Get Free Community License
Document Intelligence

The Complete LocalDocument Intelligence Platform.

Turn any document into structured, searchable, actionable data. Chat with PDFs, extract fields from invoices, split multi-document scans, and build RAG pipelines. All powered by on-device AI with adaptive processing that combines OCR, Vision Language Models, and layout analysis. Zero cloud dependency.

Start Building Free Explore Documentation
100% On-Device Adaptive Processing .NET SDK HIPAA / GDPR Ready

Ingest Any Document

PDF, DOCX, XLSX, PPTX, HTML, Markdown, images

INPUT

Adaptive Analysis

Auto-selects OCR, VLM, or text extraction per page

PROCESS

Structured Output

Chat answers, extracted fields, document segments, RAG results

OUTPUT
0
Cloud Calls
7+
Formats
100%
Traceable
3
AI Engines
Four Pillars of Document Intelligence

Every Document Workflow, One SDK

From conversational Q&A to automated data extraction, LM-Kit.NET provides a complete document intelligence toolkit built for production .NET applications.

Document Chat & Q&A
Ask questions, get grounded answers

Load any document and ask questions in natural language. The PdfChat agent combines semantic RAG with adaptive layout analysis to deliver accurate, source-attributed answers. Supports multi-document queries, follow-up conversations, and agentic tool calling.

  • Semantic RAG with intelligent chunking
  • Every answer traced to document, page, and passage
  • Multi-turn conversation with context memory
  • Agentic capabilities with tool calling and MCP
Explore Document Chat
Structured Data Extraction
Any document, any field, zero hallucinations

Define a schema, feed in a document, get structured JSON. The extraction engine uses Dynamic Sampling and symbolic validation layers to eliminate LLM hallucinations. Works on invoices, contracts, forms, receipts, IDs, and any document type.

  • Schema-driven extraction with typed outputs
  • Dynamic Sampling eliminates hallucinations
  • Built-in OCR with language auto-detection
  • Images, scans, PDFs, Office documents, handwriting
Explore Data Extraction
Document RAG Engine
Build custom document retrieval pipelines

The lower-level RAG engine for developers who need full control. Manage document lifecycle with explicit IDs, configure chunking strategies, choose vector store backends, and build custom retrieval workflows with semantic search and source attribution.

  • Full document lifecycle management (import, update, delete)
  • Pluggable vector stores (filesystem, Qdrant, custom)
  • Configurable chunking (text, markdown, HTML)
  • Real-time progress events for all processing phases
Explore Document RAG
Intelligent Document Splitting
One PDF, multiple documents, automatically separated

Automatically detect logical document boundaries within multi-page PDFs using vision language models. The neuro-symbolic engine identifies where each document starts and ends, assigns descriptive labels, and returns page ranges with confidence scores. No templates required.

  • VLM-powered boundary detection on scanned pages
  • Automatic document labels and confidence scoring
  • Semantic guidance for improved accuracy
  • Template-free: works on any document type
Explore Document Splitting

Adaptive Processing: Three AI Engines, One API

Every page in every document is different. A digital PDF has clean text layers. A scanned invoice needs OCR. A complex form with tables and columns needs visual understanding. LM-Kit.NET's adaptive engine analyzes each page individually and selects the optimal extraction strategy automatically.

This content-aware approach means you never have to classify documents upfront or write format-specific code. One API call handles a 500-page batch containing digital contracts, scanned receipts, and image-heavy reports.

Built by IDP pioneers: This isn't a wrapper around generic RAG. It's purpose-built document intelligence from a team with 20+ years of experience processing billions of documents in production worldwide.

Auto (PageProcessingMode.Auto)

Analyzes each page and automatically selects the best strategy. Uses VLM for image-heavy pages, direct text extraction for digital content, OCR for scanned text. Zero configuration required.

TextExtraction

Extracts text directly from PDF structure with OCR fallback for scanned pages. Fastest processing, lowest resource usage. Ideal for clean digital documents.

DocumentUnderstanding

Vision Language Models analyze pages visually to understand layout, structure, tables, and relationships. Outputs structured markdown. Best for complex layouts, forms, and multi-column content.

Up and Running in Minutes

LM-Kit.NET is a single NuGet package. No microservices, no Docker, no API keys. Load a model, point at a document, and start extracting intelligence.

  1. Install the NuGet package and load your preferred AI models (chat, embedding, vision)
  2. Create a PdfChat instance and feed it any document: PDF, Word, Excel, images, HTML
  3. Ask questions in natural language and get grounded answers with source attribution

The same models power all four pillars. Switch from document Q&A to data extraction to document splitting by changing one class.

DocumentIntelligence.cs 
using LMKit.Retrieval;
using LMKit.Extraction;
using LMKit.Model;

// Load models
var chat = LM.LoadFromModelID("gemma3:4b");
var embed = LM.LoadFromModelID("embeddinggemma-300m");

// ── Document Q&A ──
using var pdfChat = new PdfChat(chat, embed);
await pdfChat.LoadDocumentAsync("report.pdf");
var answer = await pdfChat.SubmitAsync(
    "What were the Q4 results?");

// ── Structured Extraction ──
var extractor = new TextExtraction(chat);
extractor.SetContent(new Attachment("invoice.pdf"));
var result = extractor.Parse();

// ── Document Splitting ──
var vision = LM.LoadFromModelID("gemma3-vl:4b");
var splitter = new DocumentSplitting(vision);
var segments = splitter.Split(
    new Attachment("batch_scan.pdf"));
Platform Capabilities

Enterprise-Grade Document Processing

Built for production workloads that demand accuracy, traceability, and compliance.

Layout Analysis Engine

Deep document structure understanding: columns, paragraphs, lines, text regions, reading order. Purpose-built algorithms for real-world document layouts.

Source Attribution

Every answer and extracted value is traced to its source document, page number, and passage. Full audit trail for compliance and verification.

Intelligent Caching

Processed document embeddings are cached via IVectorStore. Subsequent loads are instant. Supports filesystem, Qdrant, and custom backends.

Vision Language Models

VlmOcr uses multimodal AI to transcribe pages as structured markdown. Understands tables, forms, multi-column layouts, and handwritten notes visually.

100% On-Device

All processing runs on your infrastructure. Documents never leave. Air-gapped deployments, HIPAA, GDPR, and SOC 2 compliance ready out of the box.

Neuro-Symbolic Validation

Dynamic Sampling combined with symbolic validation layers eliminates LLM hallucinations. Confidence scores on every extraction for production-grade reliability.

File Format Support

Process Any Document Format

Native support for the most common document types in enterprise workflows.

.pdf
PDF Documents
.docx
Word Documents
.xlsx
Excel Spreadsheets
.pptx
PowerPoint Slides
.html
HTML Pages
.md
Markdown Files
.png .jpg
Images & Scans
.txt
Plain Text
Use Cases

Built for Real-World Document Workflows

From mailroom automation to compliance audits, LM-Kit.NET handles the document intelligence that matters.

Invoice & Receipt Processing

Extract vendor, amounts, line items, tax, and payment terms from any invoice format. Schema-driven extraction with zero hallucinations.

Contract Analysis

Query legal agreements for clauses, obligations, termination conditions, and payment terms. Multi-document comparison with full source attribution.

Compliance & Audit

Verify regulatory compliance across document collections. Traceable source references create audit trails for HIPAA, GDPR, and SOC 2.

Mailroom Automation

Split multi-document scans into individual files, classify each automatically, and route to the correct workflow. No templates needed.

Knowledge Base & Research

Build searchable knowledge bases from technical manuals, research papers, and specifications. Semantic search across thousands of documents.

Customer Support Automation

Ingest product documentation and answer customer questions automatically. Grounded responses ensure accuracy with zero fabrication.

Ready-to-Run Demos

See Document Intelligence in Action

Every capability ships with a complete, runnable console application. Download, build, and explore. Full source code on GitHub.

Featured Demo

Chat with PDF

Interactive console application for conversational Q&A over PDF documents. Load one or more files, choose between standard and vision processing modes, and ask questions with real-time streaming, source references, and generation stats.

  • Model selection with automatic download
  • Standard text extraction or VLM-based understanding
  • Multi-document loading with embedding cache
  • Interactive commands: /help, /status, /add, /clear
Sample Guide GitHub Source
Featured Demo

Invoice Data Extraction

Extract structured fields from invoice documents (PDF and images) using vision language models. Outputs vendor details, line items, totals, tax, and payment terms as clean JSON. Includes sample invoices and a customizable extraction schema.

  • Schema-driven extraction with JSON output
  • PDF and image support (PNG, JPG, TIFF)
  • Optional OCR with auto language detection
  • Sample invoices included for immediate testing
Sample Guide GitHub Source

More Document Intelligence Demos

Document Splitting

Detect logical boundaries in multi-page PDFs and split them into separate files. Vision-based analysis with labels and confidence scores.

Guide GitHub

Structured Data Extraction

Define custom schemas and extract typed fields from text documents. Supports invoices, job offers, medical records, and more.

Guide GitHub

Document to Markdown

Convert PDFs, images, and scans to structured Markdown using VLMs. Preserves tables, formatting, and document structure.

Guide GitHub

Document Processing Agent

An AI agent with 9 built-in tools: PDF split, merge, render, inspect, OCR, deskew, crop, resize, and text extraction via natural language.

Guide GitHub

Document Summarizer

Generate titles and concise summaries from PDFs, images, and text files. Customizable summary length and style guidance.

Guide GitHub

Language Detection from Document

Detect the language of PDF and image documents using VLMs. Multilingual support with fast processing and performance metrics.

Guide GitHub

Explore All LM-Kit.NET Samples

40+ console demos covering agents, chat, classification, extraction, embeddings, RAG, speech, vision, and more.

Samples Overview All Samples on GitHub
API Reference

Core Classes for Document Intelligence

The building blocks for every document workflow in your .NET application.

PdfChat

High-level conversational document agent. Load documents, ask questions, get grounded answers with source references. Supports tool calling and MCP.

View Docs
DocumentRag

Lower-level RAG engine with full control over processing modes, chunking, vector stores, and document lifecycle management.

View Docs
TextExtraction

Schema-driven structured data extraction from text, images, PDFs, and Office documents. JSON output with typed fields.

View Docs
DocumentSplitting

VLM-powered boundary detection within multi-page PDFs. Returns page ranges, labels, and confidence scores.

View Docs
VlmOcr

Vision-based document parser using multimodal LMs. Transcribes pages as structured markdown preserving layout and structure.

View Docs
IVectorStore

Interface for embedding storage and caching. Built-in filesystem backend. Pluggable: Qdrant, PostgreSQL, or custom implementations.

View Docs

Ready to Build Document Intelligence?

The most advanced local document processing platform for .NET. From chat to extraction to splitting. 100% on your infrastructure.

Download Free Contact Sales