Skip to content

Dess ai coding assistant #611

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 9 commits into
base: master
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions _config.yml
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,9 @@ navigation:
release-notes/2024:
title: '2024'
position: 100
"ai-coding-assistant":
title: AI Coding Assistant
position: 1
installation-and-deployment:
title: Installation and Deployment
position: 4
Expand Down
88 changes: 88 additions & 0 deletions ai-coding-assistant/copilot-extension.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,88 @@
---
title: Copilot Extension
page_title: DPL Copilot Extension
description: Learn how to add and use the Telerik Document Processing GitHub Copilot Extension as a DPL AI coding assistant and code generator for better developer productivity.
slug: ai-copilot-extension
tags: ai, dpl, document, processing, coding, assistant, getting, started, extension, copilot
published: True
position: 1
---


# Telerik Document Processing GitHub Copilot Extension <sup>(Preview)</sup>

The Telerik Document Processing Libraries (DPL) [GitHub Copilot](https://github.com/features/copilot) extension is an AI-powered coding assistant that provides specialized knowledge about the Telerik [Document Processing Libraries]({%slug introduction%}).

This extension enhances GitHub Copilot with proprietary context about Telerik Document Processing Libraries, helping you:

* Generate code snippets using Document Processing Libraries.
* Get contextual suggestions for component properties and methods.
* Access best practices and implementation patterns.
* Speed up development with AI-powered code completion.

## Prerequisites for the GitHub Copilot Extension

In addition to the [prerequisites for the AI Coding Assistant]({%slug ai-coding-assistant%}#prerequisites-for-the-ai-coding-assistant), before using the Telerik Document Processing Libraries GitHub Copilot extension, ensure you have:

* An active [GitHub Copilot](https://github.com/features/copilot) subscription. You can enable or configure GitHub Copilot on the [Copilot Settings page in your GitHub account](https://github.com/settings/copilot).
* The latest version of your [Copilot-enabled app](https://docs.github.com/en/copilot/building-copilot-extensions/about-building-copilot-extensions#supported-clients-and-ides) (for example, Visual Studio or Visual Studio Code).

## Installation

Follow these steps to install and configure the Telerik Document Processing Copilot extension:

1. Go to the [Telerik Document Processing GitHub App](https://github.com/apps/telerikdpl) page and click the **Install** button.
1. You will see a list that includes your GitHub account and all GitHub organizations that you are part of. **Select your GitHub account**.
1. Click the **Install & Authorize** button. This will allow the GitHub Copilot extension to integrate with your GitHub account.

![Telerik Document Processing GitHub App](images/dpl-ai-copilot-extension.png)

1. Enter your GitHub password when prompted.
1. You will be redirected to **telerik.com**. Enter your **Telerik account** credentials if prompted. This step links the GitHub Copilot extension with your Telerik account.
1. Upon successful Telerik authentication, you will be redirected to a confirmation page that indicates successful Copilot extension installation.
1. Restart your [Copilot-enabled app](https://docs.github.com/en/copilot/building-copilot-extensions/about-building-copilot-extensions#supported-clients-and-ides) (for example, Visual Studio and Visual Studio Code).
1. Start a new chat session in Copilot.

## Usage

To use the Telerik DPL Copilot extension:

1. Open the GitHub Copilot chat window in your [Copilot-enabled app](https://docs.github.com/en/copilot/building-copilot-extensions/about-building-copilot-extensions#supported-clients-and-ides) (for example, Visual Studio or VS Code).
1. Ensure you are in **Chat** mode and not in **Edit** or **Agent** mode. The Edit and Agent modes do not use the Telerik Copilot extension. However, the Agent mode can use the [Telerik DPL MCP server]({%slug ai-mcp-server%}).
1. Start your prompt with `@telerikdpl` and type your request. Verify that `@telerikdpl` is recognized and highlighted; otherwise, the extension may not be properly installed.

![Recognized TelerikDpl](images/dpl-ai-copilot-extension-recognized.png)

1. Look for a status label such as **Telerik DPL working...** or **Telerik DPL generating response...** in the output to confirm the extension is active.

![Telerik DPL generating response](images/dpl-ai-copilot-extension-generating-response.png)

1. Grant permission to the Telerik DPL extension to read your workspace files when prompted.
1. For unrelated queries, start a new chat session in a new window to avoid context pollution from previous conversations.

### Sample Prompts

The following examples demonstrate useful prompts for the Telerik DPL extension:

* "`@telerikdpl` Generate a PDF document with a table 3x3 with Name, Age, City as columns"
* "`@telerikdpl` Generate a PDF document with a text and an image"

## Number of Requests

A Telerik [Subscription license](https://www.telerik.com/purchase.aspx?filter=web) is recommended in order to use the Telerik DPL AI Coding Assistant without restrictions. Perpetual license holders and trial users can make a [limited number of requests per year]({%slug ai-coding-assistant%}#number-of-requests).

## Troubleshooting

If you encounter issues:

* Ensure the `@telerikdpl` mention is properly highlighted in your prompt.
* Verify that you have an active GitHub Copilot subscription.
* Restart your IDE after installation.
* Check that you're in Chat mode, not Edit or Agent mode.

## See Also

* [GitHub Copilot Documentation](https://docs.github.com/en/copilot)
* [GitHub Copilot Tutorials](https://github.com/features/copilot/tutorials)
* [Telerik DPL MCP Server]({%slug ai-mcp-server%})
* [Document Processing Libraries]({%slug introduction%})
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
209 changes: 209 additions & 0 deletions ai-coding-assistant/mcp-server.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,209 @@
---
title: MCP Server
page_title: DPL MCP Server
description: Learn how to add and use the Telerik Document Processing MCP Server as a .NET Document Processing AI coding assistant and code generator for better developer productivity. The Telerik Document Processing MCP server provides proprietary context about Telerik UI for .NET Document Processing to AI-powered software.
slug: ai-mcp-server
tags: telerik, dpl, ai, server, mcp, dotnet,coding assistant
published: True
position: 2
---

# Telerik Document Processing MCP Server <sup>(Preview)</sup>

The Telerik Document Processing [MCP (Model Context Protocol) Server](https://modelcontextprotocol.io/introduction) enhances your AI-powered development experience by providing specialized context about Telerik Document Processing libraries.

This MCP server enables AI-powered IDEs and tools to generate more accurate, tailored code that leverages [Telerik Document Processing Libraries](https://www.telerik.com/document-processing-libraries) and APIs. You can ask complex questions about Document Processing Libraries, request specific implementations, and generate comprehensive code solutions.

## Prerequisites for the MCP Server

In addition to the [prerequisites for the AI Coding Assistant]({%slug ai-coding-assistant%}#prerequisites-for-the-ai-coding-assistant), To use the Telerik Document Processing (DPL) MCP server, you need:

* [Node.js](https://nodejs.org/en) 18 or newer.
* An [MCP-compatible client](https://modelcontextprotocol.io/clients) that supports **MCP tools** (latest version recommended).

## Installation

Install the Telerik DPL MCP server using npm:

```bash
npm i @progress/telerik-dpl-mcp
```

### Configuration

Use these settings when configuring the server in your MCP client:

|Setting|Value|
|----|----|
| Package Name | `@progress/telerik-dpl-mcp` |
| Type | `stdio` (standard input/output transport) |
| Command | `npx` |
| Arguments | `-y` |
| Server Name | `telerikDplAssistant` (customizable) |

### License Configuration

Add your [Telerik license key]({%slug setting-up-license-key%}) as an environment parameter in your `mcp.json` file using one of these options:

Option 1: License File Path (Recommended)

```json
"env": {
"TELERIK_LICENSE_PATH": "THE_PATH_TO_YOUR_LICENSE_FILE"
}
```

Option 2: Direct License Key

```json
"env": {
"TELERIK_LICENSE": "YOUR_LICENSE_KEY_HERE"
}
```

> Option 1 is recommended unless you're sharing settings across different systems. Remember to [update your license key]({%slug setting-up-license-key%}#updating-your-license-key) when necessary.

## Visual Studio

For complete setup instructions, see [Use MCP servers in Visual Studio](https://learn.microsoft.com/en-us/visualstudio/ide/mcp-servers).

> Early Visual Studio 17.14 versions require the Copilot Chat window to be open when opening a solution for the MCP server to work properly.

### Workspace-Specific Setup:

1. Add `.mcp.json` to your solution folder:

```json
{
"servers": {
"telerikDplAssistant": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@progress/telerik-dpl-mcp@latest"],
"env": {
"TELERIK_LICENSE_PATH": "THE_PATH_TO_YOUR_LICENSE_FILE",
// or
"TELERIK_LICENSE": "YOUR_LICENSE_KEY"
}
}
}
}
```

2. Restart Visual Studio.
3. Enable the `telerikDplAssistant` tool in the [Copilot Chat window's tool selection dropdown](https://learn.microsoft.com/en-us/visualstudio/ide/mcp-servers?view=vs-2022#configuration-example-with-github-mcp-server).

### Global Setup:

Add the `.mcp.json` file to your user directory (`%USERPROFILE%`, e.g., `C:\Users\YourName\.mcp.json`).

## Visual Studio Code

For complete setup instructions, see [Use MCP servers in Visual Studio Code](https://code.visualstudio.com/docs/copilot/chat/mcp-servers).

> Visual Studio Code 1.102.1 or newer is required to use the Telerik MCP Server

The basic setup in Visual Studio Code follows these steps:

1. Enable [`chat.mcp.enabled`](vscode://settings/chat.mcp.enabled) in Visual Studio Code settings.
2. Create `.vscode/mcp.json` in your workspace root (or user folder for global setup):

```json
{
"servers": {
"telerik-dpl-assistant": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@progress/telerik-dpl-mcp@latest"],
"env": {
"TELERIK_LICENSE_PATH": "THE_PATH_TO_YOUR_LICENSE_FILE",
// or
"TELERIK_LICENSE": "YOUR_LICENSE_KEY"
}
}
}
}
```

3. For global discovery, enable [`chat.mcp.discovery.enabled`](vscode://settings/chat.mcp.discovery.enabled) in `settings.json`:

```json
{
"chat.mcp.discovery.enabled": true
}
```

4. Restart Visual Studio Code.

## Cursor

For complete setup instructions, see [Model Context Protocol](https://docs.cursor.com/context/mcp).

Create `.cursor/mcp.json` in your workspace root (or user folder for global setup):

```json
{
"mcpServers": {
"telerikDplAssistant": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@progress/telerik-dpl-mcp@latest"],
"env": {
"TELERIK_LICENSE_PATH": "THE_PATH_TO_YOUR_LICENSE_FILE",
// or
"TELERIK_LICENSE": "YOUR_LICENSE_KEY"
}
}
}
}
```

## Usage

To use the Telerik MCP Server:

1. Start your prompt with one of these triggers:
- `/telerik` / `@telerik` / `#telerik`
- `/telerikdpl` / `@telerikdpl` / `#telerikdpl`
- `#telerik-dpl-assistant`

2. Verify server activation by looking for these messages:
- Visual Studio: `Running telerikDplAssistant`
- Visual Studio Code: `Running telerik-dpl-assistant`
- Cursor: `Calling MCP tool telerikDplAssistant`

3. Grant permissions when prompted (per session, workspace, or always).

4. Start fresh sessions for unrelated prompts to avoid context pollution.

### Improving Server Usage

To increase the likelihood of the Telerik MCP server being used, add custom instructions to your AI tool:
- [GitHub Copilot custom instructions](https://docs.github.com/en/copilot/customizing-copilot/adding-repository-custom-instructions-for-github-copilot#about-repository-custom-instructions-for-github-copilot-chat)
- [Cursor rules](https://docs.cursor.com/context/rules)

### Sample Prompts

The following examples demonstrate useful prompts for the Telerik Document Processing MCP Server:

* "`/telerik` Generate a PDF document with a table 3x3 with Name, Age, City as columns"
* "`/telerikdpl` Generate a PDF document with a text and an image"

## Number of Requests

A Telerik [Subscription license](https://www.telerik.com/purchase.aspx?filter=web) is recommended in order to use the Telerik DPL AI Coding Assistant without restrictions. Perpetual license holders and trial users can make a [limited number of requests per year]({%slug ai-coding-assistant%}#number-of-requests).

## Local AI Model Integration

You can use the Telerik DPL MCP server with local large language models (LLMs):

1. Run a local model, for example, through [Ollama](https://ollama.com).
2. Use a bridge package like [MCP-LLM Bridge](https://github.com/patruff/ollama-mcp-bridge).
3. Connect your local model to the Telerik MCP server.

This setup allows you to use the Telerik AI Coding Assistant without cloud-based AI models.

## See Also

* [Telerik DPL GitHub Copilot Extension]({%slug ai-copilot-extension%})
* [AI Coding Assistant Overview]({%slug ai-coding-assistant%})
69 changes: 69 additions & 0 deletions ai-coding-assistant/overview.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,69 @@
---
title: Overview
page_title: Telerik Document Processing AI Tooling Overview
description: Learn about the Telerik Document Processing Libraries AI-powered developer tools that integrate with your IDE or code editor for greater productivity and enhanced developer experience.
slug: ai-coding-assistant
tags: ai, dpl, document, processing, coding, assistant
published: True
position: 0
---

# Telerik Document Processing AI Coding Assistant <sup>(Preview)</sup>

Telerik Document Processing offers an **AI Coding Assistant** which will leverage AI to enhance productivity, reduce guesswork, and ensure compliance with security standards when building applications with the [Document Processing Libraries]({%slug introduction%}). The coding assistant is an AI code generator that provides specialized context to AI models, enabling them to produce higher-quality code samples.

## Supported Libraries

* [RadPdfPocessing]({%slug radpdfprocessing-overview%})

## Available Tools

The **AI Coding Assistant** is represented by:

* GenAI-powered Embeddability [Copilot Extension]({%slug ai-copilot-extension%})

* [MCP server]({%slug ai-mcp-server%})

### Key Differences

The major differences between these tools are:

| Feature| MCP Server| GitHub Copilot Extension|
|-----|----|----|
|Prompt Handling|Handles complex, multi-step prompts| Offers shorter, focused code snippets|
|Client Compatibility|Works with MCP-enabled clients (e.g., Cursor, Copilot Agent mode)|Integrated as a Copilot extension|
|Code Suggestions|Can directly suggest changes and rebuild applications to verify code|Provides detailed explanations alongside code suggestions|
|Response Focus|Primarily code-focused|Better for learning and understanding implementation|

## Prerequisites for the AI Coding Assistant

To use the Telerik Document Processing Libraries AI Coding Assistant, you need:

* A [Telerik user account](https://www.telerik.com/account/).
* An active [Telerik license](https://www.telerik.com/purchase.aspx?filter=web) that includes Telerik Document Processing.
* An application that uses the Telerik [Document Processing Libraries]({%slug introduction%}).

## Number of Requests

The Document Processing AI Coding Assistant allows the following maximum number of requests based on your [Telerik license type](https://www.telerik.com/purchase.aspx?filter=web):

| License Type | Request Limit |
|--------------|---------------|
| Perpetual | 50 requests per year |
| Subscription | Virtually unlimited with fair use threshold of 300 requests per day |
| Trial | 300 requests per trial period (does not reset with new trial activations) |

> All Telerik AI tools share a single request quota for your Telerik account. Usage from the [Telerik Copilot extension]({%slug ai-copilot-extension%}) and [Telerik MCP server]({%slug ai-mcp-server%}) counts toward the same limit. Complex prompts in the MCP server may consume multiple requests.

## Privacy

The Telerik Document Processing AI Coding Assistant operates under strict privacy guidelines:

Data Access:
* No access to your workspace and application code.
* Exception: when using the Telerik MCP server (or any other MCP server), the LLM generates parameters for the MCP server request, which may include parts of your application code.

## Next Steps

* Install the [Telerik Document Processing Libraries GitHub Copilot Extension]({%slug ai-copilot-extension%})
* Configure the [Telerik Document Processing Libraries MCP Server]({%slug ai-mcp-server%}) with an MCP-enabled client