = "sample_data/batch1-0274.jpg"
 
 def main():
-    """Run invoice extraction on sample document."""
+    """Run invoice extraction on sample image."""
     
     # Validate configuration
     if PROJECT_ID == "your-project-id-here" or ORGANIZATION_ID == "your-organization-id-here":
@@ -50,9 +50,9 @@ def main():
         agent = extract.get_agent(name=AGENT_NAME)
         print(f"✅ Successfully connected to agent: {AGENT_NAME}")
         
-        # Run extraction on sample document
-        print(f"📄 Processing sample invoice: {SAMPLE_DOCUMENT}")
-        result = agent.extract(SAMPLE_DOCUMENT)
+        # Run extraction on sample image
+        print(f"📄 Processing sample invoice: {SAMPLE_IMAGE}")
+        result = agent.extract(SAMPLE_IMAGE)
         
         # Display results
         print("✅ Extraction completed successfully!")
@@ -73,8 +73,8 @@ def main():
         print(f"❌ API Error: {e}")
         print("Check your API key and agent configuration.")
     except FileNotFoundError:
-        print(f"❌ Sample document not found: {SAMPLE_DOCUMENT}")
-        print("Make sure the sample_data directory exists with the sample document.")
+        print(f"❌ Sample image not found: {SAMPLE_IMAGE}")
+        print("Make sure the sample_data directory exists with the sample image.")
     except Exception as e:
         print(f"❌ Unexpected error: {e}")