Files
fil/docs/snippets/csharp/advanced_config.md

30 lines
798 B
Markdown
Raw Permalink Normal View History

2026-06-01 23:40:55 +02:00
```csharp title="C#"
using Kreuzberg;
var config = new ExtractionConfig
{
Ocr = new OcrConfig { Backend = "tesseract", Language = "eng+deu" },
Chunking = new ChunkingConfig { MaxChars = 1000, MaxOverlap = 100 },
TokenReduction = new TokenReductionConfig { Enabled = true },
LanguageDetection = new LanguageDetectionConfig
{
Enabled = true,
DetectMultiple = true
},
UseCache = true,
EnableQualityProcessing = true
};
var result = KreuzbergLib.ExtractFileSync("document.pdf", config);
foreach (var chunk in result.Chunks)
{
Console.WriteLine($"Chunk: {chunk.Content[..Math.Min(100, chunk.Content.Length)]}");
}
if (result.DetectedLanguages?.Count > 0)
{
Console.WriteLine($"Languages: {string.Join(", ", result.DetectedLanguages)}");
}
```