feat: Updated descriptions of some properties.

docs/openapi.yaml

@@ -338,90 +338,106 @@ components:
           type: integer
           nullable: true
           description: |
-            Sets the random number seed to use for generation. Setting this to a specific number will make the model generate the same text for the same prompt. (Default: 0)
+            Sets the random number seed to use for generation. Setting this to a specific number will make the model 
+            generate the same text for the same prompt. (Default: 0)
         num_predict:
           type: integer
           nullable: true
           description: |
-            Maximum number of tokens to predict when generating text. (Default: 128, -1 = infinite generation, -2 = fill context)
+            Maximum number of tokens to predict when generating text. 
+            (Default: 128, -1 = infinite generation, -2 = fill context)
         top_k:
           type: integer
           nullable: true
           description: |
-            Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative. (Default: 40)
+            Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, 
+            while a lower value (e.g. 10) will be more conservative. (Default: 40)
         top_p:
           type: number
           format: float
           nullable: true
           description: |
-            Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)
+            Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value 
+            (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)
         tfs_z:
           type: number
           format: float
           nullable: true
           description: |
-            Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting. (default: 1)
+            Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value 
+            (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting. (default: 1)
         typical_p:
           type: number
           format: float
           nullable: true
           description: |
-            Typical p is used to reduce the impact of less probable tokens from the output.
+            Typical p is used to reduce the impact of less probable tokens from the output. (default: 1)
         repeat_last_n:
           type: integer
           nullable: true
           description: |
-            Sets how far back for the model to look back to prevent repetition. (Default: 64, 0 = disabled, -1 = num_ctx)
+            Sets how far back for the model to look back to prevent repetition. 
+            (Default: 64, 0 = disabled, -1 = num_ctx)
         temperature:
           type: number
           format: float
           nullable: true
           description: |
-            The temperature of the model. Increasing the temperature will make the model answer more creatively. (Default: 0.8)
+            The temperature of the model. Increasing the temperature will make the model answer more creatively. 
+            (Default: 0.8)
         repeat_penalty:
           type: number
           format: float
           nullable: true
           description: |
-            Sets how strongly to penalize repetitions. A higher value (e.g., 1.5) will penalize repetitions more strongly, while a lower value (e.g., 0.9) will be more lenient. (Default: 1.1)
+            Sets how strongly to penalize repetitions. A higher value (e.g., 1.5) will penalize repetitions more 
+            strongly, while a lower value (e.g., 0.9) will be more lenient. (Default: 1.1)
         presence_penalty:
           type: number
           format: float
           nullable: true
           description: |
-            Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
+            Positive values penalize new tokens based on whether they appear in the text so far, increasing the 
+            model's likelihood to talk about new topics. (Default: 0)
         frequency_penalty:
           type: number
           format: float
           nullable: true
           description: |
-            Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
+            Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the 
+            model's likelihood to repeat the same line verbatim. (Default: 0)
         mirostat:
           type: integer
           nullable: true
           description: |
-            Enable Mirostat sampling for controlling perplexity. (default: 0, 0 = disabled, 1 = Mirostat, 2 = Mirostat 2.0)
+            Enable Mirostat sampling for controlling perplexity. 
+            (default: 0, 0 = disabled, 1 = Mirostat, 2 = Mirostat 2.0)
         mirostat_tau:
           type: number
           format: float
           nullable: true
           description: |
-            Controls the balance between coherence and diversity of the output. A lower value will result in more focused and coherent text. (Default: 5.0)
+            Controls the balance between coherence and diversity of the output. A lower value will result in more 
+            focused and coherent text. (Default: 5.0)
         mirostat_eta:
           type: number
           format: float
           nullable: true
           description: |
-            Influences how quickly the algorithm responds to feedback from the generated text. A lower learning rate will result in slower adjustments, while a higher learning rate will make the algorithm more responsive. (Default: 0.1)
+            Influences how quickly the algorithm responds to feedback from the generated text. A lower learning rate 
+            will result in slower adjustments, while a higher learning rate will make the algorithm more responsive. 
+            (Default: 0.1)
         penalize_newline:
           type: boolean
           nullable: true
           description: |
-            Penalize newlines in the output. (Default: false)
+            Penalize newlines in the output. (Default: true)
         stop:
           type: array
           nullable: true
-          description: Sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.
+          description: |
+            Sequences where the API will stop generating further tokens. The returned text will not contain the stop 
+            sequence.
           items:
             type: string
         numa:
@@ -433,17 +449,18 @@ components:
           type: integer
           nullable: true
           description: |
-            Sets the size of the context window used to generate the next token.
+            Sets the size of the context window used to generate the next token. (Default: 2048)
         num_batch:
           type: integer
           nullable: true
           description: |
-            Sets the number of batches to use for generation. (Default: 1)
+            Sets the number of batches to use for generation. (Default: 512)
         num_gpu:
           type: integer
           nullable: true
           description: |
-            The number of layers to send to the GPU(s). On macOS it defaults to 1 to enable metal support, 0 to disable.
+            The number of layers to send to the GPU(s). 
+            On macOS it defaults to 1 to enable metal support, 0 to disable.
         main_gpu:
           type: integer
           nullable: true
@@ -483,7 +500,9 @@ components:
           type: integer
           nullable: true
           description: |
-            Sets the number of threads to use during computation. By default, Ollama will detect this for optimal performance. It is recommended to set this value to the number of physical CPU cores your system has (as opposed to the logical number of cores).
+            Sets the number of threads to use during computation. By default, Ollama will detect this for optimal 
+            performance. It is recommended to set this value to the number of physical CPU cores your system has 
+            (as opposed to the logical number of cores).
     ResponseFormat:
       type: string
       description: |

src/libs/Directory.Build.props

@@ -14,7 +14,7 @@
   </ItemGroup>
 
   <PropertyGroup Label="Nuget">
-    <Version>1.4.1</Version>
+    <Version>1.4.2</Version>
     <GeneratePackageOnBuild Condition=" '$(Configuration)' == 'Release' ">true</GeneratePackageOnBuild>
     <GenerateDocumentationFile>true</GenerateDocumentationFile>
     <Authors>tryAGI and contributors</Authors>

src/libs/Ollama/Generated/JsonSerializerContext.g.cs

@@ -2,6 +2,7 @@
 #nullable enable
 
 #pragma warning disable CS0618 // Type or member is obsolete
+#pragma warning disable CS3016 // Arrays as attribute arguments is not CLS-compliant
 
 namespace Ollama
 {

src/libs/Ollama/Generated/Ollama.ChatClient.GenerateChatCompletion.g.cs

@@ -5,6 +5,17 @@ namespace Ollama
 {
     public partial class ChatClient
     {
+        partial void PrepareGenerateChatCompletionArguments(
+            global::System.Net.Http.HttpClient httpClient,
+            global::Ollama.GenerateChatCompletionRequest request);
+        partial void PrepareGenerateChatCompletionRequest(
+            global::System.Net.Http.HttpClient httpClient,
+            global::System.Net.Http.HttpRequestMessage httpRequestMessage,
+            global::Ollama.GenerateChatCompletionRequest request);
+        partial void ProcessGenerateChatCompletionResponse(
+            global::System.Net.Http.HttpClient httpClient,
+            global::System.Net.Http.HttpResponseMessage httpResponseMessage);
+
         /// <summary>
         /// Generate the next message in a chat with a provided model.<br/>
         /// This is a streaming endpoint, so there will be a series of responses. The final response object will include statistics and additional data from the request.
@@ -18,6 +29,12 @@ public partial class ChatClient
         {
             request = request ?? throw new global::System.ArgumentNullException(nameof(request));
 
+            PrepareArguments(
+                client: _httpClient);
+            PrepareGenerateChatCompletionArguments(
+                httpClient: _httpClient,
+                request: request);
+
             using var httpRequest = new global::System.Net.Http.HttpRequestMessage(
                 method: global::System.Net.Http.HttpMethod.Post,
                 requestUri: new global::System.Uri(_httpClient.BaseAddress?.AbsoluteUri.TrimEnd('/') + "/chat", global::System.UriKind.RelativeOrAbsolute));
@@ -27,10 +44,25 @@ public partial class ChatClient
                 encoding: global::System.Text.Encoding.UTF8,
                 mediaType: "application/json");
 
+            PrepareRequest(
+                client: _httpClient,
+                request: httpRequest);
+            PrepareGenerateChatCompletionRequest(
+                httpClient: _httpClient,
+                httpRequestMessage: httpRequest,
+                request: request);
+
             using var response = await _httpClient.SendAsync(
                 request: httpRequest,
                 completionOption: global::System.Net.Http.HttpCompletionOption.ResponseHeadersRead,
                 cancellationToken: cancellationToken).ConfigureAwait(false);
+
+            ProcessResponse(
+                client: _httpClient,
+                response: response);
+            ProcessGenerateChatCompletionResponse(
+                httpClient: _httpClient,
+                httpResponseMessage: response);
             response.EnsureSuccessStatusCode();
 
             using var stream = await response.Content.ReadAsStreamAsync(cancellationToken).ConfigureAwait(false);

src/libs/Ollama/Generated/Ollama.ChatClient.g.cs

@@ -39,5 +39,18 @@ public void Dispose()
         {
             _httpClient.Dispose();
         }
+
+        partial void PrepareArguments(
+            global::System.Net.Http.HttpClient client);
+        partial void PrepareRequest(
+            global::System.Net.Http.HttpClient client,
+            global::System.Net.Http.HttpRequestMessage request);
+        partial void ProcessResponse(
+            global::System.Net.Http.HttpClient client,
+            global::System.Net.Http.HttpResponseMessage response);
+        partial void ProcessResponseContent(
+            global::System.Net.Http.HttpClient client,
+            global::System.Net.Http.HttpResponseMessage response,
+            ref string content);
     }
 }

src/libs/Ollama/Generated/Ollama.CompletionsClient.GenerateCompletion.g.cs

@@ -5,6 +5,17 @@ namespace Ollama
 {
     public partial class CompletionsClient
     {
+        partial void PrepareGenerateCompletionArguments(
+            global::System.Net.Http.HttpClient httpClient,
+            global::Ollama.GenerateCompletionRequest request);
+        partial void PrepareGenerateCompletionRequest(
+            global::System.Net.Http.HttpClient httpClient,
+            global::System.Net.Http.HttpRequestMessage httpRequestMessage,
+            global::Ollama.GenerateCompletionRequest request);
+        partial void ProcessGenerateCompletionResponse(
+            global::System.Net.Http.HttpClient httpClient,
+            global::System.Net.Http.HttpResponseMessage httpResponseMessage);
+
         /// <summary>
         /// Generate a response for a given prompt with a provided model.<br/>
         /// The final response object will include statistics and additional data from the request.
@@ -18,6 +29,12 @@ public partial class CompletionsClient
         {
             request = request ?? throw new global::System.ArgumentNullException(nameof(request));
 
+            PrepareArguments(
+                client: _httpClient);
+            PrepareGenerateCompletionArguments(
+                httpClient: _httpClient,
+                request: request);
+
             using var httpRequest = new global::System.Net.Http.HttpRequestMessage(
                 method: global::System.Net.Http.HttpMethod.Post,
                 requestUri: new global::System.Uri(_httpClient.BaseAddress?.AbsoluteUri.TrimEnd('/') + "/generate", global::System.UriKind.RelativeOrAbsolute));
@@ -27,10 +44,25 @@ public partial class CompletionsClient
                 encoding: global::System.Text.Encoding.UTF8,
                 mediaType: "application/json");
 
+            PrepareRequest(
+                client: _httpClient,
+                request: httpRequest);
+            PrepareGenerateCompletionRequest(
+                httpClient: _httpClient,
+                httpRequestMessage: httpRequest,
+                request: request);
+
             using var response = await _httpClient.SendAsync(
                 request: httpRequest,
                 completionOption: global::System.Net.Http.HttpCompletionOption.ResponseHeadersRead,
                 cancellationToken: cancellationToken).ConfigureAwait(false);
+
+            ProcessResponse(
+                client: _httpClient,
+                response: response);
+            ProcessGenerateCompletionResponse(
+                httpClient: _httpClient,
+                httpResponseMessage: response);
             response.EnsureSuccessStatusCode();
 
             using var stream = await response.Content.ReadAsStreamAsync(cancellationToken).ConfigureAwait(false);

src/libs/Ollama/Generated/Ollama.CompletionsClient.g.cs

@@ -39,5 +39,18 @@ public void Dispose()
         {
             _httpClient.Dispose();
         }
+
+        partial void PrepareArguments(
+            global::System.Net.Http.HttpClient client);
+        partial void PrepareRequest(
+            global::System.Net.Http.HttpClient client,
+            global::System.Net.Http.HttpRequestMessage request);
+        partial void ProcessResponse(
+            global::System.Net.Http.HttpClient client,
+            global::System.Net.Http.HttpResponseMessage response);
+        partial void ProcessResponseContent(
+            global::System.Net.Http.HttpClient client,
+            global::System.Net.Http.HttpResponseMessage response,
+            ref string content);
     }
 }