Metadata-Version: 2.4
Name: iflow-mcp_ahmad-act-open-webui-mcp
Version: 0.1.0
Summary: Leave Manager MCP server for managing employee leave balance, applications, and history
Requires-Python: >=3.12
Description-Content-Type: text/markdown
Requires-Dist: mcp[cli]>=1.9.2

# Local AI with Ollama, WebUI & MCP on Windows

A self-hosted AI stack combining Ollama for running language models, Open WebUI for user-friendly chat interaction, and MCP for centralized model management—offering full control, privacy, and flexibility without relying on the cloud.

This sample project provides an **MCP-based tool server** for managing employee leave balance, applications, and history. It is exposed via OpenAPI using `mcpo` for easy integration with **Open WebUI** or other OpenAPI-compatible clients.

---

## 🚀 Features

- ✅ Check employee leave balance
- 📆 Apply for leave on specific dates
- 📜 View leave history
- 🙋 Personalized greeting functionality

---

## 📁 Project Structure

```text
leave-manager/
├── main.py                  # MCP server logic for leave management
├── requirements.txt         # Python dependencies for the MCP server
├── Dockerfile               # Docker image configuration for the leave manager
├── docker-compose.yml       # Docker Compose file to run leave manager and Open WebUI
└── README.md                # Project documentation (this file)
```
---


## 📋 Prerequisites

1. **Windows 10 or later** (required for Ollama)
2. **Docker Desktop for Windows** (required for Open WebUI and MCP)
   - Install from: [Docker Desktop for Windows](https://docs.docker.com/desktop/install/windows-install/)

---

## 🛠️ Workflow

1. Install Ollama on Windows
2. Pull the `deepseek-r1` model
3. Clone the repository and navigate to the project directory
4. Run the `docker-compose.yml` file to launch services

---

## Install Ollama

### ➤ Windows

1. **Download the Installer**:
   - Visit [Ollama Download](https://ollama.com/download/windows) and click **Download for Windows** to get `OllamaSetup.exe`.
   - Alternatively, download from [Ollama GitHub Releases](https://github.com/ollama/ollama/releases).

2. **Run the Installer**:
   - Execute `OllamaSetup.exe` and follow the installation prompts.
   - After installation, Ollama runs as a background service, accessible at: [http://localhost:11434](http://localhost:11434).
   - Verify in your browser; you should see:
     ```text
     Ollama is running
     ```
   ![Ollama Initial Window](readme-img/ollama-setup-steps-1.png)
   ![Ollama Setup Progress](readme-img/ollama-setup-steps-2.png)
   ![Ollama In System Tray](readme-img/ollama-setup-steps-3.png)
   ![Ollama On Browser](readme-img/ollama-setup-steps-4.png)
3. **Start Ollama Server (if not already running)**:
   ```powershell
   ollama serve
   ```
   - Access the server at: [http://localhost:11434](http://localhost:11434).


### Verify Installation

Check the installed version of Ollama:

```powershell
ollama --version
```

**Expected Output**:
```
ollama version 0.7.1
```

---

## Pull the `deepseek-r1` Model

### 1. Pull the Default Model (7B):

#### Using PoweShell

```powershell
ollama pull deepseek-r1
```

![deepseek-r1](readme-img/deepseek-r1-setup-1.png)

*To Pull Specific Versions:*

```powershell
ollama run deepseek-r1:1.5b
ollama run deepseek-r1:671b
```

### 2. List Installed Models:

```powershell
ollama list
```

Expected:

**Expected Output**:
```text
NAME                    ID              SIZE
deepseek-r1:latest      xxxxxxxxxxxx    X.X GB
```

![deepseek-r1:latest](readme-img/deepseek-r1-setup-2.png)

### 4. Alternative Check via API:

```powershell
curl http://localhost:11434/api/tags
```

**Expected Output**:
A JSON response listing installed models, including `deepseek-r1:latest`.

![alternative check](readme-img/deepseek-r1-setup-3.png)

### 4. Test the API via PowerShell:

```powershell
Invoke-RestMethod -Uri http://localhost:11434/api/generate -Method Post -Body '{"model": "deepseek-r1", "prompt": "Hello, world!", "stream": false}' -ContentType "application/json"
```

**Expected Response**:
A JSON object containing the model's response to the "Hello, world!" prompt.

![test the API](readme-img/deepseek-r1-setup-7.png)

### 5. Run and Chat the Model via PowerShell:

```powershell
ollama run deepseek-r1
```

- This opens an interactive chat session with the `deepseek-r1` model.
- Type `/bye` and press `Enter` to exit the chat session.

![run and chat](readme-img/deepseek-r1-setup-4.png)

![run and chat with Hi](readme-img/deepseek-r1-setup-5.png)

![exist chat](readme-img/deepseek-r1-setup-6.png)

---

## 🐳 Run Open WebUI and MCP Server with Docker Compose

1. **Clone the Repository**:

   ```powershell
   git clone https://github.com/ahmad-act/Local-AI-with-Ollama-Open-WebUI-MCP-on-Windows.git
   cd Local-AI-with-Ollama-Open-WebUI-MCP-on-Windows
   ```

2. **To launch both the MCP tool and Open WebUI locally (on Docker Desktop)**:

   ```powershell
   docker-compose up --build
   ```

   ![exist chat](readme-img/openwebui-mcp-setup-1.png)
   ![exist chat](readme-img/openwebui-mcp-setup-2.png)
   ![exist chat](readme-img/openwebui-mcp-setup-3.png)
   ![exist chat](readme-img/openwebui-mcp-setup-4.png)
   ![exist chat](readme-img/openwebui-mcp-setup-5.png)
   ![exist chat](readme-img/openwebui-mcp-setup-6.png)
   ![exist chat](readme-img/openwebui-mcp-setup-7.png)

This will:
   - Start the Leave Manager (MCP Server) tool on port `8000`
   - Launch Open WebUI at [http://localhost:3000](http://localhost:3000)

---

## 🌐 Add MCP Tools to Open WebUI

The MCP tools are exposed via the OpenAPI specification at: [http://localhost:8000/openapi.json](http://localhost:8000/openapi.json).

1. Open [http://localhost:3000](http://localhost:3000) in your browser.
2. Click the **Profile Icon** and navigate to **Settings**.
![exist chat](readme-img/add-mcp-tools-on-open-webui-1.png)
3. Select the **Tools** menu and click the **Add (+) Button**.
![exist chat](readme-img/add-mcp-tools-on-open-webui-2.png)
4. Add a new tool by entering the URL: [http://localhost:8000/](http://localhost:8000/).
![exist chat](readme-img/add-mcp-tools-on-open-webui-3.png)
![exist chat](readme-img/add-mcp-tools-on-open-webui-4.png)
![exist chat](readme-img/add-mcp-tools-on-open-webui-5.png)
![exist chat](readme-img/add-mcp-tools-on-open-webui-6.png)
![exist chat](readme-img/add-mcp-tools-on-open-webui-7.png)
![exist chat](readme-img/add-mcp-tools-on-open-webui-8.png)
![exist chat](readme-img/add-mcp-tools-on-open-webui-9.png)

---

## 💬 Example Prompts

Use these prompts in Open WebUI to interact with the Leave Manager tool:

- **Check Leave Balance**:
   ```
   Check how many leave days are left for employee E001
   ```
   ![exist chat](readme-img/add-mcp-tools-on-open-webui-10.png)
   ![exist chat](readme-img/add-mcp-tools-on-open-webui-11.png)
- **Apply for Leave**:
   ```
   Apply
   ![exist chat](readme-img/add-mcp-tools-on-open-webui-12.png)
- **View Leave History**:
   ```
   What's the leave history of E001?
   ```
   ![exist chat](readme-img/add-mcp-tools-on-open-webui-13.png)
- **Personalized Greeting**:
   ```
   Greet me as Alice
   ```
   ![exist chat](readme-img/add-mcp-tools-on-open-webui-14.png)

---

## 🛠️ Troubleshooting

- **Ollama not running**: Ensure the service is active (`ollama serve`) and check [http://localhost:11434](http://localhost:11434).
- **Docker issues**: Verify Docker Desktop is running and you have sufficient disk space.
- **Model not found**: Confirm the `deepseek-r1` model is listed with `ollama list`.
- **Port conflicts**: Ensure ports `11434`, `3000`, and `8000` are free.

---

## 📚 Additional Resources

- [Ollama Documentation](https://github.com/ollama/ollama/tree/main/docs)
- [Open WebUI Documentation](https://docs.openwebui.com/)
- [Docker Desktop Documentation](https://docs.docker.com/desktop/)
- [MCP Documentation](https://modelcontextprotocol.io/introduction)
- [OpenAPI Tool Servers](https://github.com/open-webui/openapi-servers)
- [mcpo - Works with OpenAPI tools, SDKs, and UIs](https://github.com/open-webui/mcpo)
