Find a file
Bogdan Abaev 2568b5ccc4 Semantic search on fulltext of attachments
Add optional pref to index and search fulltext of attachments.
When enabled, attachment IDs are enqueue after regular items,
notes, and annotations.

Added helpers to extract outline and sections from structured
text module. During indexing, the sections of the attachment
are extracted, large sections are broken into chunks, and
small sections are combined to fit into the context window
of the model. Then, each chunk is embedded with its outline
path as the prefix and added to embeddings table.
Each row now contains full text of the chunk
and it's path - a good amount of duplication needed to
ensure that we can reliably connect the embedding of
the chunk to its text for a preview.

On search in Best Match mode, attachment rows get the score
of the highest ranking chunk, so if there is a very relevant
chunk in an attachment, the regular item with a non-relevant
abstract will still rank highly.

When the attachment row is selected, top 5 matching chunks
appear in the new search results collapsible-section of
the item pane, so one can examine matching chunks
without opening the actual reader.
2026-08-13 13:39:30 -07:00
.github/workflows CI: Don't run duplicate jobs for same-repo pull requests 2026-07-08 10:50:32 -04:00
app Restore dxcompiler.dll on Windows for WebGPU and leave WebGPU pref on 2026-08-05 14:10:04 -04:00
chrome Semantic search on fulltext of attachments 2026-08-13 13:39:30 -07:00
defaults/preferences Semantic search on fulltext of attachments 2026-08-13 13:39:30 -07:00
document-worker@6d0c0ce45d Update document-worker submodule 2026-07-15 12:52:00 -04:00
js-build Add SDT support 2026-06-12 13:47:08 +03:00
note-editor@acec74d09b Improve undo/redo in the note editor (#3398) 2026-07-31 14:22:53 +02:00
reader@c6edbfff75 Update reader submodule 2026-07-20 10:50:56 -04:00
resource Generate embeddings with Firefox's inference runtime 2026-08-05 15:41:41 -04:00
scripts Add script for pulling Fluent translations 2026-01-25 22:15:29 -05:00
scss Semantic search on fulltext of attachments 2026-08-13 13:39:30 -07:00
styles@dff7452b24 Update translators, styles, CSL locales, and renamed-styles.json 2026-04-02 15:51:43 -04:00
test Semantic search on fulltext of attachments 2026-08-13 13:39:30 -07:00
translators@60f2d542ff Update translators submodule 2026-07-15 12:52:54 -04:00
types/gecko fx140: Update type definitions 2025-07-30 22:30:37 -04:00
.babelrc Use production builds of react libraries (#4482) 2024-08-02 03:43:02 -04:00
.gitattributes local semantic search on abstracts 2026-08-05 15:26:55 -04:00
.gitignore Use user-provided codesign script for Windows signing 2024-04-08 10:12:58 +01:00
.gitmodules Rename pdf-worker submodule to document-worker 2026-04-22 15:50:02 -04:00
chrome.manifest Remove old citation dialogs (#5177) 2025-04-02 05:26:06 -04:00
CLAUDE.md Rename pdf-worker submodule to document-worker 2026-04-22 15:50:02 -04:00
CONTRIBUTING.md Add "support questions" to CONTRIBUTING.md 2022-12-01 05:10:42 -05:00
COPYING Update COPYING 2018-03-26 11:27:48 +02:00
eslint.config.mjs Convert ItemPane{SectionElement,Container}Base to ES modules 2026-05-18 15:48:31 -04:00
package-lock.json Update package-lock.json 2026-01-29 13:22:13 -05:00
package.json Upgrade ftl-tx. Fix #5671. 2025-12-20 02:22:23 +01:00
README.md "Zotero wiki" → "Zotero documentation" in app build README 2023-04-26 04:40:22 -04:00
update.rdf Update Fx minVersion to 45 2016-12-13 09:12:55 -05:00
version Update version to 11.0 2026-08-03 14:14:05 -04:00

Zotero

CI

Zotero is a free, easy-to-use tool to help you collect, organize, cite, and share your research sources.

Please post feature requests or bug reports to the Zotero Forums. If you're having trouble with Zotero, see Getting Help.

For more information on how to use this source code, see the Zotero documentation.