Refactor and rename application components for improved clarity and functionality

- Updated the main application entry point to reflect the new `ragadoc` package name, enhancing clarity in the codebase.
- Refactored the document upload and processing logic to integrate with the new RAG system, ensuring seamless user experience.
- Renamed environment and configuration files to align with the new package structure.
- Enhanced development instructions to clarify project setup and usage guidelines.
- Introduced new modules for chat management, LLM interface, and UI components, improving code organization and maintainability.
- Updated tests to reflect changes in module imports and ensure continued functionality.

Author: clstaudt

DEVELOPMENT_INSTRUCTIONS.md

@@ -5,4 +5,5 @@
 - Debug information belongs into the command line logs, not in the app UI/UX.
 - Always develop a generic solution, do not use content from specific examples in the code
 - Never include content from example documents in the source code. Never leak content from provided examples into test code!
-- If you create new .py files for testing or debugging, place them in the experiments folder. Delete them after they are no longer useful. If they yield meaningful unit tests, integrate them into the test suite.
+- If you create new .py files for testing or debugging, place them in the experiments folder. Delete them after they are no longer useful. If they yield meaningful unit tests, integrate them into the test suite.
+- Do not put implementation details into the README. The README serves as a compact user manual for getting started.

README.md

@@ -1,4 +1,4 @@
-# Ragnarok - Enhanced PDF Processing
+# Ragadoc - Enhanced PDF Processing
 
 A powerful PDF processing system with high-quality text extraction and structure preservation, optimized for LLM/RAG applications.
 
@@ -42,7 +42,7 @@ pip install -r requirements.txt
 2. **Or use Conda**:
 ```bash
 conda env create -f environment.yml
-conda activate ragnarok
+conda activate ragadoc
 ```
 
 3. **Install Ollama Models for RAG**:
@@ -76,7 +76,7 @@ Then:
 ### RAG System (Programmatic)
 
 ```python
-from ragnarok import create_rag_system
+from ragadoc import create_rag_system
 
 # Create RAG system
 rag = create_rag_system(
@@ -91,7 +91,7 @@ with open('document.pdf', 'rb') as f:
     pdf_bytes = f.read()
 
 # Extract text and process with RAG
-from ragnarok import EnhancedPDFProcessor
+from ragadoc import EnhancedPDFProcessor
 processor = EnhancedPDFProcessor(pdf_bytes)
 text = processor.extract_full_text()
 
@@ -107,7 +107,7 @@ print(result['response'])
 ### Basic PDF Processing
 
 ```python
-from ragnarok.enhanced_pdf_processor import EnhancedPDFProcessor
+from ragadoc.enhanced_pdf_processor import EnhancedPDFProcessor
 
 # Load PDF
 with open('document.pdf', 'rb') as f:

app.py

@@ -1,12 +1,13 @@
 """
-Refactored Streamlit App for Document Q&A
+Streamlit application that provides a web interface for enhanced PDF processing
+from the ragadoc package.
 
 This is now a much simpler main entry point that uses the UI modules
 from the ragnarok package.
 """
 
 import streamlit as st
-from ragnarok import (
+from ragadoc import (
     setup_streamlit_config,
     init_session_state,
     render_sidebar,

docker-compose.yml

@@ -4,7 +4,7 @@ services:
   # Streamlit application
   app:
     build: .
-    container_name: ragnarok-app
+    container_name: ragadoc-app
     ports:
       - "8501:8501"
     environment:

environment.yml

@@ -1,4 +1,4 @@
-name: ragnarok
+name: ragadoc
 channels:
   - defaults
   - conda-forge

ragnarok/__init__.py renamed to ragadoc/__init__.py

@@ -1,5 +1,5 @@
 """
-Ragnarok - AI-powered PDF processing and highlighting system with RAG capabilities
+Ragadoc - AI-powered PDF processing and highlighting system with RAG capabilities
 """
 
 from .enhanced_pdf_processor import (