Use OllamaSharp package (#46455)

Author: gewarren

docs/ai/microsoft-extensions-ai.md

@@ -90,14 +90,14 @@ Some models and services support _tool calling_. To gather additional informatio
 - <xref:Microsoft.Extensions.AI.AIFunctionFactory>: Provides factory methods for creating `AIFunction` instances that represent .NET methods.
 - <xref:Microsoft.Extensions.AI.FunctionInvokingChatClient>: Wraps an `IChatClient` as another `IChatClient` that adds automatic function-invocation capabilities.
 
-The following example demonstrates a random function invocation (this example depends on the [📦 Microsoft.Extensions.AI.Ollama](https://www.nuget.org/packages/Microsoft.Extensions.AI.Ollama) NuGet package):
+The following example demonstrates a random function invocation (this example depends on the [📦 OllamaSharp](https://www.nuget.org/packages/OllamaSharp) NuGet package):
 
 :::code language="csharp" source="snippets/microsoft-extensions-ai/ConsoleAI.ToolCalling/Program.cs":::
 
 The preceding code:
 
 - Defines a function named `GetCurrentWeather` that returns a random weather forecast.
-- Instantiates a <xref:Microsoft.Extensions.AI.ChatClientBuilder> with an <xref:Microsoft.Extensions.AI.OllamaChatClient> and configures it to use function invocation.
+- Instantiates a <xref:Microsoft.Extensions.AI.ChatClientBuilder> with an `OllamaSharp.OllamaApiClient` and configures it to use function invocation.
 - Calls `GetStreamingResponseAsync` on the client, passing a prompt and a list of tools that includes a function created with <xref:Microsoft.Extensions.AI.AIFunctionFactory.Create*>.
 - Iterates over the response, printing each update to the console.
 
@@ -213,10 +213,7 @@ The preceding code:
 - Has a primary constructor that accepts an endpoint and model ID, which are used to identify the generator.
 - Implements the `GenerateAsync` method to generate embeddings for a collection of input values.
 
-The sample implementation just generates random embedding vectors. You can find actual concrete implementations in the following packages:
-
-- [📦 Microsoft.Extensions.AI.OpenAI](https://www.nuget.org/packages/Microsoft.Extensions.AI.OpenAI)
-- [📦 Microsoft.Extensions.AI.Ollama](https://www.nuget.org/packages/Microsoft.Extensions.AI.Ollama)
+The sample implementation just generates random embedding vectors. You can find a concrete implementation in the [📦 Microsoft.Extensions.AI.OpenAI](https://www.nuget.org/packages/Microsoft.Extensions.AI.OpenAI) package.
 
 #### Create embeddings
 

docs/ai/quickstarts/chat-local-model.md

@@ -62,10 +62,10 @@ Complete the following steps to create a .NET console app that connects to your
     dotnet new console -o LocalAI
     ```
 
-1. Add the [Microsoft.Extensions.AI.Ollama](https://www.nuget.org/packages/Microsoft.Extensions.AI.Ollama/) package to your app:
+1. Add the [OllamaSharp](https://www.nuget.org/packages/OllamaSharp) package to your app:
 
     ```dotnetcli
-    dotnet add package Microsoft.Extensions.AI.Ollama --prerelease
+    dotnet add package OllamaSharp
     ```
 
 1. Open the new app in your editor of choice, such as Visual Studio Code.

docs/ai/quickstarts/snippets/local-ai/Program.cs

@@ -1,7 +1,8 @@
 using Microsoft.Extensions.AI;
+using OllamaSharp;
 
 IChatClient chatClient =
-    new OllamaChatClient(new Uri("http://localhost:11434/"), "phi3:mini");
+    new OllamaApiClient(new Uri("http://localhost:11434/"), "phi3:mini");
 
 // Start the conversation with context for the AI model
 List<ChatMessage> chatHistory = new();

docs/ai/quickstarts/snippets/local-ai/ollama.csproj

@@ -8,7 +8,7 @@
   </PropertyGroup>
 
   <ItemGroup>
-    <PackageReference Include="Microsoft.Extensions.AI.Ollama" Version="9.5.0-preview.1.25265.7" />
+    <PackageReference Include="OllamaSharp" Version="5.1.19" />
   </ItemGroup>
 
 </Project>

docs/ai/snippets/microsoft-extensions-ai/ConsoleAI.CacheResponses/ConsoleAI.CacheResponses.csproj

@@ -8,7 +8,7 @@
   </PropertyGroup>
 
   <ItemGroup>
-    <PackageReference Include="Microsoft.Extensions.AI.Ollama" Version="9.5.0-preview.1.25265.7" />
+    <PackageReference Include="OllamaSharp" Version="5.1.19" />
     <PackageReference Include="Microsoft.Extensions.Caching.Memory" Version="10.0.0-preview.3.25171.5" />
   </ItemGroup>
 

docs/ai/snippets/microsoft-extensions-ai/ConsoleAI.CacheResponses/Program.cs

@@ -2,8 +2,9 @@
 using Microsoft.Extensions.Caching.Distributed;
 using Microsoft.Extensions.Caching.Memory;
 using Microsoft.Extensions.Options;
+using OllamaSharp;
 
-var sampleChatClient = new OllamaChatClient(new Uri("http://localhost:11434"), "llama3.1");
+var sampleChatClient = new OllamaApiClient(new Uri("http://localhost:11434"), "llama3.1");
 
 IChatClient client = new ChatClientBuilder(sampleChatClient)
     .UseDistributedCache(new MemoryDistributedCache(

docs/ai/snippets/microsoft-extensions-ai/ConsoleAI.ConsumeClientMiddleware/ConsoleAI.ConsumeClientMiddleware.csproj

@@ -8,7 +8,6 @@
   </PropertyGroup>
 
   <ItemGroup>
-    <PackageReference Include="Microsoft.Extensions.AI.Ollama" Version="9.5.0-preview.1.25265.7" />
     <PackageReference Include="Microsoft.Extensions.Hosting" Version="10.0.0-preview.3.25171.5" />
     <ProjectReference Include="..\AI.Shared\AI.Shared.csproj" />
   </ItemGroup>

docs/ai/snippets/microsoft-extensions-ai/ConsoleAI.CreateEmbeddings/Program.cs

@@ -13,5 +13,5 @@ await generator.GenerateAsync(["What is AI?", "What is .NET?"]))
 // </Snippet1>
 
 // <Snippet2>
-ReadOnlyMemory<float> vector = await generator.GenerateEmbeddingVectorAsync("What is AI?");
+ReadOnlyMemory<float> vector = await generator.GenerateVectorAsync("What is AI?");
 // </Snippet2>

docs/ai/snippets/microsoft-extensions-ai/ConsoleAI.CustomClientMiddle/ConsoleAI.CustomClientMiddle.csproj

@@ -8,7 +8,7 @@
   </PropertyGroup>
 
   <ItemGroup>
-    <PackageReference Include="Microsoft.Extensions.AI.Ollama" Version="9.5.0-preview.1.25265.7" />
+    <PackageReference Include="OllamaSharp" Version="5.1.19" />
     <PackageReference Include="System.Threading.RateLimiting" Version="10.0.0-preview.4.25258.110" />
   </ItemGroup>
 

docs/ai/snippets/microsoft-extensions-ai/ConsoleAI.CustomClientMiddle/Program.cs

@@ -1,8 +1,9 @@
 using Microsoft.Extensions.AI;
+using OllamaSharp;
 using System.Threading.RateLimiting;
 
 var client = new RateLimitingChatClient(
-    new OllamaChatClient(new Uri("http://localhost:11434"), "llama3.1"),
+    new OllamaApiClient(new Uri("http://localhost:11434"), "llama3.1"),
     new ConcurrencyLimiter(new() { PermitLimit = 1, QueueLimit = int.MaxValue }));
 
 Console.WriteLine(await client.GetResponseAsync("What color is the sky?"));