Nomad changes

2026-06-01 23:40:55 +02:00
parent 72b1a0a6ed
commit b4c07d3693
5723 changed files with 1130655 additions and 0 deletions
--- a/docs/snippets/csharp/advanced/extract_with_config.cs
+++ b/docs/snippets/csharp/advanced/extract_with_config.cs
@@ -0,0 +1,98 @@
+using Kreuzberg;
+
+class Program
+{
+    static async Task Main()
+    {
+        try
+        {
+            var config = new ExtractionConfig
+            {
+                UseCache = true,
+                EnableQualityProcessing = true,
+                ForceOcr = false,
+
+                Ocr = new OcrConfig
+                {
+                    Backend = "tesseract",
+                    Language = "eng+fra",
+                    TesseractConfig = new TesseractConfig
+                    {
+                        Psm = 3,
+                        Oem = 3,
+                        MinConfidence = 0.8,
+                        Preprocessing = new ImagePreprocessingConfig
+                        {
+                            TargetDpi = 300,
+                            Denoise = true,
+                            Deskew = true,
+                            ContrastEnhance = true
+                        },
+                        EnableTableDetection = true
+                    }
+                },
+
+                PdfOptions = new PdfConfig
+                {
+                    ExtractImages = true,
+                    ExtractMetadata = true
+                },
+
+                Images = new ImageExtractionConfig
+                {
+                    ExtractImages = true,
+                    TargetDpi = 150,
+                    MaxImageDimension = 4096
+                },
+
+                Chunking = new ChunkingConfig
+                {
+                    MaxChars = 1000,
+                    MaxOverlap = 200,
+                    Preset = "default"
+                },
+
+                TokenReduction = new TokenReductionConfig
+                {
+                    Mode = "moderate",
+                    PreserveImportantWords = true
+                },
+
+                LanguageDetection = new LanguageDetectionConfig
+                {
+                    Enabled = true,
+                    MinConfidence = 0.8,
+                    DetectMultiple = false
+                },
+
+                Postprocessor = new PostProcessorConfig
+                {
+                    Enabled = true
+                }
+            };
+
+            var result = await KreuzbergLib.ExtractFileAsync(
+                "document.pdf",
+                config
+            );
+
+            Console.WriteLine($"Content length: {result.Content.Length}");
+            Console.WriteLine($"MIME type: {result.MimeType}");
+            Console.WriteLine($"Format type: {result.Metadata.FormatType}");
+
+            if (result.Tables.Any())
+            {
+                Console.WriteLine($"Found {result.Tables.Count} tables");
+            }
+
+            if (result.Chunks?.Any() == true)
+            {
+                Console.WriteLine($"Created {result.Chunks.Count} chunks");
+            }
+        }
+        catch (KreuzbergException ex)
+        {
+            Console.WriteLine($"Extraction error: {ex.Message}");
+        }
+    }
+}