LogoLogo
HomeNewsSupportVideos
  • Welcome
  • Wisej.NET
  • Concepts
    • Getting Started
    • General Concepts
    • Architecture
    • Extensibility
    • AI Providers
    • Vector Databases
    • Usage Metrics
    • Logging & Error Handling
  • Markup
  • Components
    • API
      • SmartAdapter
        • SmartAudioTTSAdapter
        • SmartAudioWhisperAdapter
        • SmartCalendarAdapter
        • SmartChartAdapter
        • SmartChartJS3Adapter
        • SmartChatBoxAdapter
        • SmartComboBoxAdapter
        • SmartCopilotAdapter
        • SmartDataEntryAdapter
        • SmartDocumentAdapter
        • SmartFullCalendarAdapter
        • SmartObjectAdapter
        • SmartPictureBoxAdapter
        • SmartQueryAdapter
        • SmartRealtimeAdapter
        • SmartReportAdapter
        • SmartTextBoxAdapter
        • SmartAdapter.ExtendsAttribute
        • SmartAdapter.FieldNameAttribute
        • SmartAdapter.FieldPromptAttribute
        • SmartAdapter.FieldRectangleAttribute
        • SmartAdapter.WorksWithAttribute
      • SmartEndpoint
        • AmazonBedrockEndpoint
        • AnthropicEndpoint
        • AzureAIEndpoint
        • CerebrasEndpoint
        • DeepSeekEndpoint
        • GoogleAIEndpoint
        • GroqCloudEndpoint
        • GroqCloudEndpointWhisper
        • HuggingFaceEndpoint
        • HuggingFaceJavaScriptEndpoint
        • LocalAIEndpoint
        • LocalAIEndpointImageGen
        • LocalAIEndpointTTS
        • LocalAIEndpointWhisper
        • NvidiaAIEndpoint
        • OllamaEndpoint
        • OpenAIEndpoint
        • OpenAIEndpointDallE
        • OpenAIEndpointRealtime
        • OpenAIEndpointTTS
        • OpenAIEndpointWhisper
        • SambaNovaEndpoint
        • SmartHttpEndpoint
        • TogetherAIEndpoint
        • XAIEndpoint
        • SmartEndpoint.Metrics
        • SmartEndpoint.Response
      • SmartExtensions
      • SmartHub
        • SmartSession.ConvertParameterEventArgs
        • SmartSession.ConvertParameterEventHandler
        • SmartSession.ErrorEventArgs
        • SmartSession.ErrorEventHandler
        • SmartSession.InvokeToolEventArgs
        • SmartSession.InvokeToolEventHandler
        • SmartSession.MessagesEventArgs
        • SmartSession.MessagesEventHandler
      • SmartObject
      • SmartPrompt
        • SmartAgentPrompt
        • SmartParallelPrompt
        • SmartPrompt.Parameter
        • SmartSession.ConvertParameterEventArgs
        • SmartSession.ConvertParameterEventHandler
        • SmartSession.ErrorEventArgs
        • SmartSession.ErrorEventHandler
        • SmartSession.InvokeToolEventArgs
        • SmartSession.InvokeToolEventHandler
        • SmartSession.MessagesEventArgs
        • SmartSession.MessagesEventHandler
      • SmartRealtimeSession
      • SmartSession
        • SmartSession.ConvertParameterEventArgs
        • SmartSession.ConvertParameterEventHandler
        • SmartSession.ErrorEventArgs
        • SmartSession.ErrorEventHandler
        • SmartSession.InvokeToolEventArgs
        • SmartSession.InvokeToolEventHandler
        • SmartSession.Message
        • SmartSession.MessageCollection
        • SmartSession.MessageRole
        • SmartSession.MessagesEventArgs
        • SmartSession.MessagesEventHandler
        • SmartSession.TrimmingStrategy
      • SmartTool
        • SmartTool.IToolProvider
        • SmartTool.ToolAttribute
        • SmartTool.ToolContext
      • Markup
        • MarkupExtensions
      • Controls
        • UVLightOverlay
      • Embeddings
        • EmbeddedDocument
        • Embedding
        • Matches
        • Metadata
      • Helpers
        • ApiKeys
        • Markdown
        • TextTokenizer
      • Services
        • DefaultSessionTrimmingService
        • IDocumentConversionService
          • DefaultDocumentConversionService
        • IEmbeddingGenerationService
          • DefaultEmbeddingGenerationService
          • HuggingFaceEmbeddingGenerationService
        • IEmbeddingStorageService
          • AzureAISearchEmbeddingStorageService
          • ChromaEmbeddingStorageService
          • FileSystemEmbeddingStorageService
          • MemoryEmbeddingStorageService
          • PineconeEmbeddingStorageService
          • QdrantEmbeddingStorageService
        • IHttpClientService
          • DefaultHttpClientService
        • ILoggerService
          • DefaultLoggerService
        • IOCRService
          • DefaultOCRService
        • IRerankingService
          • DefaultRerankingService
          • LocalAIRerankingService
          • PineconeRerankingService
        • ISessionTrimmingService
          • DefaultSessionTrimmingService
        • ITextSplitterService
          • RecursiveCharacterTextSplitterService
          • TextSplitterServiceBase
        • ITokenizerService
          • DefaultTokenizerService
        • IWebSearchService
          • BingWebSearchService
          • BraveWebSearchService
          • GoogleWebSearchService
      • Tools
        • ArxivTools
        • ChartJS3Tools
        • DatabaseTools
        • DataTableFilterTools
        • DocumentSearchTools
        • DocumentTools
        • FullCalendarTools
        • IToolsContainer
        • MathTools
        • ToolsContainer
        • UtilityTools
        • WebSearchTools
    • Built-in Services
      • IOCRService
      • ILoggerService
      • ITextSplitterService
      • ITokenizerService
      • IHttpClientService
      • IWebSearchService
      • IRerankingService
      • ISessionTrimmingService
      • IDocumentConversionService
      • IEmbeddingStorageService
      • IEmbeddingGenerationService
    • Built-in SmartTools
      • ToolsContainer
      • MathTools
      • UtilityTools
      • DatabaseTools
      • DocumentTools
      • DocumentSearchTools
      • WebSearchTools
      • ChartJS3Tools
      • FullCalendarTools
    • Built-in SmartAdapters
      • SmartAdapter
      • SmartAudioTTSAdapter
      • SmartAudioWhisperAdapter
      • SmartCalendarAdapter
      • SmartChartAdapter
      • SmartChartJS3Adapter
      • SmartChatBoxAdapter
      • SmartComboBoxAdapter
      • SmartCopilotAdapter
      • SmartDataEntryAdapter
      • SmartDocumentAdapter
      • SmartFullCalendarAdapter
      • SmartObjectAdapter
      • SmartPictureBoxAdapter
      • SmartQueryAdapter
      • SmartRealtimeAdapter
      • SmartReportAdapter
      • SmartTextBoxAdapter
    • Configure Services
    • Using SmartHub
    • Using SmartTools
    • Using SmartPrompt
    • Using SmartSession
    • Using SmartRealTimeAdapter
    • UVLightOverlay Control
Powered by GitBook
On this page
  • Methods
  • Convert(stream, fileType, metadata, iterator)
  • Implemented By
Export as PDF
  1. Components
  2. API
  3. Services

IDocumentConversionService

Wisej.AI.Services.IDocumentConversionService

PreviousDefaultSessionTrimmingServiceNextDefaultDocumentConversionService

Last updated 5 days ago

Namespace: Wisej.AI.Services

Assembly: Wisej.AI (3.5.0.0)

Represents a service interface for converting documents from one format to another.

public interface IDocumentConversionService
Public Interface IDocumentConversionService

Implementations of this interface provide functionality to convert documents that are provided as a stream. This allows for flexibility in handling documents from various sources such as files or network streams. Usage of this interface requires specifying the desired output file type and optionally providing metadata for the document being converted.

Methods

Convert(stream, fileType, metadata, iterator)

Converts a document from a provided stream to plain text.

Parameter
Type
Description

stream

The stream containing the document to be converted. It must be readable and positioned at the start of the document.

fileType

The format of the input stream represented as a string. It should be the file type, i.e.: "pdf", "docx", "html", ...

An optional output parameter to receive metadata about the document. If not provided, the default is null.

An optional function to process each page or paragraph or section of the document being converted.

Returns: . An string representing the converted document.

This method reads a document of type fileType from the specified stream and convert it to an array strings representing either line, paragraphs or pages, depending on the conversion implementation. If the metadata parameter is provided, this method will output additional information about the document, such as the title, author, subject, pages, etc. If the iterator parameter is provided, this method will call it for each section of the document it is converting and will use the returned string value to compose the converted text. Example usage:


using System.IO;

public class DocumentConverter
{
private readonly IDocumentConversionService _conversionService;

public DocumentConverter(IDocumentConversionService conversionService)
{
_conversionService = conversionService;
}

public void ConvertDocument()
{
using (FileStream fileStream = new FileStream("input.docx", FileMode.Open, FileAccess.Read))
{
string convertedDocument = _conversionService.Convert(fileStream, "pdf");
// Use the converted document
}
}
}

Throws:

Implemented By

Name
Description

Provides functionality to convert documents from various formats into text representations.

metadata

iterator

Thrown when stream or fileType is null.

ArgumentNullException
Stream
String
Metadata
Func<String, String>
DefaultDocumentConversionService
String