Document blended caption retrieval and Jellyfin display limits

This commit is contained in:
Sleeps
2026-10-08 10:32:51 +01:00
parent 367e75ac8c
commit 035da1bb1f
+23 -10
View File
@@ -539,23 +539,36 @@ Search is blocked only while the local routing GPU is in use and while Meilisear
Plugin-triggered indexing reuses the API process's existing SigLIP instance and blocks semantic searches while the indexing job owns the model, avoiding a second GPU copy on the same machine.
The prefix is intentional for the first rollout. Jellyfin 12 uses non-empty external-provider results instead of its built-in SQL search results. While only a test library is indexed, making Scene Search answer every query could hide ordinary Jellyfin results that have not been indexed yet.
Normal Jellyfin searches now combine external providers, including the separate
Jellyfin Meilisearch plugin and Scene Search. Hybrid visual similarity still
finds semantic scenes; a separate caption-only text query ensures that literal
caption phrases are not buried below millions of visual frame matches. At
most two distinct exact-caption items receive a tiny reserved score boost
above normal Meilisearch scores (0–1), leaving most results for normal title
and other provider matches. This runs against the **existing** Meilisearch
documents and does **not** require re-captioning or a full Meilisearch rebuild.
With the default configuration:
The optional `scene:` prefix still gives Scene Search stronger preference and
is stripped before querying the backend:
```text
scene: woman standing outside
```
uses semantic Scene Search, while:
Jellyfin 12's standard search cards display Jellyfin media metadata, **not
caption excerpts**: an external `SearchResult` contains only an item ID and
score. To see why an item matched, open **Dashboard → Plugins → Scene Search →
Jellyfin Search Diagnostics**, enter the same phrase and inspect the *Top API
results*. They include `[EXACT CAPTION MATCH]` and the best caption text where
available. The standalone Scene Search dashboard still displays scenes and
captions. An item can have a saved caption in `caption_windows` while its
`frames.caption` is null; only the representative frame carries the window
caption into the serving index.
```text
Alien
```
continues to use Jellyfin's normal search.
Once the complete libraries you care about are indexed and semantic ranking is calibrated, the prefix requirement can be disabled in the plugin settings so normal Jellyfin searches use Scene Search directly.
If the API returns caption matches but Jellyfin does not, check the diagnostics
for `API/core overlap` and `Resolved in Jellyfin DB`, and check that both the
Docker Scene Search service and the Jellyfin plugin DLL were updated. Caption
synchronisation progress and any failures appear in the caption job status.
The first version contributes Movies, Episodes and generic Videos because those are the item types currently ingested by `jellyfin-index`.