Push to production

.gitignore

@@ -119,3 +119,4 @@ PythonRpcServer/ct_pb2.py
 /old--dot.env
 /docker-compose.yml
 /PythonRpcServer/corpus_count.json
+DevExperiments/LocalEnvironmentVariables.txt

ClassTranscribeDatabase/CommonUtils.cs

@@ -1,11 +1,13 @@
 using ClassTranscribeDatabase.Models;
+using Microsoft.EntityFrameworkCore;
 using Newtonsoft.Json;
 using Newtonsoft.Json.Linq;
 using System;
 using System.Globalization;
 using System.IO;
 using System.Linq;
 using System.Text;
+using System.Threading.Tasks;
 
 
 namespace ClassTranscribeDatabase
@@ -165,17 +167,29 @@
             return name;
         }
         public static string ToCourseOfferingSubDirectory(CTDbContext ctx, Entity entity) {
-            #nullable enable
-            String? path = GetRelatedCourseOfferingFilePath(ctx, entity);
-
-            if( !string.IsNullOrEmpty(path ) ) {
-                return path;
+#nullable enable
+            try
+            {
+                String? path = GetRelatedCourseOfferingFilePath(ctx, entity);
+
+                if (!string.IsNullOrEmpty(path))
+                {
+                    return path;
+                }
+            } catch (Exception ignored)
+            {
+                Console.WriteLine(ignored);
             }
             #nullable disable
             return "/data/"; //legacy, pre 2022, default = everything is stored in the same directory
+            // we could still get here if something in the model has been deleted.
+        }
+#nullable enable
+        public static string GetRelatedCourseOfferingFilePath(CTDbContext ctx, Entity entity)
+        {
+            return GetRelatedCourseOfferingFilePathAsync(ctx, entity).GetAwaiter().GetResult();
         }
-        #nullable enable
-        public static string? GetRelatedCourseOfferingFilePath(CTDbContext ctx, Entity entity)
+        public static async Task<string?> GetRelatedCourseOfferingFilePathAsync(CTDbContext ctx, Entity entity)
         {
             // the only thing that we can trust exists on the given the entity Id
             // Drop recursion... this may reduce the number of SQL calls
@@ -186,40 +200,61 @@
             switch (entity)
             {
                 case CourseOffering co:
-                    return ctx.CourseOfferings.Where(co2 => co2.Id == co.Id).OrderBy(co=>co.CreatedAt).FirstOrDefault()?.FilePath;
+                    return co.FilePath;
 
                 case Course c:
-                    return ctx.CourseOfferings.Where(c2 => c2.CourseId == c.Id)
-                        .OrderBy(co=>co.CreatedAt).FirstOrDefault()?.FilePath;
+                    return (await ctx.CourseOfferings.OrderBy(co => co.CreatedAt).FirstOrDefaultAsync(co=>co.CourseId == c.Id))?.FilePath;
 
                 case Media m:
-                    return ctx.Medias.FirstOrDefault(m2=>m2.Id == m.Id ).Playlist.Offering
-                        .CourseOfferings.OrderBy(co=>co.CreatedAt).FirstOrDefault()?.FilePath;
+                    return await playlistIdToFilePath(ctx, m.PlaylistId);
 
                 case Offering o:
-                    return ctx.CourseOfferings.Where(co2 => co2.OfferingId == o.Id)
-                        .OrderBy(co=>co.CreatedAt).FirstOrDefault()?.FilePath;
+                    return (await ctx.CourseOfferings.OrderBy(co=>co.CreatedAt).FirstOrDefaultAsync(co2 => co2.OfferingId == o.Id))?.FilePath;
 
                 case Playlist p:
-                    return ctx.Playlists.FirstOrDefault(p2=>p2.Id == p.Id ).Offering
-                        .CourseOfferings.OrderBy(co=>co.CreatedAt).FirstOrDefault()?.FilePath;
-
+                    return await playlistIdToFilePath(ctx, p.Id);
+
                 case Transcription t:
-                    return ctx.Transcriptions.FirstOrDefault(t2=>t2.Id == t.Id)?.Video
-                        .Medias.OrderBy(co=>co.CreatedAt).FirstOrDefault()
-                        ?.Playlist.Offering
-                        .CourseOfferings.OrderBy(co=>co.CreatedAt).FirstOrDefault()?.FilePath;
+                    {
+                        var playlistId = (await ctx.Transcriptions.Include(t => t.Video).ThenInclude(v => v.Medias).FirstOrDefaultAsync(t2 => t2.Id == t.Id))
+                            ?.Video.Medias.OrderBy(co => co.CreatedAt).Select(m => m.PlaylistId).FirstOrDefault();
+                        return await playlistIdToFilePath(ctx, playlistId);
+                    }
+                    // return ctx.Transcriptions.FirstOrDefault(t2=>t2.Id == t.Id)?.Video
+                    //    .Medias.OrderBy(co=>co.CreatedAt).FirstOrDefault()
+                    //    ?.Playlist.Offering
+                    //    .CourseOfferings.OrderBy(co=>co.CreatedAt).FirstOrDefault()?.FilePath;
 
                 case Video v:
-                    return ctx.Medias.OrderBy(co=>co.CreatedAt).FirstOrDefault(m2=>m2.VideoId == v.Id )
-                        .Playlist.Offering
-                        .CourseOfferings.OrderBy(co=>co.CreatedAt).FirstOrDefault()?.FilePath;
+                    {
+                        var playlistId = (await ctx.Medias.OrderBy(co => co.CreatedAt).FirstOrDefaultAsync(m => m.VideoId == v.Id))?.PlaylistId;
+                        return await playlistIdToFilePath(ctx, playlistId);
+                    }
+                    // return ctx.Medias.OrderBy(co=>co.CreatedAt).FirstOrDefault(m2=>m2.VideoId == v.Id )
+                    //    .Playlist.Offering
+                    //    .CourseOfferings.OrderBy(co=>co.CreatedAt).FirstOrDefault()?.FilePath;
 
                 default:
                     throw new InvalidOperationException($"GetRelatedCourseOffering not implemented for type {entity.GetType()} (Object ID: {entity.Id})");
             }
 
         }
-        #nullable disable
+
+        private async static Task<string?> playlistIdToFilePath(CTDbContext ctx, string? playlistId)
+        {
+            if (string.IsNullOrEmpty(playlistId)) return "";
+
+            var playlist = (await ctx.Playlists.Include(p => p.Offering).FirstOrDefaultAsync(p => p.Id == playlistId));
+            var offeringId = playlist?.Offering?.Id ?? "";
+            return offeringId.Length >0 ?  await offeringIdToFilePath(ctx, offeringId) : "";
+        }
+        private async static Task<string?> offeringIdToFilePath(CTDbContext ctx, string? offeringId)
+        {
+            if (string.IsNullOrEmpty(offeringId)) return "";
+
+            var courseoffering = (await ctx.CourseOfferings.OrderBy(co => co.CreatedAt).FirstOrDefaultAsync(co => co.OfferingId == offeringId));
+            return courseoffering?.FilePath ?? "";
+        }
+#nullable disable
     }
 }

ClassTranscribeDatabase/Globals.cs

@@ -82,6 +82,13 @@ public class AppSettings
 
         public string DIGEST_CALCULATION_METHOD { get; set; } = "";
 
+        public string LLAVA_PATH { get; set; } = "/llava/llava-v1.5-7b-q4.llamafile";
+        public string LLAVA_ARGS { get; set; } = "--threads {cpuCount} -m llava-v1.5-7b-Q4_K.gguf --mmproj llava-v1.5-7b-mmproj-Q4_0.gguf  --temp 0.0 --silent-prompt  --image \"{imagePath}\" --escape -p \"{prompt}\"";
+        public string LLAVA_PROMPT { get; set; } = "### User: I am blind and listening to a university lecture video. What is in this image, that has been extracted from the lecture video? Be concise. Do your best to describe only the technical content of the image that is relevant to learning. Do not add opinions about the image.\n### Assistant:";
+
+        public string LLAVA_LOG_STREAMS { get; set; } = "out,err";
+        public string LLAVA_USESHELL { get; set; } = "";
+
     }
 
     /// <summary>

ClassTranscribeDatabase/Services/Slack.cs

@@ -24,7 +24,7 @@
             _logger = logger;
 
             // ignore
-            string url = _appSettings.SLACK_WEBHOOK_URL.Trim();
+            string url = _appSettings.SLACK_WEBHOOK_URL?.Trim()??"";
             if (url.Length > 0 && !url.Contains("<ADD WEBHOOK URL HERE>"))
             {
                 _uri = new Uri(url);
@@ -79,7 +79,7 @@
             }
             try
             {
                 using (WebClient client = new WebClient())
                 {
                     NameValueCollection data = new NameValueCollection();
                     data["payload"] = payloadJson;

ClassTranscribeServer.sln

@@ -1,7 +1,7 @@
 
 Microsoft Visual Studio Solution File, Format Version 12.00
-# Visual Studio Version 16
-VisualStudioVersion = 16.0.28902.138
+# Visual Studio Version 17
+VisualStudioVersion = 17.8.34330.188
 MinimumVisualStudioVersion = 10.0.40219.1
 Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "ClassTranscribeServer", "ClassTranscribeServer\ClassTranscribeServer.csproj", "{E4C52518-A6B4-42B0-8A02-DC1BFBE9CD89}"
 EndProject
@@ -25,6 +25,8 @@ Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "UnitTests", "UnitTests\Unit
 EndProject
 Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "TestAzureCognitiveServices", "TestAzureCognitiveServices\TestAzureCognitiveServices.csproj", "{DA560288-98FC-4233-8CD5-252F8570CBFB}"
 EndProject
+Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "TestRemoteLLM", "TestRemoteLLM\TestRemoteLLM.csproj", "{9D9DB7A1-DBDA-49DF-9D31-D39846BABE30}"
+EndProject
 Global
 	GlobalSection(SolutionConfigurationPlatforms) = preSolution
 		Debug|Any CPU = Debug|Any CPU
@@ -55,6 +57,10 @@ Global
 		{DA560288-98FC-4233-8CD5-252F8570CBFB}.Debug|Any CPU.Build.0 = Debug|Any CPU
 		{DA560288-98FC-4233-8CD5-252F8570CBFB}.Release|Any CPU.ActiveCfg = Release|Any CPU
 		{DA560288-98FC-4233-8CD5-252F8570CBFB}.Release|Any CPU.Build.0 = Release|Any CPU
+		{9D9DB7A1-DBDA-49DF-9D31-D39846BABE30}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{9D9DB7A1-DBDA-49DF-9D31-D39846BABE30}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{9D9DB7A1-DBDA-49DF-9D31-D39846BABE30}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{9D9DB7A1-DBDA-49DF-9D31-D39846BABE30}.Release|Any CPU.Build.0 = Release|Any CPU
 	EndGlobalSection
 	GlobalSection(SolutionProperties) = preSolution
 		HideSolutionNode = FALSE

DevExperiments/Program.cs

@@ -20,11 +20,12 @@ static void Main(string[] args)
                 {
                     builder.AddConsole();
                     builder.AddFilter<Microsoft.Extensions.Logging.ApplicationInsights.ApplicationInsightsLoggerProvider>
-                             ("", LogLevel.Warning);
-                    builder.AddApplicationInsights(configuration.GetValue<string>("APPLICATION_INSIGHTS_KEY"));
+                              ("", LogLevel.Warning);
+                    //builder.AddApplicationInsights(configuration.GetValue<string>("APPLICATION_INSIGHTS_KEY"));
                 })
                 .AddOptions()
                 .Configure<AppSettings>(configuration)
+                //.AddDbContext<CTDbContext>(options => options.UseNpgsql(CTDbContext.ConnectionStringBuilder()))
                 .AddDbContext<CTDbContext>(options => options.UseLazyLoadingProxies().UseNpgsql(CTDbContext.ConnectionStringBuilder()))
                 .AddScoped<SlackLogger>()
                 .AddSingleton<MSTranscriptionService>()

DevExperiments/TempCode.cs

@@ -1,9 +1,16 @@
 using ClassTranscribeDatabase;
+using ClassTranscribeDatabase.Migrations;
+using ClassTranscribeDatabase.Models;
 using ClassTranscribeDatabase.Services;
 using ClassTranscribeDatabase.Services.MSTranscription;
+using Microsoft.EntityFrameworkCore;
+using Microsoft.EntityFrameworkCore.Metadata;
 using Newtonsoft.Json.Linq;
+using NpgsqlTypes;
 using System;
 using System.Threading.Tasks;
+using System.Linq;
+using System.Collections.Generic;
 
 namespace DevExperiments
 {
@@ -22,9 +29,88 @@ public TempCode(CTDbContext c, MSTranscriptionService transcriptionService, RpcC
             _rpcClient = rpcClient;
         }
 
+        public async Task ReadEntity()
+        {
+            Transcription transcription = context.Transcriptions.FirstOrDefault((t=>t.Id == "a3013ae4-869a-4de4-97d2-101af3ef75d7"));
+            Video video = context.Videos.OrderByDescending(co => co.CreatedAt).FirstOrDefault();
+            Playlist playlist = context.Playlists.OrderByDescending(co => co.CreatedAt).FirstOrDefault();
+            CourseOffering co = context.CourseOfferings.OrderByDescending(co => co.CreatedAt).FirstOrDefault();
+            Offering off = context.Offerings.OrderByDescending(co => co.CreatedAt).FirstOrDefault();
+            Media media = context.Medias.OrderByDescending(co => co.CreatedAt).FirstOrDefault();
+
+            List<Entity> items = new List<Entity>();
+            items.Add(video);
+            items.Add(playlist);
+            items.Add(transcription);
+            items.Add(co);
+            items.Add(off);
+            items.Add(media);
+
+            foreach(var entity in items) {
+                var filePath1 = CommonUtils.ToCourseOfferingSubDirectory(context, entity);
+                Console.WriteLine(filePath1);
+            }
+
+        }
+        public async Task ReadEntity2()
+        {
+            int count = await context.Transcriptions.CountAsync();
+            Console.WriteLine($"Count: {count}");
+            var tid1 = "4aa9e224-75f0-4775-a531-a5b0c99693f0"; // playlist deleted
+            var tid2 = "a3013ae4-869a-4de4-97d2-101af3ef75d7";
+            var tid3 = "a3013ae4-869a-4de4-97d2-101af3ef75d7"; // "8c4f01ec-5620-49e5-aa33-89cdfa37ac55"; // "4d47ee07-6bbc-47b7-8da5-6a80cf006f1c";
+            var tid = tid1;
+            var playlistId = (await context.Transcriptions.Include(t => t.Video).ThenInclude(v=>v.Medias).FirstOrDefaultAsync(t2 => t2.Id == tid)) 
+                    ?.Video.Medias.OrderBy(co => co.CreatedAt).Select(m=>m.PlaylistId).FirstOrDefault();
+            var offeringId =(await context.Playlists.Include(p => p.Offering).FirstOrDefaultAsync(p => p.Id == playlistId)) ?.Offering.Id;
+            CourseOffering courseoff = (await context.CourseOfferings.Where(co => co.OfferingId == offeringId).OrderBy(co => co.CreatedAt).FirstOrDefaultAsync());
+            string filepath = courseoff?.FilePath;
+
+            Console.WriteLine($"# playlistId isnull {playlistId == null},{playlistId}");
+            Console.WriteLine($"# Offering isnull {offeringId == null},{offeringId}");
+            Console.WriteLine($"courseoff isnull:{courseoff == null}, {courseoff} ");
+            Console.WriteLine($"FilePath isnull:{filepath == null}, {filepath} ");
+
+
+            /*            string filepath = context.Transcriptions.FirstOrDefault(t2 => t2.Id == tid)?.Video
+                                   .Medias.OrderBy(co => co.CreatedAt).FirstOrDefault()
+                                   ?.Playlist.Offering
+                                   .CourseOfferings.OrderBy(co => co.CreatedAt).FirstOrDefault()?.FilePath; */
+            //  Console.WriteLine($"Path:{filepath}");
+            return;
+        }
+        void ignore() { 
+            // Transcription t1 = context.Transcriptions.Include("Video").FirstOrDefault(t2 => t2.Id == tid);
+
+            //Console.WriteLine($"T found {t1.Id} -> {t1.VideoId}");
+            //Video v2 = context.Videos.Find( t1.VideoId);
+            //Console.WriteLine($"V2 found {v2.Id}");
+
+            // Video v1 = t1.Video;
+
+            // Console.WriteLine($"V1 found {v1.Id}");
+
+            // List<Media> m1 = context.Transcriptions.FirstOrDefault(t2 => t2.Id == tid)?.Video.Medias;
+
+            // Media m1 = context.Transcriptions.Include(t => t.Video.Medias).FirstOrDefault(t2 => t2.Id == tid)?.Video.Medias.OrderBy(co => co.CreatedAt).FirstOrDefault();
+            // Console.WriteLine($"# Media found {m1}");
+
+            // Offering o1 = context.Playlists.Include(p => p.Offering).FirstOrDefault(p => p.Id == m1.PlaylistId).Offering;
+            // Console.WriteLine($"# Offering found {o1}");
+
+            // var filepath = context.Playlists.Include(p=>p.Offering.CourseOfferings).FirstOrDefault(p => p.Id == m1.PlaylistId).Offering.CourseOfferings.OrderBy(co => co.CreatedAt).FirstOrDefault()?.FilePath;
+
+            //Offering o1 = context.Transcriptions.FirstOrDefault(t2 => t2.Id == tid)?.Video
+            //            .Medias.OrderBy(co => co.CreatedAt).FirstOrDefault()
+            //            ?.Playlist.Offering;
+
+
+        }
         public void Temp()
         {
-            TempAsync().GetAwaiter().GetResult();
+            ReadEntity().GetAwaiter().GetResult(); ;
+
+            //TempAsync().GetAwaiter().GetResult();
         }
 
         private async Task TempAsync()

TaskEngine.Dockerfile

@@ -22,7 +22,21 @@ RUN dotnet publish TaskEngine.csproj -c Release -o /app --no-restore
 
 FROM mcr.microsoft.com/dotnet/aspnet:8.0-bookworm-slim as publish_base
 # FROM mcr.microsoft.com/dotnet/core/runtime:3.1.3-bionic as publish_base
-RUN apt-get update && apt-get install -y build-essential libasound2 wget netcat-traditional && apt-get -q update
+# Install prerequisites for Azure Speech Services: build-essential libssl-dev ca-certificates libasound2 wget
+# See https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/quickstarts/setup-platform
+
+RUN apt-get update && apt-get install -y  build-essential libssl-dev ca-certificates libasound2 wget && \
+apt-get install -y netcat-traditional && apt-get -q update
+
+# Microsoft 8.0 issue: https://github.com/Azure-Samples/cognitive-services-speech-sdk/issues/2204
+# This  will install OpenSSL 1.1.1 because it is needed by the Speech SDK.
+RUN \
+wget http://security.ubuntu.com/ubuntu/pool/main/o/openssl/libssl1.1_1.1.1f-1ubuntu2.20_amd64.deb && \
+wget http://security.ubuntu.com/ubuntu/pool/main/o/openssl/libssl-dev_1.1.1f-1ubuntu2.20_amd64.deb && \
+dpkg -i libssl1.1_1.1.1f-1ubuntu2.20_amd64.deb && \
+dpkg -i libssl-dev_1.1.1f-1ubuntu2.20_amd64.deb && \
+rm libssl1.1_1.1.1f-1ubuntu2.20_amd64.deb libssl-dev_1.1.1f-1ubuntu2.20_amd64.deb
+
 
 FROM publish_base as publish
 WORKDIR /

TaskEngine/TaskEngine.csproj

@@ -26,6 +26,7 @@
     <PackageReference Include="Microsoft.Extensions.Logging.Console" Version="8.0.0" />
     <PackageReference Include="NEST" Version="7.17.5" />
     <PackageReference Include="Elasticsearch.Net" Version="7.17.5" />
+    <PackageReference Include="RestSharp" Version="110.2.0" />
   </ItemGroup>
 
   <ItemGroup>

TaskEngine/TaskEngine.sln

@@ -0,0 +1,25 @@
+
+Microsoft Visual Studio Solution File, Format Version 12.00
+# Visual Studio Version 17
+VisualStudioVersion = 17.5.002.0
+MinimumVisualStudioVersion = 10.0.40219.1
+Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "TaskEngine", "TaskEngine.csproj", "{09720F43-452A-43D0-BE7E-AAE2CF822AA0}"
+EndProject
+Global
+	GlobalSection(SolutionConfigurationPlatforms) = preSolution
+		Debug|Any CPU = Debug|Any CPU
+		Release|Any CPU = Release|Any CPU
+	EndGlobalSection
+	GlobalSection(ProjectConfigurationPlatforms) = postSolution
+		{09720F43-452A-43D0-BE7E-AAE2CF822AA0}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{09720F43-452A-43D0-BE7E-AAE2CF822AA0}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{09720F43-452A-43D0-BE7E-AAE2CF822AA0}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{09720F43-452A-43D0-BE7E-AAE2CF822AA0}.Release|Any CPU.Build.0 = Release|Any CPU
+	EndGlobalSection
+	GlobalSection(SolutionProperties) = preSolution
+		HideSolutionNode = FALSE
+	EndGlobalSection
+	GlobalSection(ExtensibilityGlobals) = postSolution
+		SolutionGuid = {83861AB8-4CDE-41B0-8309-63BD076F3EA6}
+	EndGlobalSection
+EndGlobal