--- title: "Vision" canonical_url: "https://www.nutrient.io/api/csharp/vision/" md_url: "https://www.nutrient.io/api/csharp/vision.md" last_updated: "2026-10-08T08:55:57.713Z" description: "Provides machine learning and computer vision capabilities for document processing. Enables AI-powered document description and content extraction." --- Provides machine learning and computer vision capabilities for document processing. Enables AI-powered document description and content extraction. ```csharp using Nutrient; ``` The SDK creates this class through factory methods or other SDK objects. ## Methods ### Classify ```csharp public string Classify(ClassificationRequest request) ``` Classifies the document against the candidate labels carried by `request` (zero-shot) and exports the ranked result. Branch weights, supplied text, and the other knobs are read from `DocumentClassificationSettings` on the document's settings. The result is always JSON; `OutputFormat` is not consulted because only the JSON exporter serializes the classification result. **Parameters** | Name | Type | Description | | --------- | ----------------------------------------------------------------------- | ------------------------------------------------------------------ | | `request` | [`ClassificationRequest`](/api/csharp/requests/classification-request/) | The classification request carrying at least two candidate labels. | **Returns:** `string` - The exported content as a string (JSON), including the predicted label and ranked candidate probabilities. ### ClassifyText ```csharp public static string ClassifyText(ClassificationRequest request, string text) ``` Classifies caller-supplied text against the candidate labels carried by `request` (zero-shot) with no document. The text is scored directly by the text branch and the image branch is skipped, so nothing is rendered and no file is opened — use this when you already have the text (an email body, a database field, your own extraction pipeline) rather than a document on disk. **Parameters** | Name | Type | Description | | --------- | ----------------------------------------------------------------------- | ------------------------------------------------------------------ | | `request` | [`ClassificationRequest`](/api/csharp/requests/classification-request/) | The classification request carrying at least two candidate labels. | | `text` | `string` | The text to classify. | **Returns:** `string` - JSON with the predicted label and the ranked candidate probabilities. ### ClassifyToFile ```csharp public void ClassifyToFile(ClassificationRequest request, string outputPath) ``` Classifies the document against the candidate labels carried by `request` (zero-shot) and writes the exported result to a file. The result is always JSON; `OutputFormat` is not consulted because only the JSON exporter serializes the classification result. **Parameters** | Name | Type | Description | | ------------ | ----------------------------------------------------------------------- | ------------------------------------------------------------------ | | `request` | [`ClassificationRequest`](/api/csharp/requests/classification-request/) | The classification request carrying at least two candidate labels. | | `outputPath` | `string` | Path to the output file. | ### Describe ```csharp public string Describe() ``` Generates an AI-powered description of the document content. **Returns:** `string` - A string containing the document description. ### DetectForms ```csharp public string DetectForms() ``` Detects form fields on the document and exports the result. Output format is determined by `OutputFormat` (JSON or IR Lite). Each detected field carries its type and bounding box. To also assign AI semantic labels (e.g. "First name"), set `FormLabelingSettings.EnableAiLabeling` on the document's settings before calling — no separate method is needed. **Returns:** `string` - The exported content as a string (JSON or IR Lite JSON depending on settings). ### DetectFormsToFile ```csharp public void DetectFormsToFile(string outputPath) ``` Detects form fields on the document and writes the exported result to a file. Output format is determined by `OutputFormat` (JSON or IR Lite). **Parameters** | Name | Type | Description | | ------------ | -------- | ------------------------ | | `outputPath` | `string` | Path to the output file. | ### DetectLanguages ```csharp public string DetectLanguages() ``` Detects the language and text direction of the document, fully offline, and exports the result. Runs the offline cascade (Tesseract OSD for script → script-model OCR → fastText for the specific language) on every page and reports one detection per page. Output format is determined by `OutputFormat`. **Returns:** `string` - JSON with the predicted language, text direction, and per-page detections. ### DetectLanguagesText ```csharp public static string DetectLanguagesText(string text) ``` Detects the language of caller-supplied text, fully offline, with no document. CLD3 scores the text directly — nothing is rendered and no file is opened. Use this when you already have the text (an email body, a database field, your own extraction pipeline) rather than a document on disk. **Parameters** | Name | Type | Description | | ------ | -------- | ----------------------------------- | | `text` | `string` | The text to detect the language of. | **Returns:** `string` - JSON with the predicted language and text direction. ```csharp public static string DetectLanguagesText(string text, DocumentSettings settings) ``` Detects the language(s) of caller-supplied text, fully offline, with explicit settings — raise `MaxLanguages` to report more than one language in mixed text. Without settings the dominant language only is returned. **Parameters** | Name | Type | Description | | ---------- | ---------------------------------------------------------------------- | ------------------------------------------------------------------------- | | `text` | `string` | The text to detect the language(s) of. | | `settings` | [`DocumentSettings`](/api/csharp/settings/document/document-settings/) | Document settings; `MaxLanguages` bounds how many languages are reported. | **Returns:** `string` - JSON with the predicted language(s) and text direction. ### DetectLanguagesToFile ```csharp public void DetectLanguagesToFile(string outputPath) ``` Detects the language and text direction of the document, fully offline, and writes the exported result to a file. Output format is determined by `OutputFormat`. **Parameters** | Name | Type | Description | | ------------ | -------- | ------------------------ | | `outputPath` | `string` | Path to the output file. | ### ExtractContent ```csharp public string ExtractContent() ``` Extracts structured content from the document using machine vision processing. The pipeline used is determined by the `Engine` setting and the output format by `OutputFormat`. **Returns:** `string` - The exported content as a string (JSON, Markdown, or IR Lite JSON depending on settings). ```csharp public string ExtractContent(DocumentLayoutJsonExportSettings settings) ``` Extracts structured content from the document using machine vision processing with custom export settings. The pipeline used is determined by the `Engine` setting. **Parameters** | Name | Type | Description | | ---------- | ---------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------- | | `settings` | [`DocumentLayoutJsonExportSettings`](/api/csharp/settings/vision/advanced/document-layout-json-export-settings/) | Settings controlling what to include in the JSON output. | **Returns:** `string` - A JSON string containing the extracted content structure. ### ExtractContentToFile ```csharp public void ExtractContentToFile(string outputPath) ``` Extracts structured content from the document and writes it to a file. The pipeline used is determined by the `Engine` setting and the output format by `OutputFormat`. **Parameters** | Name | Type | Description | | ------------ | -------- | ------------------------ | | `outputPath` | `string` | Path to the output file. | ```csharp public void ExtractContentToFile(string outputPath, DocumentLayoutJsonExportSettings settings) ``` Extracts structured content from the document and saves it to a JSON file with custom settings. **Parameters** | Name | Type | Description | | ------------ | ---------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------- | | `outputPath` | `string` | Path to the output JSON file. | | `settings` | [`DocumentLayoutJsonExportSettings`](/api/csharp/settings/vision/advanced/document-layout-json-export-settings/) | Settings controlling what to include in the JSON output. | ### ExtractStructured ```csharp public string ExtractStructured(StructuredExtractionRequest request) ``` Extracts structured data from the document, shaped to the JSON Schema carried by the `request`'s `{"schema":...}` envelope. The document is first read by the extraction pipeline selected by `Engine`, then an AI model fills the schema from the recognized content. Provider, model, endpoint, and confidence reporting are driven by `AiProcessingSettings` on the document's settings. **Parameters** | Name | Type | Description | | --------- | ------------------------------------------------------------------------------------ | ----------------------------------------------------------------------------------------- | | `request` | [`StructuredExtractionRequest`](/api/csharp/requests/structured-extraction-request/) | The extraction request carrying the schema envelope (required) and optional instructions. | **Returns:** `string` - A JSON string with two top-level nodes: `extraction` (the schema-shaped extracted fields) and `metadata` (per-field source locations and grounding labels). ### ExtractStructuredToFile ```csharp public void ExtractStructuredToFile(StructuredExtractionRequest request, string outputPath) ``` Extracts structured data from the document, shaped to the JSON Schema carried by the `request`'s `{"schema":...}` envelope, and writes the JSON result to a file. See `ExtractStructured` for the result shape. **Parameters** | Name | Type | Description | | ------------ | ------------------------------------------------------------------------------------ | ----------------------------------------------------------------------------------------- | | `request` | [`StructuredExtractionRequest`](/api/csharp/requests/structured-extraction-request/) | The extraction request carrying the schema envelope (required) and optional instructions. | | `outputPath` | `string` | Path to the output file. | ### GenerateSchema ```csharp public static string GenerateSchema(SchemaGenerationRequest request) ``` Generates a JSON Schema for a class of documents using a vision model, with default document settings. The schema is designed for downstream LLM structured-output extraction tasks: it is hard-clamped to the knobs in `SchemaGenerationSettings` and to the target structured-output dialect selected there, so the same call with the same settings always yields a schema the target accepts. **Parameters** | Name | Type | Description | | --------- | ---------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `request` | [`SchemaGenerationRequest`](/api/csharp/requests/schema-generation-request/) | The schema generation request: the document type the schema must represent (required), an optional natural-language requirement, and up to five example documents used as grounding samples. | **Returns:** `string` - A JSON envelope object with a `schema` property (the generated JSON Schema) and a `constraints` array of cross-field rules in standard JsonLogic. The array is empty unless `SchemaGenerationSettings.IncludeConstraints` is enabled. ```csharp public static string GenerateSchema(SchemaGenerationRequest request, DocumentSettings settings) ``` Generates a JSON Schema for a class of documents using a vision model, with explicit document settings. The schema is designed for downstream LLM structured-output extraction tasks: it is hard-clamped to the knobs in `SchemaGenerationSettings` and to the target structured-output dialect selected there, so the same call with the same settings always yields a schema the target accepts. The vision model connection is resolved from `Provider` and the matching provider settings class — the same way `Describe` is configured. **Parameters** | Name | Type | Description | | ---------- | ---------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `request` | [`SchemaGenerationRequest`](/api/csharp/requests/schema-generation-request/) | The schema generation request: the document type the schema must represent (required), an optional natural-language requirement, and up to five example documents used as grounding samples. | | `settings` | [`DocumentSettings`](/api/csharp/settings/document/document-settings/) | Document settings carrying `SchemaGenerationSettings` (schema shape and target dialect) and the vision model connection. | **Returns:** `string` - A JSON envelope object with a `schema` property (the generated JSON Schema) and a `constraints` array of cross-field rules in standard JsonLogic. The array is empty unless `SchemaGenerationSettings.IncludeConstraints` is enabled. ### GenerateSchemaToFile ```csharp public static void GenerateSchemaToFile(SchemaGenerationRequest request, string outputPath) ``` Generates a JSON Schema for a class of documents using a vision model and writes it to a file, with default document settings. **Parameters** | Name | Type | Description | | ------------ | ---------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `request` | [`SchemaGenerationRequest`](/api/csharp/requests/schema-generation-request/) | The schema generation request: the document type the schema must represent (required), an optional natural-language requirement, and up to five example documents used as grounding samples. | | `outputPath` | `string` | Path to the output file receiving the JSON Schema. | ```csharp public static void GenerateSchemaToFile(SchemaGenerationRequest request, DocumentSettings settings, string outputPath) ``` Generates a JSON Schema for a class of documents using a vision model and writes it to a file, with explicit document settings. **Parameters** | Name | Type | Description | | ------------ | ---------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `request` | [`SchemaGenerationRequest`](/api/csharp/requests/schema-generation-request/) | The schema generation request: the document type the schema must represent (required), an optional natural-language requirement, and up to five example documents used as grounding samples. | | `settings` | [`DocumentSettings`](/api/csharp/settings/document/document-settings/) | Document settings carrying `SchemaGenerationSettings` (schema shape and target dialect) and the vision model connection. | | `outputPath` | `string` | Path to the output file receiving the JSON Schema. | ### Set ```csharp public static Vision Set(Document document) ``` Creates a Vision instance for the specified document. **Parameters** | Name | Type | Description | | ---------- | ----------------------------------- | -------------------------------------------------- | | `document` | [`Document`](/api/csharp/document/) | The document to analyze using vision capabilities. | **Returns:** [`Vision`](/api/csharp/vision/) - A Vision instance ready to perform analysis on the document. **Throws:** [`NutrientException`](/api/csharp/exceptions/nutrient-exception/) - Thrown when document is null. ### Split ```csharp public string Split() ``` Splits a merged document into its constituent sub-documents (page-stream segmentation) and exports the result. Every page is scored for whether it starts a new sub-document — fusing a per-page image signal with the page's text — and the contiguous page ranges are returned. The threshold and the other knobs are read from `DocumentSplitSettings` on the document's settings. The result is always JSON; `OutputFormat` is not consulted because only the JSON exporter serializes the split result. **Returns:** `string` - The exported content as a string (JSON), carrying the detected sub-document segments (1-based inclusive page ranges with their boundary confidence). ### SplitToFile ```csharp public void SplitToFile(string outputPath) ``` Splits a merged document into its constituent sub-documents (page-stream segmentation) and writes the exported result to a file. The result is always JSON; `OutputFormat` is not consulted because only the JSON exporter serializes the split result. **Parameters** | Name | Type | Description | | ------------ | -------- | ------------------------ | | `outputPath` | `string` | Path to the output file. | ### Warmup ```csharp public void Warmup() ``` Preloads (warms up) all resources needed for vision processing. This downloads all model files based on the document's VisionSettings before execution. Call this to avoid download delays during ExtractContent(). ## Resource management ```csharp public void Dispose() ``` `Vision` implements `IDisposable` and owns native resources. Always call `Dispose()` or use a C# `using` declaration: it is not released automatically. --- ## Related pages - [Csharp](/api/csharp.md) - [Data Extraction](/api/csharp/data-extraction.md) - [Document](/api/csharp/document.md) - [License](/api/csharp/license.md) - [Query](/api/csharp/query.md) - [Telemetry](/api/csharp/telemetry.md)