kg-rag 0.1.0__tar.gz

kg_rag-0.1.0/.env

@@ -0,0 +1,3 @@
+AWS_ACCESS_KEY_ID=ASIAVUPQWCEVZBUYND3S
+AWS_SECRET_ACCESS_KEY=J9Fxd56STR9AhrQ8yxcYLPhoWOdKIgy6FcFGPuYC
+AWS_SESSION_TOKEN=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

kg_rag-0.1.0/.gitignore

@@ -0,0 +1,4 @@
+.mypy_cache
+.ruff_cache
+.litellm_cache
+__pycache__

kg_rag-0.1.0/.vscode/mcp.json

@@ -0,0 +1,4 @@
+{
+	"inputs": [],
+	"servers": {}
+}

kg_rag-0.1.0/.vscode/settings.json

@@ -0,0 +1,8 @@
+{
+  "python.defaultInterpreterPath": "python",
+  "python.terminal.activateEnvironment": true,
+  "files.associations": {
+    "*.md": "markdown"
+  },
+  "postman.settings.dotenv-detection-notification-visibility": false
+}

kg_rag-0.1.0/PKG-INFO

@@ -0,0 +1,154 @@
+Metadata-Version: 2.4
+Name: kg-rag
+Version: 0.1.0
+Summary: Knowledge Graph-based RAG system with MCP server integration
+Project-URL: Homepage, https://github.com/prout/kg-rag
+Project-URL: Repository, https://github.com/prout/kg-rag
+Project-URL: Issues, https://github.com/prout/kg-rag/issues
+Author-email: prout <thepuspak@gmail.com>
+License: MIT
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.12
+Requires-Dist: azure-identity
+Requires-Dist: fastmcp
+Requires-Dist: graspologic
+Requires-Dist: litellm
+Requires-Dist: markitdown
+Requires-Dist: nest-asyncio
+Requires-Dist: networkx
+Requires-Dist: numpy
+Requires-Dist: pandas
+Requires-Dist: pydantic
+Requires-Dist: python-dotenv
+Requires-Dist: sqlalchemy
+Requires-Dist: sqlmodel
+Requires-Dist: streamlit
+Requires-Dist: tenacity
+Requires-Dist: tiktoken
+Provides-Extra: dev
+Requires-Dist: mypy; extra == 'dev'
+Requires-Dist: pytest; extra == 'dev'
+Requires-Dist: pytest-cov; extra == 'dev'
+Requires-Dist: ruff; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# KnowledgeGraphRAG with MCP Server
+
+A Knowledge Graph-based RAG system with a modern MCP server for seamless integration with MCP-compatible clients like Claude Desktop.
+
+## Quick Start
+
+### 1. Install Dependencies
+```bash
+pip install -r requirements.txt
+pip install fastmcp
+```
+
+### 2. Test the Setup
+```bash
+python test_mcp.py
+```
+
+### 3. Start the MCP Server
+```bash
+# Direct execution
+python mcp_server.py
+
+# Using startup scripts
+# Windows:
+start_mcp_server.bat
+
+# Unix/Linux/macOS:
+./start_mcp_server.sh
+```
+
+### 4. Configure Claude Desktop
+Add to your Claude Desktop configuration:
+
+**Windows**: `%APPDATA%\Claude\claude_desktop_config.json`
+**macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
+
+```json
+{
+  "mcpServers": {
+    "knowledgegraph-rag": {
+      "command": "python",
+      "args": ["C:/path/to/kg-rag/mcp_server.py"],
+      "cwd": "C:/path/to/kg-rag"
+    }
+  }
+}
+```
+
+## Core Files
+
+### MCP Server
+- **`mcp_server.py`** - Main MCP server implementation
+- **`test_mcp.py`** - Test script for the MCP server
+- **`setup_mcp.py`** - Automated dependency installation
+
+### Configuration & Startup
+- **`mcp_config.json`** - Claude Desktop configuration template
+- **`start_mcp_server.bat`** - Windows startup script
+- **`start_mcp_server.sh`** - Unix startup script
+
+### Documentation
+- **`FASTMCP_GUIDE.md`** - Comprehensive setup and usage guide
+
+### KnowledgeGraphRAG Core
+- **`kgrag/`** - Core RAG system implementation
+- **`requirements.txt`** - Python dependencies
+- **`rag.db`** - SQLite database for the knowledge graph
+
+## Available Tools
+
+- **index_document** - Index documents into the knowledge graph
+- **query_documents** - Query and get AI-generated answers
+- **list_documents** - List all indexed documents
+- **remove_document** - Remove documents from the knowledge graph
+- **get_document_stats** - Get document statistics
+
+## Available Resources
+
+- **knowledgegraph://document/{doc_name}** - Dynamic document resources
+
+## Available Prompts
+
+- **generate_query_prompt** - Generate prompts for querying topics
+- **analyze_document_prompt** - Generate prompts for document analysis
+
+## Example Usage
+
+```
+User: List the documents in the knowledge graph
+Assistant: 📚 Documents in knowledge graph (2 total):
+- Research Paper 2024
+- Q1 Report
+
+User: What are the key findings in the Research Paper 2024?
+Assistant: 💬 Answer to 'What are the key findings in the Research Paper 2024?':
+[AI-generated response based on the knowledge graph]
+```
+
+## Troubleshooting
+
+1. **Import Errors**: Run `python test_mcp.py` to check setup
+2. **Server Issues**: Check that `kgrag` module is accessible
+3. **Claude Integration**: Verify paths in Claude Desktop config
+
+For detailed information, see `FASTMCP_GUIDE.md`.
+
+## Architecture
+
+```
+Claude Desktop → MCP Server → KnowledgeGraphRAG → SQLite Database
+```
+
+The MCP server provides a clean, type-safe interface to the KnowledgeGraphRAG system with minimal boilerplate code.

kg_rag-0.1.0/README.md

@@ -0,0 +1,113 @@
+# KnowledgeGraphRAG with MCP Server
+
+A Knowledge Graph-based RAG system with a modern MCP server for seamless integration with MCP-compatible clients like Claude Desktop.
+
+## Quick Start
+
+### 1. Install Dependencies
+```bash
+pip install -r requirements.txt
+pip install fastmcp
+```
+
+### 2. Test the Setup
+```bash
+python test_mcp.py
+```
+
+### 3. Start the MCP Server
+```bash
+# Direct execution
+python mcp_server.py
+
+# Using startup scripts
+# Windows:
+start_mcp_server.bat
+
+# Unix/Linux/macOS:
+./start_mcp_server.sh
+```
+
+### 4. Configure Claude Desktop
+Add to your Claude Desktop configuration:
+
+**Windows**: `%APPDATA%\Claude\claude_desktop_config.json`
+**macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
+
+```json
+{
+  "mcpServers": {
+    "knowledgegraph-rag": {
+      "command": "python",
+      "args": ["C:/path/to/kg-rag/mcp_server.py"],
+      "cwd": "C:/path/to/kg-rag"
+    }
+  }
+}
+```
+
+## Core Files
+
+### MCP Server
+- **`mcp_server.py`** - Main MCP server implementation
+- **`test_mcp.py`** - Test script for the MCP server
+- **`setup_mcp.py`** - Automated dependency installation
+
+### Configuration & Startup
+- **`mcp_config.json`** - Claude Desktop configuration template
+- **`start_mcp_server.bat`** - Windows startup script
+- **`start_mcp_server.sh`** - Unix startup script
+
+### Documentation
+- **`FASTMCP_GUIDE.md`** - Comprehensive setup and usage guide
+
+### KnowledgeGraphRAG Core
+- **`kgrag/`** - Core RAG system implementation
+- **`requirements.txt`** - Python dependencies
+- **`rag.db`** - SQLite database for the knowledge graph
+
+## Available Tools
+
+- **index_document** - Index documents into the knowledge graph
+- **query_documents** - Query and get AI-generated answers
+- **list_documents** - List all indexed documents
+- **remove_document** - Remove documents from the knowledge graph
+- **get_document_stats** - Get document statistics
+
+## Available Resources
+
+- **knowledgegraph://document/{doc_name}** - Dynamic document resources
+
+## Available Prompts
+
+- **generate_query_prompt** - Generate prompts for querying topics
+- **analyze_document_prompt** - Generate prompts for document analysis
+
+## Example Usage
+
+```
+User: List the documents in the knowledge graph
+Assistant: 📚 Documents in knowledge graph (2 total):
+- Research Paper 2024
+- Q1 Report
+
+User: What are the key findings in the Research Paper 2024?
+Assistant: 💬 Answer to 'What are the key findings in the Research Paper 2024?':
+[AI-generated response based on the knowledge graph]
+```
+
+## Troubleshooting
+
+1. **Import Errors**: Run `python test_mcp.py` to check setup
+2. **Server Issues**: Check that `kgrag` module is accessible
+3. **Claude Integration**: Verify paths in Claude Desktop config
+
+For detailed information, see `FASTMCP_GUIDE.md`.
+
+## Architecture
+
+```
+Claude Desktop → MCP Server → KnowledgeGraphRAG → SQLite Database
+```
+
+The MCP server provides a clean, type-safe interface to the KnowledgeGraphRAG system with minimal boilerplate code.