AI Examples
AI samples for TX Text Control .NET Server range from a console chat with a local language model to a complete web application and a document server for AI agents. Examples in AI Integration lists all of them with their repositories. Where to begin, which online demos cover the same tasks without a model and which articles introduce the skills and MCP servers are collected below.
Where to Start
The samples of the TX Text Control AI preview, version 0.1.0-beta.3 at the time of writing, are in the repository txtextcontrol-ai-samples. They need a GGUF model and an inference runtime that you provide; Run the Samples in Text Control AI describes the setup.
| Example | What it shows | Where |
|---|---|---|
| The complete web application | Chat, Document Studio, runtime administration, knowledge collections and the Document Editor in one ASP.NET Core application. Text Control names it the best way to explore the whole workflow; it uses the MCP document server sample, which you start first | samples/WebDocumentAssistant |
| A first local chat | The smallest sample: a console loop that answers prompts with a local model | samples/LocalChat |
| A local chat without the repository | A streaming console chat built step by step in a new project, written for version 0.1.0-beta.1 of the preview | Running a Local LLM in .NET C# with TX Text Control AI |
The blog article Introducing TX Text Control AI: Private AI for Real Document Workflows in .NET C# introduces the preview and its samples.
Document Analysis Without a Model
Not every analysis needs a language model. Four online demos classify documents, extract tables, map form fields and sanitize documents with rules that give the same, explainable result every time. Each has a sample project on GitHub:
| Example | What it shows | Where |
|---|---|---|
| Document classification | DOCX files classified with weighted rules, with the confidence and the evidence behind each result | Document Classification, TXTextControl.Document.Classification |
| Table extraction | The domain of a table detected, its columns normalized and its data extracted as JSON | Structured Table Extraction, TXTextControl.SmartTableExtraction |
| Form field mapping | Form field names matched to the properties of JSON data with confidence scores, then merged | Form Field Mapping, TXTextControl.FormFieldMapper |
| Sanitization | Metadata, form values, comments, tracked changes and embedded content found and removed before a document leaves your system | Document Sanitization, TXTextControl.Sanitize.Data |
The sample projects target .NET 10 and version 34.0. The blog article From Classification to Data Extraction: New Document Analysis Samples introduces the demos, and Document Analysis compares these approaches with a language model.
Agent Skills and MCP
The repositories of the MCP document server and the Agent Skills are listed in Examples in AI Integration. These articles introduce them:
| Example | What it shows | Where |
|---|---|---|
| Agent Skills | Skills that teach AI coding assistants to integrate the Document Editor | Introducing Text Control Agent Skills |
| ServerTextControl skills | Skills for document processing with ServerTextControl | Expanding Text Control Agent Skills: New ServerTextControl Skills for AI Assisted Document Processing |
| MCP document backend | A backend whose document operations AI agents discover and call as MCP tools | Build Your Own MCP-Powered Document Processing Backend with TX Text Control |
| Documents from natural language | Documents created from instructions in natural language through the MCP server | AI Natural Language Document Generation with MCP and TX Text Control .NET |
The blog samples that call OpenAI's hosted API are listed in Examples in AI Integration; three of them were written for versions 31.0 and 32.0.
Next Steps
- Text Control AI: the packages of the preview and how to run the samples.
- Local / Private LLMs: run models on your own hardware.
- Document Processing Examples: samples of document processing without AI.