Show all data sources on the embeddings page from the start

This commit is contained in:
Thorsten Sommer 2026-09-16 19:36:04 +02:00
parent cd42c48caf
commit 5f438cbfbe
Signed by untrusted user who does not match committer: tsommer
GPG Key ID: 371BBA77A02C0108
3 changed files with 44 additions and 0 deletions

View File

@ -19,6 +19,12 @@
<MudChip T="string" Color="Color.Default" Variant="Variant.Filled">@string.Format(T("Skipped files: {0}"), this.TotalPermanentlySkippedFiles)</MudChip>
<MudChip T="string" Color="Color.Error" Variant="Variant.Filled">@string.Format(T("Failed files: {0}"), this.TotalFailedFiles)</MudChip>
</MudStack>
@if (this.IsWorkingThroughDataSources)
{
<MudText Typo="Typo.body2" Class="mt-2">
@string.Format(T("Data source {0} of {1} is being worked on. The others are waiting their turn."), this.CurrentDataSourceNumber, this.Statuses.Count)
</MudText>
}
</MudPaper>
@if (this.Statuses.Count == 0)

View File

@ -43,6 +43,19 @@ public partial class Embeddings : MSGComponentBase
private int TotalPermanentlySkippedFiles => this.Statuses.Sum(status => status.PermanentlySkippedFiles);
/// <remarks>
/// The chips above count files, which says nothing about how far the list of data sources itself
/// has come. While several of them wait their turn, this is the one line saying so. With a single
/// data source there is nothing to say: its own row already tells the whole story.
/// </remarks>
private bool IsWorkingThroughDataSources => this.Statuses.Count > 1 && this.Statuses.Any(status => status.State is DataSourceEmbeddingState.RUNNING or DataSourceEmbeddingState.QUEUED);
/// <remarks>
/// The one being worked on is the one after those which are done. A data source which needs
/// attention counts as done here: nothing is going to happen to it during this pass.
/// </remarks>
private int CurrentDataSourceNumber => Math.Min(this.Statuses.Count, this.Statuses.Count(status => status.State is DataSourceEmbeddingState.COMPLETED or DataSourceEmbeddingState.FAILED) + 1);
protected override async Task OnInitializedAsync()
{
//

View File

@ -1164,6 +1164,31 @@ public sealed partial class DataSourceEmbeddingService(SettingsManager settingsM
"Starting initial persisted hash check for {DataSourceCount} supported internal data source(s). Incomplete or failed local RAG embedding state will be retried during this pass. File watchers will be activated after this check completes.",
supportedDataSources.Count);
//
// Every data source gets its row before the first run starts. This pass works through them
// one after the other, and re-indexing a large source takes its time: without this, the
// embeddings page would show the one source being worked on and nothing else, which reads
// as if the others were gone rather than waiting their turn. The queueing path does the
// same thing when it reserves a slot, which is why it never had this problem.
//
foreach (var dataSource in supportedDataSources)
{
if (this.statuses.TryGetValue(dataSource.Id, out var knownStatus) && knownStatus.State is DataSourceEmbeddingState.RUNNING)
continue;
this.statuses[dataSource.Id] = this.CreateStatus(
dataSource,
DataSourceEmbeddingState.QUEUED,
knownStatus?.TotalFiles ?? 0,
knownStatus?.IndexedFiles ?? 0,
knownStatus?.FailedFiles ?? 0,
failures: knownStatus?.Failures ?? [],
permanentlySkippedFiles: knownStatus?.PermanentlySkippedFiles ?? 0);
}
// One message for the whole list, rather than one per data source:
this.PublishStatusChanged();
foreach (var dataSource in supportedDataSources)
{
token.ThrowIfCancellationRequested();