adding File Content Extraction Services ...

Interfaces/IXFileContentExtractor.cs

@@ -0,0 +1,26 @@
+using System.IO;
+using System.Threading;
+using System.Threading.Tasks;
+
+namespace xAiApi.Interfaces
+{
+    /// <summary>
+    /// a Service for Extracting File Content ...
+    /// </summary>
+    public interface IXFileContentExtractor
+    {
+        /// <summary>
+        /// Check if this extractor supports the specified MIME type ...
+        /// </summary>
+        bool CanExtract(string mimeType);
+
+        /// <summary>
+        /// Extract text content from file stream ...
+        /// </summary>
+        Task<string> ExtractAsync(
+            Stream fileStream,
+            string mimeType,
+            CancellationToken cancellationToken = default
+        );
+    }
+}

Providers/XCompositeFileContentExtractor.cs

@@ -0,0 +1,68 @@
+using System.IO;
+using System.Linq;
+using System.Threading;
+using xAiApi.Interfaces;
+using xCommons.Extensions;
+using xExceptions.Constants;
+using System.Threading.Tasks;
+using System.Collections.Generic;
+
+namespace xAiApi.Providers
+{
+    /// <summary>
+    /// Composite extractor that delegates to appropriate extractor 
+    /// based on MIME type ...
+    /// </summary>    
+    public class XCompositeFileContentExtractor : IXFileContentExtractor
+    {
+        //
+        private readonly IEnumerable<IXFileContentExtractor> extractors;
+
+        public XCompositeFileContentExtractor(
+            IEnumerable<IXFileContentExtractor> extractors
+        )
+        {
+            this.extractors = extractors;
+        }
+
+        /// <summary>
+        /// Check if this extractor supports the specified MIME type ...
+        /// </summary>
+        public bool CanExtract(string mimeType)
+        {
+            return extractors.Any(e => e.CanExtract(mimeType));
+        }
+
+        /// <summary>
+        /// Extract text content from file stream ...
+        /// </summary>
+        public async Task<string> ExtractAsync(
+            Stream fileStream,
+            string mimeType,
+            CancellationToken cancellationToken = default
+        )
+        {
+            //
+            var extractor = extractors
+                .FirstOrDefault(e => e.CanExtract(mimeType));
+            if (extractor.IsNull())
+            {
+                //
+                XException.NotAllowed.Throw(
+                    $"Unsupported file type: {mimeType}"
+                );
+            }
+
+            //
+            var result = await extractor
+                .ExtractAsync(
+                    mimeType: mimeType,
+                    fileStream: fileStream,
+                    cancellationToken: cancellationToken
+                );
+
+            //
+            return result;
+        }
+    }
+}

Providers/XPdfContentExtractor.cs

@@ -0,0 +1,69 @@
+using System;
+using System.IO;
+using System.Linq;
+using System.Text;
+using UglyToad.PdfPig;
+using System.Threading;
+using xAiApi.Interfaces;
+using System.Threading.Tasks;
+
+namespace xAiApi.Providers
+{
+    /// <summary>
+    /// Extracts content from PDF files using PdfPig ...
+    /// </summary>    
+    public class XPdfContentExtractor : IXFileContentExtractor
+    {
+        /// <summary>
+        /// Supported MIME Types ...
+        /// </summary>
+        private static readonly string[] SupportedMimeTypes =
+        [
+            "application/pdf"
+        ];
+
+        /// <summary>
+        /// Check if this extractor supports the specified MIME type ...
+        /// </summary>
+        public bool CanExtract(string mimeType)
+        {
+            //
+            return SupportedMimeTypes.Contains(
+                mimeType?.ToLowerInvariant() ?? string.Empty
+            );
+        }
+
+        /// <summary>
+        /// Extract text content from file stream ...
+        /// </summary>
+        public async Task<string> ExtractAsync(
+            Stream fileStream,
+            string mimeType,
+            CancellationToken cancellationToken = default
+        )
+        {
+            //
+            var result = await Task.Run(() =>
+            {
+                //
+                var sb = new StringBuilder();
+                using var document = PdfDocument.Open(fileStream);
+                foreach (var page in document.GetPages())
+                {
+                    //
+                    var text = page.Text;
+
+                    //
+                    sb.AppendLine(text);
+                    sb.AppendLine();
+                }
+
+                //
+                return sb.ToString();
+            }, cancellationToken);
+
+            //
+            return result;
+        }
+    }
+}

Providers/XPlainTextContentExtractor.cs

@@ -0,0 +1,54 @@
+using System;
+using System.IO;
+using System.Linq;
+using System.Threading;
+using xAiApi.Interfaces;
+using System.Threading.Tasks;
+
+namespace xAiApi.Providers
+{
+    /// <summary>
+    /// Extracts content from plain text files (txt, md, csv, json, xml) ...
+    /// </summary>    
+    public class XPlainTextContentExtractor : IXFileContentExtractor
+    {
+        /// <summary>
+        /// Supported MIME Types ...
+        /// </summary>
+        private static readonly string[] SupportedMimeTypes =
+        [
+            "text/plain",
+            "text/markdown",
+            "text/csv",
+            "text/html",
+            "text/xml",
+            "application/json",
+            "application/xml"
+        ];
+
+        /// <summary>
+        /// Check if this extractor supports the specified MIME type ...
+        /// </summary>
+        public bool CanExtract(string mimeType)
+        {
+            //
+            return SupportedMimeTypes.Contains(
+                mimeType?.ToLowerInvariant() ?? string.Empty
+            );
+        }
+
+        /// <summary>
+        /// Extract text content from file stream ...
+        /// </summary>
+        public async Task<string> ExtractAsync(
+            Stream fileStream,
+            string mimeType,
+            CancellationToken cancellationToken = default
+        )
+        {
+            //
+            using var reader = new StreamReader(fileStream);
+            return await reader.ReadToEndAsync();
+        }
+    }
+}

Startup.cs

@@ -185,6 +185,12 @@ namespace xAiApi
             // Register XAiApi Configuration ...
             services.AddXAiApiConfiguration(Configuration);
 
+            //
+            // Register File Content Extractors ...
+            services.AddSingleton<IXFileContentExtractor, XPdfContentExtractor>();
+            services.AddSingleton<IXFileContentExtractor, XPlainTextContentExtractor>();
+            services.AddSingleton<IXFileContentExtractor, XCompositeFileContentExtractor>();
+
             //
             // Register Default Ai Service ...
             services.AddScoped<IXDefaultAiService, XDefaultAiService>();

xAiApi.csproj

@@ -24,8 +24,7 @@
 
   <!-- Icon Handling -->
   <ItemGroup>
-    <None Include="../../Resources/Images/favicon.png" Link="icon.png" Pack="true"
+    <None Include="../../Resources/Images/favicon.png" Link="icon.png" Pack="true" PackagePath="\icon.png" />
-      PackagePath="\icon.png" />
   </ItemGroup>
 
   <!-- Local Modules -->
@@ -48,6 +47,7 @@
   <!-- Dependencies -->
   <ItemGroup>
     <PackageReference Include="OllamaSharp" Version="5.4.25" />
+    <PackageReference Include="UglyToad.PdfPig" Version="1.7.0-custom-5" />
     <PackageReference Include="Microsoft.AspNetCore.Mvc.NewtonsoftJson" Version="3.1.11" />
     <PackageReference Include="IdentityModel.AspNetCore.OAuth2Introspection" Version="5.0.0" />
   </ItemGroup>