🧠✂️ SemanticSlicer

Smart, recursive text slicing for LLM-ready documents.

SemanticSlicer is a lightweight C# application that recursively splits text into meaningful chunks—preserving semantic boundaries (sentences, headings, HTML tags) and ideal for embedding generation (OpenAI, Azure OpenAI, LangChain, etc.). You can run it on MacOs, Linux, or Windows and it can run from the command line, as a daemon, as service or as a REST API. You can also directly use the library by referencing the Nuget package in your code.

GitHub: https://github.com/drittich/SemanticSlicer

Table of Contents

• 🧠✂️ SemanticSlicer
  • Table of Contents
  • Overview
  • Nuget Installation
  • Download & Run (no build)
  • CLI Usage
    • Run once
    • Daemon mode
  • Service Installation
    • Linux (systemd)
    • Windows
  • Sample Usage
  • Advanced Usage
    • Split Engine Without Preprocessing
    • Preprocessing Utilities
    • Prepare Content Separately
    • Token Counting
  • Chunk Order
  • Understanding Offsets
  • Additional Metadata
  • Adding Headers to Chunks
  • License
  • Contact

Overview

This library accepts text and will break it into smaller chunks, typically useful for when creating LLM AI embeddings.

Nuget Installation

The package name is drittich.SemanticSlicer. You can install this from Nuget via the command line:

dotnet add package drittich.SemanticSlicer

or from the Package Manager Console:

NuGet\Install-Package drittich.SemanticSlicer

Download & Run (no build)

Prebuilt binaries are published under GitHub Releases of this repository: https://github.com/drittich/SemanticSlicer/releases

Choose the asset that matches your platform:

• Windows x64: SemanticSlicer.Cli-win-x64.zip
• macOS Intel: SemanticSlicer.Cli-osx-x64.zip
• macOS Apple Silicon: SemanticSlicer.Cli-osx-arm64.zip
• Linux x64: SemanticSlicer.Cli-linux-x64.zip

After downloading:

• Windows:

  • Unzip the file.
  • Open Command Prompt in the unzipped folder.
  • Language: cmd Command: SemanticSlicer.Cli.exe MyDocument.txt
  • Or pipe input: Language: cmd Command: type MyDocument.txt | SemanticSlicer.Cli.exe

• macOS:

  • Unzip the file.
  • In Terminal, mark the binary executable if needed and run:
    • Intel:
      • Language: bash Command: chmod +x SemanticSlicer.Cli && ./SemanticSlicer.Cli MyDocument.txt
    • Apple Silicon:
      • Language: bash Command: chmod +x SemanticSlicer.Cli && ./SemanticSlicer.Cli MyDocument.txt
  • Pipe input:
    • Language: bash Command: cat MyDocument.txt | ./SemanticSlicer.Cli

• Linux:

  • Unzip the file.
  • Language: bash Command: chmod +x SemanticSlicer.Cli && ./SemanticSlicer.Cli MyDocument.txt
  • Pipe input:
    • Language: bash Command: cat MyDocument.txt | ./SemanticSlicer.Cli

Daemon mode (keeps slicer in memory):

• Language: bash Command: ./SemanticSlicer.Cli daemon
• Named pipe (Linux/macOS):
  • Language: bash Command: ./SemanticSlicer.Cli daemon --pipe slicerpipe

Notes:

• These builds are self-contained; the .NET runtime is not required.
• If your OS flags the binary (macOS Gatekeeper), you may need to allow it in System Settings → Privacy & Security.

CLI Usage

Build the command-line tool:

dotnet publish SemanticSlicer.Cli/SemanticSlicer.Cli.csproj -c Release -o ./cli

Run once

Slice a file and output JSON chunk data:

dotnet ./cli/SemanticSlicer.Cli.dll --overlap 30 MyDocument.txt

You can also pipe text in (omit the overlap flag to use the default 0%):

cat MyDocument.txt | dotnet ./cli/SemanticSlicer.Cli.dll --overlap 20

Use the --overlap flag (0-100) to carry forward that percentage of the previous chunk's tokens, respecting your configured max chunk size.

Daemon mode

Keep a slicer in memory and read lines from stdin (or a named pipe):

dotnet ./cli/SemanticSlicer.Cli.dll daemon --overlap 25

Optionally listen on a named pipe:

dotnet ./cli/SemanticSlicer.Cli.dll daemon --pipe slicerpipe --overlap 25

Service Installation

The repository includes a small Web API (SemanticSlicer.Service) that can be installed as a background service so the slicer stays in memory.

First publish the service:

dotnet publish SemanticSlicer.Service/SemanticSlicer.Service.csproj -c Release -o ./publish

Linux (systemd)

1. Copy the ./publish folder to /opt/semanticslicer (or a location of your choice).
2. Create /etc/systemd/system/semanticslicer.service with:

[Unit]
Description=Semantic Slicer Service
After=network.target

[Service]
Type=simple
WorkingDirectory=/opt/semanticslicer
ExecStart=/usr/bin/dotnet /opt/semanticslicer/SemanticSlicer.Service.dll
Restart=always

[Install]
WantedBy=multi-user.target

3. Enable and start the service:

sudo systemctl enable semanticslicer
sudo systemctl start semanticslicer

Windows

1. Publish the service to a folder, e.g. C:\SemanticSlicer:

dotnet publish SemanticSlicer.Service/SemanticSlicer.Service.csproj -c Release -o C:\SemanticSlicer

2. From an elevated command prompt install and start the service:

sc create SemanticSlicer binPath= "\"%ProgramFiles%\dotnet\dotnet.exe\" \"C:\\SemanticSlicer\\SemanticSlicer.Service.dll\""
sc start SemanticSlicer

Once running you can POST text to the service:

curl -X POST http://localhost:5000/slice -H "Content-Type: application/json" \
    -d '{"content":"Hello world","overlapPercentage":30}'

overlapPercentage is optional (defaults to 0) and clamped between 0 and 100. Header tokens also count toward the overlap budget.

Sample Usage

Simple text document:

// The default options uses text separators, a max chunk size of 1,000, and 
// cl100k_base encoding to count tokens.
var slicer = new Slicer();
var text = File.ReadAllText("MyDocument.txt");
var documentChunks = slicer.GetDocumentChunks(text);

Markdown document:

// Let's use Markdown separators and reduce the chunk size
var options = new SlicerOptions { MaxChunkTokenCount = 600, Separators = Separators.Markdown };
var slicer = new Slicer(options);
var text = File.ReadAllText("MyDocument.md");
var documentChunks = slicer.GetDocumentChunks(text);

Overlapping chunks:

// Reuse the last 30% of the previous chunk (by tokens), while still respecting the max size
var options = new SlicerOptions { MaxChunkTokenCount = 800, OverlapPercentage = 30 };
var slicer = new Slicer(options);
var documentChunks = slicer.GetDocumentChunks(text);

HTML document:

var options = new SlicerOptions { Separators = Separators.Html };
var slicer = new Slicer(options);
var text = File.ReadAllText("MyDocument.html");
var documentChunks = slicer.GetDocumentChunks(text);

Removing HTML tags:

For any content you can choose to remove HTML tags from the chunks to minimize the number of tokens. The inner text is preserved, and if there is a <Title> tag the title will be pre-pended to the result:

// Let's remove the HTML tags as they just consume a lot of tokens without adding much value
var options = new SlicerOptions { Separators = Separators.Html, StripHtml = true };
var slicer = new Slicer(options);
var text = File.ReadAllText("MyDocument.html");
var documentChunks = slicer.GetDocumentChunks(text);

Custom separators:

You can pass in your own list if of separators if you wish, e.g., if you wish to add support for other documents.

Advanced Usage

For advanced scenarios where you need full control over preprocessing, SemanticSlicer provides lower-level APIs:

Split Engine Without Preprocessing

Use SplitDocumentChunksRaw when you want to apply your own preprocessing but still benefit from token-aware splitting, overlap, and indexing:

var slicer = new Slicer();
// Apply your own custom preprocessing
var customProcessed = MyCustomPreprocessing(rawHtml);
// Split using the engine directly (no normalization, HTML stripping, or whitespace collapsing)
var chunks = slicer.SplitDocumentChunksRaw(customProcessed);

Important: SplitDocumentChunksRaw treats content exactly as provided:

• Does NOT normalize line endings
• Does NOT strip HTML (even if StripHtml is true)
• Does NOT collapse whitespace
• Does NOT trim content
• Offsets in returned chunks are relative to the exact content string you provide

Preprocessing Utilities

SemanticSlicer exposes the same preprocessing utilities used internally:

// Normalize line endings (CRLF and CR to LF)
var normalized = TextUtilities.NormalizeLineEndings(input);

// Collapse excessive whitespace (max 2 consecutive spaces or newlines)
var collapsed = TextUtilities.CollapseWhitespace(input);

// Extract text from HTML (already public on Slicer instance)
var slicer = new Slicer();
var plainText = slicer.RemoveNonBodyContent(htmlContent);

Combine these with SplitDocumentChunksRaw for custom pipelines:

var slicer = new Slicer()