Merge pull request #444 from tryAGI/bot/auto-format_202408260517

style:Run dotnet format

src/DocumentLoaders/Word/src/ExcelLoader.cs

@@ -14,11 +14,11 @@ public async Task<IReadOnlyCollection<Document>> LoadAsync(
         dataSource = dataSource ?? throw new ArgumentNullException(nameof(dataSource));
 
         using var stream = await dataSource.GetStreamAsync(cancellationToken).ConfigureAwait(false);
-        
+
         var markdowns = ExcelToMarkdown.Convert(stream, firstRowIsHeader);
 
         var metadata = settings.CollectMetadataIfRequired(dataSource);
-        
+
         return markdowns
             .Select(x => new Document(x.Value, metadata: metadata?.With("Worksheet", x.Key)))
             .ToArray();

src/DocumentLoaders/Word/src/Helpers.ExcelToMarkdown.cs

@@ -34,10 +34,10 @@ public static IList<KeyValuePair<string, string>> Convert(
             {
                 continue;
             }
-            
+
             var isFirstRow = true;
             var builder = new StringBuilder();
-            
+
             foreach (var row in (document.WorkbookPart.GetPartById(sheet.Id.Value) as WorksheetPart)?.Worksheet
                      .GetFirstChild<SheetData>()?
                      .Descendants<Row>() ?? [])
@@ -60,16 +60,16 @@ public static IList<KeyValuePair<string, string>> Convert(
                         .ToList()) + " |");
                 }
             }
-            
+
             markdowns.Add(new KeyValuePair<string, string>(
-                sheet.Name?.Value  ?? $"Sheet{markdowns.Count}",
+                sheet.Name?.Value ?? $"Sheet{markdowns.Count}",
                 builder.ToString()));
         }
-        
-        
+
+
         return markdowns;
     }
-    
+
     private static string GetCellValue(SharedStringTable? table, Cell cell)
     {
         var value = cell.CellValue?.InnerText ?? string.Empty;
@@ -80,7 +80,7 @@ private static string GetCellValue(SharedStringTable? table, Cell cell)
         {
             return table.ChildElements[index].InnerText;
         }
-        
+
         return value;
     }
 }

src/Helpers/GenerateDocs/Program.cs

@@ -74,19 +74,19 @@ static async Task ConvertTestToMarkdown(string path, string outputFolder)
     {
         return;
     }
-    
+
     var usings = string.Join('\n', lines
         .Where(x => x.StartsWith("using"))
         .ToArray());
-    
+
     var start = lines.IndexOf("    {");
     var end = lines.IndexOf("    }");
     lines = lines
         .GetRange(start + 1, end - start - 1)
         .Where(x => !x.Contains(".Should()"))
         .Select(x => x.StartsWith("        ") ? x[8..] : x)
         .ToList();
-    
+
     const string commentPrefix = "//// ";
     var markdown = string.Empty;
     var completeCode = string.Join('\n', lines.Where(x => !x.StartsWith(commentPrefix)));
@@ -101,7 +101,7 @@ static async Task ConvertTestToMarkdown(string path, string outputFolder)
             {
                 i++;
             }
-            
+
             var comment = string.Join('\n', lines
                 .GetRange(startGroup, i - startGroup)
                 .Select(x => x[commentPrefix.Length..]));
@@ -120,14 +120,14 @@ static async Task ConvertTestToMarkdown(string path, string outputFolder)
                 isFirstCode = false;
                 markdown += Environment.NewLine + usings + Environment.NewLine;
             }
-            
+
             markdown += $@"
 {string.Join('\n', lines
     .GetRange(startGroup, i - startGroup)).Trim()}
 ```" + '\n';
         }
     }
-    
+
     markdown = anyComment ? @"`Scroll till the end of the page if you just want code`  
 " + markdown : markdown;
     markdown += anyComment ? @$"

src/Meta/test/WikiTests.AgentWithOllamaReact.cs

@@ -27,7 +27,7 @@ public async Task AgentWithOllamaReact()
         //// ## Using ReAct with Google search
         //// 
         //// Now you should have all necessary to connect your LLM to Google search
-        
+
         // var provider = new OllamaProvider(
         //     options: new RequestOptions
         //     {
@@ -55,7 +55,7 @@ public async Task AgentWithOllamaReact()
                 .UseTool(searchTool); // add the google search tool
 
         await chain.RunAsync();
-        
+
         //// Lets run it and see the output:
         //// As you can see, instead of giving answer right away, the model starts to think on it
         //// ```

src/Meta/test/WikiTests.BuildingChatWithOpenAi.cs

@@ -60,7 +60,7 @@ public async Task BuildingChatWithOpenAi()
             Console.Write("AI: ");
             Console.WriteLine(res);
         }
-        
+
         //// Now you can run the program and try to chat with it.
         //// 
         //// The final output will look like this:

src/Meta/test/WikiTests.GettingStarted.cs

@@ -48,27 +48,27 @@ public async Task GettingStarted()
         //// ***
         //// 
         //// So, finally, let's write some code!
-        
+
         // get model path
         var modelPath = await HuggingFaceModelDownloader.GetModelAsync(
             repository: "TheBloke/Thespis-13B-v0.5-GGUF",
             fileName: "thespis-13b-v0.5.Q2_K.gguf",
             version: "main");
-        
+
         //// This line will download the model and save it locally for future usage. After model is downloaded it will return path to the *.gguf file. 
         //// _**You can manually download any model you want and insert path to it directly. Without using HuggingFaceModelDownloader.**_
         //// 
         //// Now it's time to load our model into memory:
 
         // load model
         var model = LLamaSharpModelInstruction.FromPath(modelPath).UseConsoleForDebug();
-        
+
         //// Now let's build a chain!
         //// 
         //// # Building a chain
         //// 
         //// This is minimal chain to make LLM work:
-        
+
         // building a chain
         var prompt = @"
 You are an AI assistant that greets the world.
@@ -80,7 +80,7 @@ You are an AI assistant that greets the world.
             | LLM(model, inputKey: "prompt");
 
         await chain.RunAsync();
-        
+
         //// We can see here 2 chains(or links) working together: Set and LLM.
         //// 
         //// * Set - setting value for the _chain context variable **prompt**_

src/Meta/test/WikiTests.HowToUseOpenAiProvider.cs

@@ -21,7 +21,7 @@ public async Task HowToUseOpenAiProvider()
         var result = await chain.RunAsync("text", CancellationToken.None);  // execute chain and get `text` context variable
         Console.WriteLine(result);
         // Hello! How can I assist you today?
-        
+
         //// `inputKey` and `outputKey` here is more for understanding of what goes where. They have default values and can be omitted. Also there is classes like `Gpt35TurboModel` for simplicity.
 
         //// ## Additional options

src/Meta/test/WikiTests.ImageGenerationWithOllamaAndStableDiffusion.cs

@@ -72,7 +72,7 @@ public async Task ImageGenerationWithOllamaAndStableDiffusion()
         //// I took it from [here](https://github.com/vicuna-tools/Stablediffy/blob/main/Stablediffy.txt) with some minor modifications.  
         //// Basically, we are showing some examples so model could understand a principle of prompt generation. You can play around with examples and instructions to better match your preferences.  
         //// Now let's build a chain!  
-        
+
         var template =
     @"[INST]Transcript of a dialog, where the User interacts with an Assistant named Stablediffy. Stablediffy knows much about prompt engineering for stable diffusion (an open-source image generation software). The User asks Stablediffy about prompts for stable diffusion Image Generation. 
 
@@ -102,7 +102,7 @@ public async Task ImageGenerationWithOllamaAndStableDiffusion()
 
         // run the chain
         await chain.RunAsync();
-        
+
         //// If everything done correctly - you should have `image.png` in your bin directory.
     }
 }

src/Meta/test/WikiTests.RagWithOpenAiOllama.cs

@@ -54,14 +54,14 @@ public async Task RagWithOpenAiOllama()
         //// 
         //// ### OpenAI
         //// To use this chat and embedding model, you will need an API key from OpenAI.  This has non-zero cost.
-        
+
         // prepare OpenAI embedding model
         var provider = new OpenAiProvider(apiKey:
             Environment.GetEnvironmentVariable("OPENAI_API_KEY") ??
             throw new InvalidOperationException("OPENAI_API_KEY key is not set"));
         var embeddingModel = new TextEmbeddingV3SmallModel(provider);
         var llm = new OpenAiLatestFastChatModel(provider);
-        
+
         //// ### Ollama
         //// To use this chat and embedding model, you will need an Ollama instance running.
         //// This is free, assuming it is running locally--this code assumes it is available at https://localhost:11434.
@@ -82,7 +82,7 @@ public async Task RagWithOpenAiOllama()
         var vectorCollection = await vectorDatabase.AddDocumentsFromAsync<PdfPigPdfLoader>(
             embeddingModel,
             dimensions: 1536, // Should be 1536 for TextEmbeddingV3SmallModel
-            // First, specify the source to index.
+                              // First, specify the source to index.
             dataSource: DataSource.FromPath("E:\\AI\\Datasets\\Books\\Harry-Potter-Book-1.pdf"),
             collectionName: "harrypotter",
             // Second, configure how to extract chunks from the bigger document.
@@ -131,7 +131,7 @@ public async Task RagWithOpenAiOllama()
         var result = await chain.RunAsync("text", CancellationToken.None);
 
         Console.WriteLine(result);
-        
+
         //// We are done! Since we previously registered for events on the completion model, the output will be printed automatically.
         //// 
         //// # Example

src/Meta/test/WikiTests.UsingChainOutput.cs

@@ -33,24 +33,24 @@ You are an AI assistant that greets the world.
         //// Almost every possible link in a chain are having having at least one input and output.
         //// 
         //// Look here:
-        
+
         var chain =
             Set(prompt, outputKey: "prompt")
             | LLM(model, inputKey: "prompt", outputKey: "result");
-        
+
         //// This means that, after link `Set` get executed, we are storring it's result into "prompt" variable inside of chain context.
         //// In its turn, link `LLM` gets "prompt" variable from chain context and uses it's as input.
         //// 
         //// `LLM` link also has output key argument. Let's use it to save the result of llm.
 
         var result = await chain.RunAsync("result", CancellationToken.None);
-        
+
         //// Now the `LLM` link saves it's result into "result" variable inside of chain context. But how do we extract it from there?
         //// 
         //// `chain.Run()` method has an optional argument "resultKey". This allows you to specify variable inside of chain context to return as a result.
-        
+
         Console.WriteLine(result);
-        
+
         //// Output:
         //// ```
         //// Hello, World! How can I help you today?