Merge pull request #53 from martindevans/xml_docs_fixes

XML docs fixes

LLama/Abstractions/ILLamaExecutor.cs

@@ -15,6 +15,7 @@ public interface ILLamaExecutor
         /// The loaded model for this executor.
         /// </summary>
         public LLamaModel Model { get; }
+
         /// <summary>
         /// Infers a response from the model.
         /// </summary>
@@ -24,6 +25,13 @@ public interface ILLamaExecutor
         /// <returns></returns>
         IEnumerable<string> Infer(string text, InferenceParams? inferenceParams = null, CancellationToken token = default);
 
+        /// <summary>
+        /// Asynchronously infers a response from the model.
+        /// </summary>
+        /// <param name="text">Your prompt</param>
+        /// <param name="inferenceParams">Any additional parameters</param>
+        /// <param name="token">A cancellation token.</param>
+        /// <returns></returns>
         IAsyncEnumerable<string> InferAsync(string text, InferenceParams? inferenceParams = null, CancellationToken token = default);
     }
 }

LLama/ChatSession.cs

@@ -134,8 +134,9 @@ public virtual void LoadSession(string path)
         /// <summary>
         /// Get the response from the LLama model with chat histories.
         /// </summary>
-        /// <param name="prompt"></param>
+        /// <param name="history"></param>
         /// <param name="inferenceParams"></param>
+        /// <param name="cancellationToken"></param>
         /// <returns></returns>
         public IEnumerable<string> Chat(ChatHistory history, InferenceParams? inferenceParams = null, CancellationToken cancellationToken = default)
         {
@@ -156,6 +157,7 @@ public IEnumerable<string> Chat(ChatHistory history, InferenceParams? inferenceP
         /// </summary>
         /// <param name="prompt"></param>
         /// <param name="inferenceParams"></param>
+        /// <param name="cancellationToken"></param>
         /// <returns></returns>
         public IEnumerable<string> Chat(string prompt, InferenceParams? inferenceParams = null, CancellationToken cancellationToken = default)
         {
@@ -176,8 +178,9 @@ public IEnumerable<string> Chat(string prompt, InferenceParams? inferenceParams
         /// <summary>
         /// Get the response from the LLama model with chat histories.
         /// </summary>
-        /// <param name="prompt"></param>
+        /// <param name="history"></param>
         /// <param name="inferenceParams"></param>
+        /// <param name="cancellationToken"></param>
         /// <returns></returns>
         public async IAsyncEnumerable<string> ChatAsync(ChatHistory history, InferenceParams? inferenceParams = null, [EnumeratorCancellation] CancellationToken cancellationToken = default)
         {

LLama/Common/ChatHistory.cs

@@ -1,16 +1,33 @@
-using System;
-using System.Collections.Generic;
-using System.Text;
+using System.Collections.Generic;
 
 namespace LLama.Common
 {
+    /// <summary>
+    /// Role of the message author, e.g. user/assistant/system
+    /// </summary>
     public enum AuthorRole
     {
+        /// <summary>
+        /// Role is unknown
+        /// </summary>
         Unknown = -1,
+
+        /// <summary>
+        /// Message comes from a "system" prompt, not written by a user or language model
+        /// </summary>
         System = 0,
+
+        /// <summary>
+        /// Message comes from the user
+        /// </summary>
         User = 1,
+
+        /// <summary>
+        /// Messages was generated by the language model
+        /// </summary>
         Assistant = 2,
     }
+
     // copy from semantic-kernel
     /// <summary>
     /// The chat history class

LLama/Common/FixedSizeQueue.cs

@@ -24,7 +24,7 @@ public FixedSizeQueue(int size)
         }
 
         /// <summary>
-        /// Fill the quene with the data. Please ensure that data.Count <= size
+        /// Fill the quene with the data. Please ensure that data.Count &lt;= size
         /// </summary>
         /// <param name="size"></param>
         /// <param name="data"></param>

LLama/Exceptions/RuntimeError.cs

@@ -1,6 +1,4 @@
 using System;
-using System.Collections.Generic;
-using System.Text;
 
 namespace LLama.Exceptions
 {

LLama/LLamaQuantizer.cs

@@ -18,10 +18,12 @@ public static class LLamaQuantizer
         /// <param name="dstFilename">The path to save the quantized model.</param>
         /// <param name="ftype">The type of quantization.</param>
         /// <param name="nthread">Thread to be used during the quantization. By default it's the physical core number.</param>
+        /// <param name="allowRequantize"></param>
+        /// <param name="quantizeOutputTensor"></param>
         /// <returns>Whether the quantization is successful.</returns>
         /// <exception cref="ArgumentException"></exception>
         public static unsafe bool Quantize(string srcFileName, string dstFilename, LLamaFtype ftype, int nthread = -1, bool allowRequantize = true, 
-            bool quantizeOutputTensor = false)
+                                           bool quantizeOutputTensor = false)
         {
             if (!ValidateFtype(ftype))
             {
@@ -45,10 +47,12 @@ public static unsafe bool Quantize(string srcFileName, string dstFilename, LLama
         /// <param name="dstFilename">The path to save the quantized model.</param>
         /// <param name="ftype">The type of quantization.</param>
         /// <param name="nthread">Thread to be used during the quantization. By default it's the physical core number.</param>
+        /// <param name="allowRequantize"></param>
+        /// <param name="quantizeOutputTensor"></param>
         /// <returns>Whether the quantization is successful.</returns>
         /// <exception cref="ArgumentException"></exception>
         public static bool Quantize(string srcFileName, string dstFilename, string ftype, int nthread = -1, bool allowRequantize = true,
-            bool quantizeOutputTensor = false)
+                                    bool quantizeOutputTensor = false)
         {
             return Quantize(srcFileName, dstFilename, StringToFtype(ftype), nthread, allowRequantize, quantizeOutputTensor);
         }

LLama/LLamaTransforms.cs

@@ -159,8 +159,8 @@ public class KeywordTextOutputStreamTransform : ITextStreamTransform
             /// <param name="keywords">Keywords that you want to remove from the response.</param>
             /// <param name="redundancyLength">The extra length when searching for the keyword. For example, if your only keyword is "highlight", 
             /// maybe the token you get is "\r\nhighligt". In this condition, if redundancyLength=0, the token cannot be successfully matched because the length of "\r\nhighligt" (10)
-            /// has already exceeded the maximum length of the keywords (8). On the contrary, setting redundancyLengyh >= 2 leads to successful match.
-            /// The larger the redundancyLength is, the lower the processing speed. But as an experience, it won't introduce too much performance impact when redundancyLength <= 5 </param>
+            /// has already exceeded the maximum length of the keywords (8). On the contrary, setting redundancyLengyh &gt;= 2 leads to successful match.
+            /// The larger the redundancyLength is, the lower the processing speed. But as an experience, it won't introduce too much performance impact when redundancyLength &lt;= 5 </param>
             /// <param name="removeAllMatchedTokens">If set to true, when getting a matched keyword, all the related tokens will be removed. Otherwise only the part of keyword will be removed.</param>
             public KeywordTextOutputStreamTransform(IEnumerable<string> keywords, int redundancyLength = 3, bool removeAllMatchedTokens = false)
             {

LLama/Native/LLamaModelQuantizeParams.cs

@@ -8,7 +8,7 @@ namespace LLama.Native
     public struct LLamaModelQuantizeParams
     {
         /// <summary>
-        /// number of threads to use for quantizing, if <=0 will use std::thread::hardware_concurrency()
+        /// number of threads to use for quantizing, if &lt;=0 will use std::thread::hardware_concurrency()
         /// </summary>
         public int nthread;
         /// <summary>

LLama/Native/NativeApi.Quantize.cs

@@ -12,8 +12,7 @@ public partial class NativeApi
         /// </summary>
         /// <param name="fname_inp"></param>
         /// <param name="fname_out"></param>
-        /// <param name="ftype"></param>
-        /// <param name="nthread">how many threads to use. If <=0, will use std::thread::hardware_concurrency(), else the number given</param>
+        /// <param name="param"></param>
         /// <remarks>not great API - very likely to change</remarks>
         /// <returns>Returns 0 on success</returns>
         [DllImport(libraryName, CallingConvention = CallingConvention.Cdecl)]

LLama/OldVersion/ChatSession.cs

@@ -39,9 +39,9 @@ public ChatSession<T> WithPromptFile(string promptFilename, string encoding = "U
         }
 
         /// <summary>
-        /// Set the keyword to split the return value of chat AI.
+        /// Set the keywords to split the return value of chat AI.
         /// </summary>
-        /// <param name="humanName"></param>
+        /// <param name="antiprompt"></param>
         /// <returns></returns>
         public ChatSession<T> WithAntiprompt(string[] antiprompt)
         {

LLama/OldVersion/LLamaModel.cs

@@ -796,6 +796,7 @@ public IEnumerable<string> Call(string text, string encoding = "UTF-8")
             }
         }
 
+        /// <inheritdoc />
         public void Dispose()
         {
             _ctx.Dispose();