Extract Text

Overview

ToText() extracts the content of a document as a plain text string — no Markdown syntax, no bounding boxes, no metadata. It’s the simplest output format and the right choice when your downstream tool doesn’t need formatting or structure, just the words.

using PDF4LLM;

string text = PdfExtractor.ToText("document.pdf");
Console.WriteLine(text);

When to use plain text

Use case	Recommended format
Search indexing	✅ Plain text
Keyword extraction / NLP	✅ Plain text
LLM summarisation (simple)	✅ Plain text
RAG pipelines with chunking	⚠️ Consider Markdown or page chunks
Preserving document structure	❌ Use Markdown
Custom layout pipelines	❌ Use JSON

If you’re feeding content into an LLM and document structure matters — headings, lists, tables — use ToMarkdown() instead. LLMs handle Markdown well and the added structure improves output quality.

Page selection

Extract only the pages you need:

string text = PdfExtractor.ToText(
    "document.pdf",
    pages: new List<int> { 0, 1, 2 }
);

Per-page chunks

Use LlamaMarkdownReader to return one document object per page instead of a single concatenated string. Each chunk includes the page’s plain text and a metadata dictionary with the page number and source file path:

var reader = PdfExtractor.LlamaMarkdownReader();
var chunks = reader.LoadData("document.pdf");

foreach (var chunk in chunks)
{
    int    page     = (int)chunk.ExtraInfo["page"];
    string text     = chunk.Text;

    Console.WriteLine($"Page {page}: {text.Length} chars");
}

Each chunk’s Text property contains the plain Markdown for that page. For plain text specifically, strip Markdown syntax after loading, or call ToText per page using the pages parameter:

using MuPDF.NET;

Document doc    = new Document("document.pdf");
var      chunks = new List<(int Page, string Text)>();

for (int i = 0; i < doc.PageCount; i++)
{
    string pageText = PdfExtractor.ToText(doc, pages: new List<int> { i });
    chunks.Add((i, pageText));
}

doc.Close();

foreach (var chunk in chunks)
    Console.WriteLine($"Page {chunk.Page}: {chunk.Text.Length} chars");

Saving to a file

Write the output to a .txt file:

using System.IO;
using PDF4LLM;

string text = PdfExtractor.ToText("document.pdf");
File.WriteAllText("output.txt", text, System.Text.Encoding.UTF8);

To save each page as a separate file:

using MuPDF.NET;
using System.IO;

Document doc = new Document("document.pdf");
Directory.CreateDirectory("output");

for (int i = 0; i < doc.PageCount; i++)
{
    string pageText = PdfExtractor.ToText(doc, pages: new List<int> { i });
    File.WriteAllText($"output/page-{i}.txt", pageText, System.Text.Encoding.UTF8);
}

doc.Close();

OCR behaviour

Like ToMarkdown(), ToText() can invoke Tesseract OCR on pages that contain no selectable text. Pass useOcr: true to enable it:

// Enable OCR on all pages
string text = PdfExtractor.ToText("document.pdf", useOcr: true);

// Enable OCR with a specific language
string text = PdfExtractor.ToText("document.pdf", useOcr: true, ocrLanguage: "fra");

See OCR for a full walkthrough of Tesseract installation, language codes, and patterns for mixed documents.

For the full API signature, see the ToText() API reference.

Next steps

Extract Markdown

Preserve structure and formatting for LLM pipelines.

Extract JSON

Access bounding boxes and layout data for custom pipelines.

OCR

Control OCR behaviour and language configuration.

Getting Started

Guides

Integrations

Reference

Overview

When to use plain text

Page selection

Per-page chunks

Saving to a file

OCR behaviour

Next steps

Extract Markdown

Extract JSON

OCR

​Overview

​When to use plain text

​Page selection

​Per-page chunks

​Saving to a file

​OCR behaviour

​Next steps

Extract Markdown

Extract JSON

OCR

Overview

When to use plain text

Page selection

Per-page chunks

Saving to a file

OCR behaviour

Next steps