ragdex 0.1.0__tar.gz

ragdex-0.1.0/.claude/settings.local.json

@@ -0,0 +1,84 @@
+{
+  "permissions": {
+    "allow": [
+      "Bash(export SPIRITUAL_LIBRARY_BOOKS_PATH=\"/Users/hpoliset/SpiritualLibrary\")",
+      "Bash(export SPIRITUAL_LIBRARY_DB_PATH=\"/Users/hpoliset/DocumentIndexerMCP/chroma_db\")",
+      "Bash(export SPIRITUAL_LIBRARY_LOGS_PATH=\"/Users/hpoliset/DocumentIndexerMCP/logs\")",
+      "Bash(./setup.sh:*)",
+      "Bash(cat:*)",
+      "Bash(./scripts/start_web_monitor.sh:*)",
+      "Bash(./scripts/indexing_status.sh:*)",
+      "Bash(./scripts/install_service.sh:*)",
+      "Bash(./scripts/service_status.sh:*)",
+      "Bash(source:*)",
+      "Bash(pip install:*)",
+      "Bash(./scripts/uninstall_service.sh:*)",
+      "Bash(ls:*)",
+      "Bash(kill:*)",
+      "Bash(mv:*)",
+      "Bash(log show:*)",
+      "Bash(brew install:*)",
+      "Bash(soffice:*)",
+      "Bash(grep:*)",
+      "Bash(chmod:*)",
+      "Bash(./scripts/manage_failed_docs.sh:*)",
+      "Bash(find:*)",
+      "Bash(python3:*)",
+      "Bash(pandoc:*)",
+      "Bash(echo:*)",
+      "Bash(./scripts/cleanup_failed_list.sh:*)",
+      "Bash(git add:*)",
+      "Bash(git commit:*)",
+      "Bash(./scripts/cleanup_ocr_cache.sh:*)",
+      "Bash(./scripts/run.sh:*)",
+      "Bash(export PERSONAL_LIBRARY_DOC_PATH=\"/Users/hpoliset/SpiritualLibrary\")",
+      "Bash(venv_mcp/bin/python -c \"from src.core.config import config; print(f''Books directory: {config.books_directory}'')\")",
+      "Bash(git push:*)",
+      "Bash(diff:*)",
+      "Bash(venv_mcp/bin/python:*)",
+      "Bash(timeout 5 venv_mcp/bin/python:*)",
+      "Bash(venv_mcp/bin/pip:*)",
+      "Bash(curl:*)",
+      "Bash(launchctl:*)",
+      "Bash(mkdir:*)",
+      "Bash(git remote set-url:*)",
+      "Bash(for:*)",
+      "Bash(do sed -i '' 's/com\\.spiritual-library/com.personal-library/g' \"$file\")",
+      "Bash(done)",
+      "Bash(sed:*)",
+      "Bash(git checkout:*)",
+      "Bash(git pull:*)",
+      "Bash(git branch:*)",
+      "Bash(git fetch:*)",
+      "Bash(gs:*)",
+      "Bash(./scripts/view_mcp_logs.sh:*)",
+      "Bash(pkill:*)",
+      "Bash(true)",
+      "Bash(rm:*)",
+      "WebSearch",
+      "Bash(export TOKENIZERS_PARALLELISM=false CHROMA_TELEMETRY=false ANONYMIZED_TELEMETRY=false)",
+      "Bash(/opt/homebrew/bin/python3.12:*)",
+      "Bash(venv_mcp_312/bin/python:*)",
+      "Bash(venv_mcp_312/bin/pip install --upgrade pip)",
+      "Bash(venv_mcp_312/bin/pip install:*)",
+      "Bash(do)",
+      "Bash(if grep -q \"venv_mcp/bin/python\" \"$file\")",
+      "Bash(then)",
+      "Bash(fi)",
+      "Bash(export PERSONAL_LIBRARY_DB_PATH=\"/Users/hpoliset/DocumentIndexerMCP/chroma_db\")",
+      "Bash(./scripts/update_claude_config.sh:*)",
+      "Bash(./scripts/install_webmonitor_service.sh:*)",
+      "Bash(./scripts/uninstall_webmonitor_service.sh:*)",
+      "Bash(sample:*)",
+      "Bash(open http://localhost:8888)",
+      "Bash(/tmp/monitor_indexing.sh:*)",
+      "Bash(venv_mcp/bin/pdlib-cli:*)",
+      "Bash(timeout 5 venv_mcp/bin/pdlib-mcp:*)",
+      "Bash(timeout:*)",
+      "Read(//Users/hpoliset/Library/Logs/Claude/**)",
+      "Read(//Users/hpoliset/Library/Application Support/Claude/**)",
+      "Bash(python test_mcp_features.py)"
+    ],
+    "deny": []
+  }
+}

ragdex-0.1.0/.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,67 @@
+---
+name: Bug report
+about: Create a report to help us improve
+title: '[BUG] '
+labels: bug
+assignees: ''
+---
+
+## Bug Description
+A clear and concise description of what the bug is.
+
+## Steps to Reproduce
+1. Go to '...'
+2. Click on '....'
+3. Scroll down to '....'
+4. See error
+
+## Expected Behavior
+A clear and concise description of what you expected to happen.
+
+## Actual Behavior
+A clear and concise description of what actually happened.
+
+## Environment
+- OS: [e.g., macOS 14.0, Ubuntu 22.04]
+- Python version: [e.g., 3.11.13]
+- Architecture: [e.g., ARM64, x86_64]
+- Claude Desktop version: [e.g., 0.11.6]
+- Virtual environment: [e.g., venv_mcp, venv]
+
+## Configuration
+**Claude Desktop Config:**
+```json
+{
+  "mcpServers": {
+    // Your configuration here
+  }
+}
+```
+
+## Logs
+**MCP Server Logs:**
+```
+Paste relevant log entries from:
+~/Library/Logs/Claude/mcp-server-spiritual-library.log
+```
+
+**Server Output (if running manually):**
+```
+Paste output from ./run.sh or direct server execution
+```
+
+## Library Details
+- Number of books: [e.g., 68]
+- Total chunks indexed: [e.g., 38,485]
+- Failed PDFs: [e.g., 0]
+- ChromaDB size: [e.g., 55MB]
+
+## Additional Context
+Add any other context about the problem here, such as:
+- Recent changes made
+- When the issue started
+- Specific books or searches that trigger the issue
+- Screenshots if applicable
+
+## Possible Solution
+If you have ideas about what might be causing the issue or how to fix it, please describe them here.

ragdex-0.1.0/.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,69 @@
+---
+name: Feature request
+about: Suggest an idea for this project
+title: '[FEATURE] '
+labels: enhancement
+assignees: ''
+---
+
+## Feature Description
+A clear and concise description of the feature you'd like to see.
+
+## Use Case
+Describe the problem this feature would solve or the use case it addresses.
+
+## Proposed Solution
+A clear and concise description of what you want to happen.
+
+## Alternative Solutions
+A clear and concise description of any alternative solutions or features you've considered.
+
+## Implementation Ideas
+If you have ideas about how this could be implemented, please describe them:
+
+### MCP Tool Addition
+If this is a new MCP tool:
+- Tool name: [e.g., `analyze_themes`]
+- Input parameters: [e.g., `book_name`, `theme_type`]
+- Expected output: [e.g., theme analysis with quotes]
+
+### Backend Changes
+If this requires backend changes:
+- Component affected: [e.g., shared_rag.py, mcp_complete_server.py]
+- New dependencies: [e.g., additional Python packages]
+- Performance impact: [e.g., minimal, requires optimization]
+
+## Priority
+- [ ] Critical (blocks current functionality)
+- [ ] High (significantly improves user experience)
+- [ ] Medium (nice to have improvement)
+- [ ] Low (minor enhancement)
+
+## Complexity
+- [ ] Simple (few lines of code)
+- [ ] Medium (new function/method)
+- [ ] Complex (new component/architecture change)
+- [ ] Unknown
+
+## Examples
+Provide examples of how this feature would be used:
+
+```python
+# Example code if applicable
+```
+
+**Claude interaction example:**
+```
+User: "Find themes about compassion across all books"
+Claude: [uses new analyze_themes tool]
+Response: "Found 3 main themes about compassion..."
+```
+
+## Additional Context
+Add any other context, screenshots, or examples about the feature request here.
+
+## Willingness to Contribute
+- [ ] I would be willing to implement this feature
+- [ ] I would be willing to help test this feature
+- [ ] I would be willing to help document this feature
+- [ ] I would prefer someone else implements this

ragdex-0.1.0/.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,94 @@
+# Pull Request
+
+## Description
+Brief description of the changes in this PR.
+
+## Type of Change
+- [ ] Bug fix (non-breaking change which fixes an issue)
+- [ ] New feature (non-breaking change which adds functionality)
+- [ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
+- [ ] Documentation update
+- [ ] Performance improvement
+- [ ] Code refactoring
+- [ ] Test addition/improvement
+
+## Changes Made
+- 
+- 
+- 
+
+## Testing
+### Manual Testing
+- [ ] Tested MCP server integration with Claude Desktop
+- [ ] Tested search functionality with sample queries
+- [ ] Tested new tools (if applicable)
+- [ ] Tested on ARM64 (Apple Silicon)
+- [ ] Tested on x86_64 (Intel)
+
+### Automated Testing
+- [ ] All existing tests pass
+- [ ] Added tests for new functionality
+- [ ] Linting passes (flake8)
+- [ ] Formatting passes (black)
+- [ ] Type checking passes (mypy)
+
+## Environment Tested
+- OS: [e.g., macOS 14.0]
+- Python version: [e.g., 3.11.13]
+- Architecture: [e.g., ARM64]
+- Claude Desktop version: [e.g., 0.11.6]
+
+## Performance Impact
+- [ ] No performance impact
+- [ ] Minor performance improvement
+- [ ] Minor performance regression (justified)
+- [ ] Significant performance change (explained below)
+
+**Performance details:**
+[If applicable, describe performance changes]
+
+## Breaking Changes
+- [ ] No breaking changes
+- [ ] Breaking changes (described below)
+
+**Breaking change details:**
+[If applicable, describe what breaks and how to migrate]
+
+## Documentation
+- [ ] Updated README.md
+- [ ] Updated CHANGELOG.md
+- [ ] Updated CONTRIBUTING.md
+- [ ] Updated code comments/docstrings
+- [ ] No documentation changes needed
+
+## Configuration Changes
+- [ ] No configuration changes
+- [ ] Updated requirements.txt
+- [ ] Updated Claude Desktop config format
+- [ ] Added new environment variables
+
+**Configuration details:**
+[If applicable, describe configuration changes]
+
+## Related Issues
+Fixes #[issue number]
+Related to #[issue number]
+
+## Screenshots (if applicable)
+[Add screenshots of new features or UI changes]
+
+## Deployment Notes
+[Any special notes for deploying this change]
+
+## Rollback Plan
+[How to rollback this change if needed]
+
+## Checklist
+- [ ] My code follows the project's style guidelines
+- [ ] I have performed a self-review of my own code
+- [ ] I have commented my code, particularly in hard-to-understand areas
+- [ ] I have made corresponding changes to the documentation
+- [ ] My changes generate no new warnings
+- [ ] I have added tests that prove my fix is effective or that my feature works
+- [ ] New and existing unit tests pass locally with my changes
+- [ ] Any dependent changes have been merged and published

ragdex-0.1.0/.github/workflows/publish.yml

@@ -0,0 +1,85 @@
+name: Publish to PyPI
+
+on:
+  release:
+    types: [published]
+  workflow_dispatch:
+    inputs:
+      test_pypi:
+        description: 'Publish to TestPyPI instead of PyPI'
+        required: false
+        type: boolean
+        default: false
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: '3.11'
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install build twine
+
+    - name: Build package
+      run: python -m build
+
+    - name: Check package
+      run: python -m twine check dist/*
+
+    - name: Upload artifacts
+      uses: actions/upload-artifact@v4
+      with:
+        name: dist
+        path: dist/
+
+  publish-testpypi:
+    if: github.event.inputs.test_pypi == 'true'
+    needs: build
+    runs-on: ubuntu-latest
+    environment:
+      name: testpypi
+      url: https://test.pypi.org/p/personal-doc-library
+    permissions:
+      id-token: write
+
+    steps:
+    - name: Download artifacts
+      uses: actions/download-artifact@v4
+      with:
+        name: dist
+        path: dist/
+
+    - name: Publish to TestPyPI
+      uses: pypa/gh-action-pypi-publish@release/v1
+      with:
+        repository-url: https://test.pypi.org/legacy/
+        password: ${{ secrets.TEST_PYPI_API_TOKEN }}
+
+  publish-pypi:
+    if: github.event_name == 'release' || github.event.inputs.test_pypi == 'false'
+    needs: build
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/personal-doc-library
+    permissions:
+      id-token: write
+
+    steps:
+    - name: Download artifacts
+      uses: actions/download-artifact@v4
+      with:
+        name: dist
+        path: dist/
+
+    - name: Publish to PyPI
+      uses: pypa/gh-action-pypi-publish@release/v1
+      with:
+        password: ${{ secrets.PYPI_API_TOKEN }}

ragdex-0.1.0/.github/workflows/test.yml

@@ -0,0 +1,52 @@
+name: Test
+
+on:
+  push:
+    branches: [ main, develop ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  test:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-latest, macos-latest]
+        python-version: [3.9, 3.10, 3.11]
+
+    steps:
+    - uses: actions/checkout@v4
+    
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v4
+      with:
+        python-version: ${{ matrix.python-version }}
+    
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install -r requirements.txt
+        pip install pytest black flake8 mypy
+    
+    - name: Lint with flake8
+      run: |
+        # Stop build if there are Python syntax errors or undefined names
+        flake8 *.py --count --select=E9,F63,F7,F82 --show-source --statistics
+        # Exit-zero treats all errors as warnings
+        flake8 *.py --count --exit-zero --max-complexity=10 --max-line-length=100 --statistics
+    
+    - name: Check formatting with black
+      run: |
+        black --check *.py
+    
+    - name: Type check with mypy
+      run: |
+        mypy *.py --ignore-missing-imports
+    
+    - name: Test with pytest (when tests are available)
+      run: |
+        if [ -d "tests" ]; then
+          pytest tests/ -v
+        else
+          echo "No tests directory found, skipping tests"
+        fi

ragdex-0.1.0/.github/workflows/test_package.yml

@@ -0,0 +1,75 @@
+name: Test Package with uv
+
+on:
+  push:
+    branches: [ main, develop, pr-* ]
+  pull_request:
+    branches: [ main ]
+  workflow_dispatch:
+
+jobs:
+  test:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, macos-latest]
+        python-version: ['3.10', '3.11', '3.12']
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v5
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Install uv
+      run: |
+        curl -LsSf https://astral.sh/uv/install.sh | sh
+        echo "$HOME/.local/bin" >> $GITHUB_PATH
+
+    - name: Create virtual environment
+      run: uv venv
+
+    - name: Install package with dependencies
+      run: |
+        uv pip install -e .
+        uv pip install pytest pytest-cov
+
+    - name: Test imports
+      run: |
+        uv run python -c "from personal_doc_library import __version__; print(f'Version: {__version__}')"
+        uv run python -c "from personal_doc_library.core.config import config; print('Config module loaded')"
+        uv run python -c "from personal_doc_library.cli import main; print('CLI module loaded')"
+
+    - name: Test CLI commands
+      run: |
+        uv run pdlib-cli --help
+        uv run pdlib-cli config
+
+    - name: Run test files
+      run: |
+        if [ -f "test_mcp_features.py" ]; then
+          uv run python test_mcp_features.py || echo "Test completed with status $?"
+        fi
+        if [ -f "test_resources.py" ]; then
+          uv run python test_resources.py || echo "Test completed with status $?"
+        fi
+
+    - name: Build package
+      run: |
+        uv pip install build
+        uv run python -m build
+
+    - name: Check package with twine
+      run: |
+        uv pip install twine
+        uv run python -m twine check dist/*
+
+    - name: List package contents
+      run: |
+        echo "=== Wheel contents ==="
+        unzip -l dist/*.whl | head -30
+        echo "=== Source dist contents ==="
+        tar -tzf dist/*.tar.gz | head -30

ragdex-0.1.0/.gitignore

@@ -0,0 +1,98 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+env/
+venv/
+venv_mcp/
+venv_mcp_x86_backup/
+ENV/
+env.bak/
+venv.bak/
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+
+# macOS
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Logs
+logs/
+*.log
+setup_log.txt
+setup_summary.txt
+index_monitor.log
+
+# Database and vector stores
+chroma_db/
+src/core/chroma_db/
+*.sqlite3
+*.db
+
+# Books and documents (user content)
+books/
+SpiritualLibrary/
+
+# Temporary files
+tmp/
+temp/
+*.tmp
+*.temp
+
+# Configuration files with sensitive data
+config.json
+secrets.json
+claude_config.json
+
+# Backup files
+backup/
+backup_*/
+*.bak
+
+# Cache
+.cache/
+*.cache
+
+# OS generated files
+Thumbs.db
+ehthumbs.db
+
+# Application specific
+failed_pdfs.json
+index_status.json
+indexing_progress.json
+book_index.json
+
+# Service files (will be recreated)
+*.pid
+*.lock
+
+# Environment variables (user-specific)
+.env
+.env.local
+
+# Deprecated files
+*.deprecated
+
+# Editor temp files
+*~
+\#*\#
+
+# Architecture documentation in root (now in docs/)
+/architecture.html
+
+# Temporary cleaned PDFs
+*.cleaned
+tmp_cleaned_pdfs/
+
+# Old/deprecated scripts
+scripts/setup-script.sh
+scripts/run_enhanced_monitor.sh.ocr_cache/
+.ocr_cache/

ragdex-0.1.0/CHANGELOG.md

@@ -0,0 +1,72 @@
+# Changelog
+
+All notable changes to the Spiritual Library MCP Server will be documented in this file.
+
+## [2.1.0] - 2025-07-05
+
+### Added
+- **New Content Tools**: 
+  - `summarize_book` - Generate AI summaries of entire books
+  - `extract_quotes` - Find notable quotes on specific topics  
+  - `daily_reading` - Get themed passages for daily practice
+  - `question_answer` - Ask direct questions about teachings
+- **ARM64 Compatibility**: Full Apple Silicon support with dedicated `venv_mcp`
+- **Lazy Initialization**: Fast MCP startup, RAG loads only when tools are used
+- **Proper MCP Protocol Compliance**: Fixed initialization response format
+- **Enhanced Error Handling**: Proper JSON-RPC error responses
+
+### Fixed
+- **Architecture Mismatch**: Resolved x86_64 vs ARM64 issues on Apple Silicon
+- **Embedding Dimension Mismatch**: Restored original 768-dim `all-mpnet-base-v2` model
+- **MCP Timeout Issues**: Lazy initialization prevents 6-second startup delay
+- **Search Functionality**: Now returns actual results instead of 0 passages
+- **Server Disconnection**: Proper protocol flow keeps connection alive
+
+### Changed
+- **Embedding Model**: Switched from `all-MiniLM-L6-v2` (384-dim) to `all-mpnet-base-v2` (768-dim)
+- **Virtual Environment**: Using `venv_mcp` with Homebrew Python for ARM64 compatibility
+- **MCP Server Structure**: Complete rewrite with lazy loading and proper protocol handling
+
+### Technical
+- **Python Environment**: ARM64-native Python 3.11 via Homebrew
+- **Vector Database**: ChromaDB with 768-dimensional embeddings
+- **Performance**: ~1.75s search latency, supports synthesis across multiple sources
+- **Monitoring**: Real-time web dashboard and comprehensive logging
+
+## [2.0.0] - 2025-07-04
+
+### Added
+- **Hybrid Architecture**: Support for automatic, background, and manual indexing modes
+- **Background Monitor Service**: Continuous monitoring with LaunchAgent support
+- **Web Monitoring Interface**: Real-time status dashboard at localhost:8888
+- **Enhanced Lock System**: File-based locking with stale detection and auto-cleanup
+- **Automatic PDF Cleaning**: Ghostscript-based cleaning for problematic PDFs
+- **Service Mode**: Install as system service with auto-restart capabilities
+
+### Enhanced
+- **Shared RAG System**: Common functionality between MCP server and background monitor
+- **Error Recovery**: Automatic handling of corrupted or malformed PDFs
+- **Content Categorization**: Improved classification into practice, energy_work, philosophy, general
+- **Statistics Tracking**: Detailed library statistics and indexing history
+
+## [1.0.0] - 2025-07-03
+
+### Initial Release
+- **Basic MCP Server**: Core Model Context Protocol implementation
+- **RAG System**: PDF indexing with ChromaDB vector storage
+- **Search Functionality**: Semantic search across spiritual library
+- **Claude Integration**: Direct integration with Claude Desktop
+- **PDF Processing**: Automatic text extraction and chunking
+- **Synthesis Capabilities**: AI-powered synthesis across multiple sources
+
+### Core Tools
+- `search` - Semantic search with optional synthesis
+- `find_practices` - Find specific spiritual practices
+- `compare_perspectives` - Compare perspectives across sources
+- `library_stats` - Get library statistics and indexing status
+
+### Technical Foundation
+- **Vector Storage**: ChromaDB with sentence-transformers embeddings
+- **LLM Integration**: Ollama with llama3.1:70b model
+- **PDF Processing**: PyPDF2 with recursive text splitting
+- **Content Organization**: Metadata-based categorization system