English | [简体中文](./README-CN.md)
# GraphRAG-UI
GraphRAG-UI is a user-friendly interface for [GraphRAG](https://github.com/microsoft/graphrag), a powerful tool that uses the Retrieval-Augmented Generation (RAG) approach to index and query large text data. This project supports the latest version graphrag-0.3.3 and aims to provide a convenient management and interaction method for GraphRAG, supporting the configuration of local large language models like Ollama, making it easier for users to leverage.
## Acknowledgments
This project is currently an upgrade based on the work of [severian42](https://github.com/severian42) and his [GraphRAG-Local-UI](https://github.com/severian42/GraphRAG-Local-UI) project. I would like to express my sincere gratitude to him for laying a solid foundation for this project. New features may be added in the future.
## Features
- **Intuitive Web Interface**: GraphRAG-UI provides a user-friendly web interface for easy configuration and use of GraphRAG.
- **Index Management**: Quickly create, update, and manage your text data indexes.
- **Query Execution**: Submit natural language queries and retrieve relevant content from indexed data, followed by responses from a large language model.
- **Configuration Options**: Customize various settings and parameters to fine-tune the indexing and querying processes.
- **Logging and Monitoring**: Monitor the progress of indexing and querying tasks through detailed logs and status updates.
## Sample screenshots:
### Indexing
### Visualize Graph (GIF image)
### Chat With GraphRAG
## Usage with pip
1. Install Ollama (optional):
Visit the [Ollama website](https://ollama.com/) to install. If you're on Linux, you can run the following command directly:
```bash
curl -fsSL https://ollama.com/install.sh | sh
```
2. Install this software via pip:
```bash
pip install graphrag-ui
or
pip install graphrag-ui -i https://pypi.org/simple
```
3. Start the API Server
```bash
graphrag-ui-server
```
4. Start the UI
Start the comprehensive UI
```bash
graphrag-ui
```
Or start the pure UI
```bash
graphrag-ui-pure
```
## Source code installation and usage
1. Create and activate a new conda environment:
```bash
conda create -n graphrag-ui -y
conda activate graphrag-ui
```
2. Install Ollama（optional）:
Visit [Ollama's website](https://ollama.com/) for installation instructions.
Or Linux, run:
```bash
curl -fsSL https://ollama.com/install.sh | sh
```
3. Clone the repository:
```bash
git clone https://github.com/wade1010/graphrag-ui.git
```
4. Install the required packages:
```bash
cd graphrag-ui
pip install -r requirements.txt
```
5. Start the API server:
```bash
python api.py --host 0.0.0.0 --port 8012 --reload
```
6. Start the UI:
- **Clean version**
This version only supports indexing, Prompt Tuning, and file management, without query functionality.
```bash
gradio index_app.py
or
python index_app.py
```
- **Comprehensive version**
This version adds visualizations, configuration management, and GraphRAG chat functionality on top of the clean version.
```bash
python app.py
```
7. Access the UI:
- **Clean version**: `http://localhost:7860`
- **Comprehensive version**: `http://localhost:7862`
Raw data
{
"_id": null,
"home_page": "https://github.com/wade1010/graphrag-ui",
"name": "graphrag-ui",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "graphrag ollma ui local ai",
"author": "wade1010",
"author_email": "640297@qq.com",
"download_url": null,
"platform": null,
"description": "\nEnglish | [\u7b80\u4f53\u4e2d\u6587](./README-CN.md)\n\n# GraphRAG-UI\n\nGraphRAG-UI is a user-friendly interface for [GraphRAG](https://github.com/microsoft/graphrag), a powerful tool that uses the Retrieval-Augmented Generation (RAG) approach to index and query large text data. This project supports the latest version graphrag-0.3.3 and aims to provide a convenient management and interaction method for GraphRAG, supporting the configuration of local large language models like Ollama, making it easier for users to leverage.\n\n## Acknowledgments\n\nThis project is currently an upgrade based on the work of [severian42](https://github.com/severian42) and his [GraphRAG-Local-UI](https://github.com/severian42/GraphRAG-Local-UI) project. I would like to express my sincere gratitude to him for laying a solid foundation for this project. New features may be added in the future.\n\n## Features\n\n- **Intuitive Web Interface**: GraphRAG-UI provides a user-friendly web interface for easy configuration and use of GraphRAG.\n- **Index Management**: Quickly create, update, and manage your text data indexes.\n- **Query Execution**: Submit natural language queries and retrieve relevant content from indexed data, followed by responses from a large language model.\n- **Configuration Options**: Customize various settings and parameters to fine-tune the indexing and querying processes.\n- **Logging and Monitoring**: Monitor the progress of indexing and querying tasks through detailed logs and status updates.\n\n## Sample screenshots:\n### Indexing\n\n\n\n### Visualize Graph (GIF image)\n\n\n\n### Chat With GraphRAG\n\n\n\n## Usage with pip\n\n1. Install Ollama (optional):\n\n Visit the [Ollama website](https://ollama.com/) to install. If you're on Linux, you can run the following command directly:\n\n ```bash\n curl -fsSL https://ollama.com/install.sh | sh\n ```\n\n2. Install this software via pip:\n\n ```bash\n pip install graphrag-ui\n or\n pip install graphrag-ui -i https://pypi.org/simple\n ```\n\n3. Start the API Server\n\n ```bash\n graphrag-ui-server\n ```\n\n4. Start the UI\n\n Start the comprehensive UI\n\n ```bash\n graphrag-ui\n ```\n\n Or start the pure UI\n\n ```bash \n graphrag-ui-pure\n ```\n\n## Source code installation and usage\n\n1. Create and activate a new conda environment:\n ```bash\n conda create -n graphrag-ui -y\n conda activate graphrag-ui\n ```\n2. Install Ollama\uff08optional\uff09:\n\n Visit [Ollama's website](https://ollama.com/) for installation instructions.\n \n Or Linux, run:\n\n ```bash\n curl -fsSL https://ollama.com/install.sh | sh\n ```\n\n3. Clone the repository:\n ```bash\n git clone https://github.com/wade1010/graphrag-ui.git\n ```\n\n4. Install the required packages:\n ```bash\n cd graphrag-ui\n pip install -r requirements.txt\n ```\n\n5. Start the API server:\n ```bash\n python api.py --host 0.0.0.0 --port 8012 --reload\n ```\n\n6. Start the UI:\n - **Clean version**\n\n This version only supports indexing, Prompt Tuning, and file management, without query functionality.\n ```bash\n gradio index_app.py\n or\n python index_app.py\n ```\n - **Comprehensive version**\n\n This version adds visualizations, configuration management, and GraphRAG chat functionality on top of the clean version.\n ```bash\n python app.py\n ```\n\n7. Access the UI:\n - **Clean version**: `http://localhost:7860`\n - **Comprehensive version**: `http://localhost:7862`\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "The latest graphrag interface is used, using the local ollama to provide the LLM interface",
"version": "0.1.3",
"project_urls": {
"Homepage": "https://github.com/wade1010/graphrag-ui"
},
"split_keywords": [
"graphrag",
"ollma",
"ui",
"local",
"ai"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "c70944ca410c5d6f9fb32059eefacb8e1561be17f9d04cd82260e2d07abab3f7",
"md5": "74594dcbc3469d1fc71b1b7762969485",
"sha256": "bae584621ddefa4f4fb0cc78349e0a426c4eb3b1069bb6ba56e0429a5971f677"
},
"downloads": -1,
"filename": "graphrag_ui-0.1.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "74594dcbc3469d1fc71b1b7762969485",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 58273,
"upload_time": "2024-09-13T12:36:38",
"upload_time_iso_8601": "2024-09-13T12:36:38.489861Z",
"url": "https://files.pythonhosted.org/packages/c7/09/44ca410c5d6f9fb32059eefacb8e1561be17f9d04cd82260e2d07abab3f7/graphrag_ui-0.1.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-09-13 12:36:38",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "wade1010",
"github_project": "graphrag-ui",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [
{
"name": "gradio",
"specs": [
[
"==",
"4.43.0"
]
]
},
{
"name": "fastapi",
"specs": [
[
"==",
"0.112.4"
]
]
},
{
"name": "uvicorn",
"specs": [
[
"==",
"0.30.6"
]
]
},
{
"name": "python-dotenv",
"specs": [
[
"==",
"1.0.1"
]
]
},
{
"name": "pydantic",
"specs": [
[
"==",
"2.9.0"
]
]
},
{
"name": "pandas",
"specs": [
[
"==",
"2.2.2"
]
]
},
{
"name": "tiktoken",
"specs": [
[
"==",
"0.7.0"
]
]
},
{
"name": "langchain-community",
"specs": [
[
"==",
"0.2.16"
]
]
},
{
"name": "aiohttp",
"specs": [
[
"==",
"3.10.5"
]
]
},
{
"name": "PyYAML",
"specs": [
[
"==",
"6.0.2"
]
]
},
{
"name": "requests",
"specs": [
[
"==",
"2.32.3"
]
]
},
{
"name": "duckduckgo-search",
"specs": [
[
"==",
"6.2.11"
]
]
},
{
"name": "ollama",
"specs": [
[
"==",
"0.3.2"
]
]
},
{
"name": "plotly",
"specs": [
[
"==",
"5.24.0"
]
]
}
],
"lcname": "graphrag-ui"
}
JSON
