LocalAI.Text.Core
0.7.2
dotnet add package LocalAI.Text.Core --version 0.7.2
NuGet\Install-Package LocalAI.Text.Core -Version 0.7.2
<PackageReference Include="LocalAI.Text.Core" Version="0.7.2" />
<PackageVersion Include="LocalAI.Text.Core" Version="0.7.2" />
<PackageReference Include="LocalAI.Text.Core" />
paket add LocalAI.Text.Core --version 0.7.2
#r "nuget: LocalAI.Text.Core, 0.7.2"
#:package LocalAI.Text.Core@0.7.2
#addin nuget:?package=LocalAI.Text.Core&version=0.7.2
#tool nuget:?package=LocalAI.Text.Core&version=0.7.2
LocalAI.Text.Core
Core text processing infrastructure for LocalAI packages.
Overview
This package provides centralized tokenization and text processing utilities used by LocalAI packages that work with text data (Embedder, Reranker, Translator, etc.).
Features
- Tokenizer Factory: Creates tokenizers from model directories
- Multiple Tokenizer Types: WordPiece, BPE, SentencePiece support
- Vocabulary Loading: JSON and TXT format support
- Batch Encoding: Efficient batch processing with padding
Usage
This is an infrastructure package typically used internally by other LocalAI packages.
using LocalAI.Text;
// Create a tokenizer from model directory
var tokenizer = TokenizerFactory.CreateFromModelDirectory(modelPath);
// Encode text
var encoded = tokenizer.Encode("Hello, world!");
Console.WriteLine($"Tokens: {encoded.InputIds.Length}");
// Decode tokens
var decoded = tokenizer.Decode(encoded.InputIds, skipSpecialTokens: true);
Supported Tokenizers
| Type | Format | Models |
|---|---|---|
| WordPiece | tokenizer.json, vocab.txt | BERT, BGE |
| BPE | tokenizer.json, vocab.json | GPT-2, RoBERTa |
| SentencePiece | tokenizer.model | XLM-R, mBART |
| Product | Versions Compatible and additional computed target framework versions. |
|---|---|
| .NET | net10.0 is compatible. net10.0-android was computed. net10.0-browser was computed. net10.0-ios was computed. net10.0-maccatalyst was computed. net10.0-macos was computed. net10.0-tvos was computed. net10.0-windows was computed. |
-
net10.0
- LocalAI.Core (>= 0.7.2)
- Microsoft.ML.Tokenizers (>= 2.0.0)
NuGet packages (3)
Showing the top 3 NuGet packages that depend on LocalAI.Text.Core:
| Package | Downloads |
|---|---|
|
LocalAI.Embedder
A simple .NET library for local text embeddings with automatic model downloading from HuggingFace. Supports CUDA, DirectML, and CoreML GPU acceleration. |
|
|
LocalAI.Reranker
A lightweight, zero-configuration semantic reranker for .NET. Supports multiple cross-encoder models with automatic download, GPU acceleration, and HuggingFace caching. |
|
|
LocalAI.Translator
A lightweight, zero-configuration neural machine translator for .NET. Supports OPUS-MT models for high-quality bilingual translation. Start small. Download what you need. Run locally. |
GitHub repositories
This package is not used by any popular GitHub repositories.