MindWorkAI/AI-Studio
1
0 Fork 0
mirror of https://github.com/MindWorkAI/AI-Studio.git synced 2026-11-05 00:47:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

Added a way to read what the AI received from your sources (#1100)

Browse Source 
Co-authored-by: Thorsten Sommer <SommerEngineering@users.noreply.github.com>
This commit is contained in:
Paul KoudelkaandThorsten Sommer authored and GitHub committed 2026-10-26 10:00:01 +01:00
1 parent e0d8e18f34
commit cbc4ce5413
229 files changed
+12739 -1269
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

app/Tests/Tools/Databases/IndexStoreFullTextSearchTests.cs
+22 -1
View File
@@ -39,6 +39,27 @@ public sealed class IndexStoreFullTextSearchTests
});
}
[Test]
public async Task AChunkFoundKnowsThePagesItSpans()
{
await using var store = await TemporaryIndexStore.CreateAsync();
await store.Client.UpsertDataSourceAsync(DATA_SOURCE_ID, "LOCAL_DIRECTORY", "b0a4c4d2-1f3e-4f0a-8c9d-5a6b7c8d9e01", "signature", string.Empty, 3, TOKEN);
const string PATH = "/tmp/test-data/report.pdf";
var parentFileId = IndexedDocumentIds.CreateParentId(DATA_SOURCE_ID, PATH);
var now = DateTimeOffset.UtcNow;
await store.Client.UpsertFileAsync(DATA_SOURCE_ID, new EmbeddingStateFile(parentFileId, PATH, "report.pdf", "report.pdf", "pdf", PATH, 64, now, now, now, 1), TOKEN);
await store.Client.UpsertChunksAsync(DATA_SOURCE_ID, [new EmbeddingStateChunk(IndexedDocumentIds.CreateChunkId(DATA_SOURCE_ID, PATH, 0), parentFileId, 3, 5, 0, "The report runs over three pages.", now)], TOKEN);
var found = (await store.Client.SearchChunksAsync(DATA_SOURCE_ID, "report", 10, TOKEN)).Single();
Assert.Multiple(() =>
{
Assert.That(found.PageNumber, Is.EqualTo(3));
Assert.That(found.EndPageNumber, Is.EqualTo(5), "The passage the AI receives from this chunk names pages 3 to 5.");
});
}
private static async Task<string> StoreFileAsync(TemporaryIndexStore store, string path, params string[] chunkTexts)
{
var parentFileId = IndexedDocumentIds.CreateParentId(DATA_SOURCE_ID, path);
@@ -47,7 +68,7 @@ public sealed class IndexStoreFullTextSearchTests
await store.Client.UpsertFileAsync(DATA_SOURCE_ID, new EmbeddingStateFile(parentFileId, path, Path.GetFileName(path), Path.GetFileName(path), "md", path, 64, now, now, now, chunkTexts.Length), TOKEN);
await store.Client.UpsertChunksAsync(
DATA_SOURCE_ID,
chunkTexts.Select((text, index) => new EmbeddingStateChunk(IndexedDocumentIds.CreateChunkId(DATA_SOURCE_ID, path, index), parentFileId, null, index, text, now)).ToList(),
chunkTexts.Select((text, index) => new EmbeddingStateChunk(IndexedDocumentIds.CreateChunkId(DATA_SOURCE_ID, path, index), parentFileId, null, null, index, text, now)).ToList(),
TOKEN);
return parentFileId;