Merge branch 'SciSharp:master' into feature-llamareranker

Author: nipeone

LLama.Unittest/LLamaEmbedderTests.cs

@@ -45,8 +45,8 @@ private async Task CompareEmbeddings(string modelPath)
         var generator = (IEmbeddingGenerator<string, Embedding<float>>)embedder;
         Assert.NotNull(generator.GetService<EmbeddingGeneratorMetadata>());
         Assert.Equal(nameof(LLamaEmbedder), generator.GetService<EmbeddingGeneratorMetadata>()?.ProviderName);
-        Assert.NotNull(generator.GetService<EmbeddingGeneratorMetadata>()?.ModelId);
-        Assert.NotEmpty(generator.GetService<EmbeddingGeneratorMetadata>()?.ModelId!);
+        Assert.NotNull(generator.GetService<EmbeddingGeneratorMetadata>()?.DefaultModelId);
+        Assert.NotEmpty(generator.GetService<EmbeddingGeneratorMetadata>()?.DefaultModelId!);
         Assert.Same(embedder, generator.GetService<LLamaEmbedder>());
         Assert.Same(generator, generator.GetService<IEmbeddingGenerator<string, Embedding<float>>>());
         Assert.Null(generator.GetService<string>());

LLama/LLamaEmbedder.EmbeddingGenerator.cs

@@ -22,8 +22,8 @@ public partial class LLamaEmbedder
             {
                 return _metadata ??= new(
                     nameof(LLamaEmbedder),
-                    modelId: Context.NativeHandle.ModelHandle.ReadMetadata().TryGetValue("general.name", out var name) ? name : null,
-                    dimensions: EmbeddingSize);
+                    defaultModelId: Context.NativeHandle.ModelHandle.ReadMetadata().TryGetValue("general.name", out var name) ? name : null,
+                    defaultModelDimensions: EmbeddingSize);
             }
 
             if (serviceType?.IsInstanceOfType(Context) is true)

LLama/LLamaSharp.csproj

@@ -51,7 +51,7 @@
   <ItemGroup>
     <PackageReference Include="CommunityToolkit.HighPerformance" Version="8.4.0" />
     <PackageReference Include="Microsoft.Bcl.AsyncInterfaces" Version="9.0.3" />
-    <PackageReference Include="Microsoft.Extensions.AI.Abstractions" Version="9.3.0-preview.1.25161.3" />
+    <PackageReference Include="Microsoft.Extensions.AI.Abstractions" Version="9.4.0-preview.1.25207.5" />
     <PackageReference Include="Microsoft.Extensions.Logging.Abstractions" Version="9.0.3" />
     <PackageReference Include="System.Numerics.Tensors" Version="9.0.3" />
   </ItemGroup>

README.md

@@ -65,7 +65,7 @@ There are integrations for the following libraries, making it easier to develop
 - [kernel-memory](https://github.com/microsoft/kernel-memory): a multi-modal AI Service specialized in the efficient indexing of datasets through custom continuous data hybrid pipelines, with support for RAG ([Retrieval Augmented Generation](https://en.wikipedia.org/wiki/Prompt_engineering#Retrieval-augmented_generation)), synthetic memory, prompt engineering, and custom semantic memory processing.
 - [BotSharp](https://github.com/SciSharp/BotSharp): an open source machine learning framework for AI Bot platform builder.
 - [Langchain](https://github.com/tryAGI/LangChain): a framework for developing applications powered by language models.
-
+- [MaIN.NET](https://github.com/wisedev-code/MaIN.NET): simplistic approach to orchestrating agents/chats from different (llm) providers
 
 The following examples show how to build APPs with LLamaSharp.
 
@@ -120,8 +120,9 @@ Generally, we recommend downloading models with quantization rather than fp16, b
 Here is a simple example to chat with a bot based on a LLM in LLamaSharp. Please replace the model path with yours.
 
 ```cs
-using LLama.Common;
 using LLama;
+using LLama.Common;
+using LLama.Sampling;
 
 string modelPath = @"<Your Model Path>"; // change it to your own model path.