Commit Graph

38 Commits

Author SHA1 Message Date
90e6b6416f new extractor bugfixes:
- fix old_has_fragments
- new_is_user_provided is always false when generating fragments,
  even if no fragment ever matches
2025-07-03 14:35:02 +02:00
735634e998 Send owned metadata and clear inputs in case of error 2025-07-03 10:32:57 +02:00
a06cb1bfd6 Remove Embed::process_embeddings and have it be an inherent function of the type that uses it 2025-07-03 10:02:16 +02:00
b086c51a23 new settings indexer 2025-07-02 00:05:13 +02:00
f8232976ed Implement in new document indexer 2025-07-02 00:05:12 +02:00
e414284335 Clippy too many arguments 2025-06-30 14:25:28 +02:00
7a204609fe Move document context and identifiers in document.rs 2025-06-30 14:21:46 +02:00
6db5939f84 Re-integrate embedder stats 2025-06-30 09:52:06 +02:00
0687cf058a Avoid rewritting documents that don't change
Ensure being on a reindex action before getting embedder_category_id

Fix document skip function
2025-06-30 09:52:06 +02:00
77802dabf6 rename DocumentChangeContext into DocumentContext 2025-06-26 18:14:48 +02:00
900be0ccad Extract or regenerate vectors related to settings changes 2025-06-26 18:14:48 +02:00
29f6eeff8f Remove lots of Arcs 2025-06-26 12:15:08 +02:00
d08e89ea3d Remove options 2025-06-24 15:10:15 +02:00
695877043a Fix warnings 2025-06-24 14:53:39 +02:00
4925b30196 Move embedder stats out of progress 2025-06-23 15:24:14 +02:00
4cadc8113b Add embedder stats in batches 2025-06-20 12:42:22 +02:00
7200437246 Comment the cases 2025-06-12 15:55:52 +02:00
68e7bfb37f Don't fail if you cannot render previous version 2025-06-12 15:55:33 +02:00
209c4bfc18 Switch the versions of the documents for rendering :/ 2025-06-12 15:47:47 +02:00
396d76046d Regenerate embeddings more often:
- When `regenerate` was previously `false` and became `true`
- When rendering the old version of the docs failed
2025-06-12 15:41:53 +02:00
b025f1bcf1 Merge branch 'main' into release-v1.14.0-tmp 2025-04-14 12:35:47 +02:00
4d90e3d2ec Make Cargo and Clippy happy 2025-04-01 11:26:34 +02:00
f729864466 Check dimension mismatch at insertion time 2025-03-31 15:27:49 +02:00
4a2643daa2 Rename embed_one to embed_search and embed_chunks* to embed_index* 2025-02-24 13:58:26 +01:00
b83275c9c5 Change the updated* functions to only_new functions, hopefully better communicating what they do 2025-02-11 15:27:10 +01:00
bfca54cc2c Return docid in case of errors while rendering the document template 2024-12-11 15:26:18 +01:00
70802eb7c7 Fix most issues with the lifetimes 2024-11-27 14:32:42 +01:00
6ac5b3b136 Finish most of the channels types 2024-11-27 14:32:26 +01:00
8442db8101 Implement mostly all senders 2024-11-27 14:16:35 +01:00
04c38220ca Move MostlySend, ThreadLocal, FullySend to their own commit 2024-11-18 16:43:05 +01:00
b17896d899 Finialize the GeoExtractor 2024-11-13 17:43:02 +01:00
3b0cb5b487 Fix vector error messages 2024-11-12 23:26:16 +01:00
c4e9f761e9 Emit better error messages when parsing vectors 2024-11-12 22:49:22 +01:00
980921e078 Vector fixes 2024-11-12 16:31:22 +01:00
6094bb299a Fix user_provided vectors 2024-11-12 10:15:55 +01:00
e2138170ad some warning fix 2024-11-07 10:06:07 +01:00
10f49f0d75 Post processing of the merge 2024-11-06 17:50:12 +01:00
ee03743355 Merge branch 'indexer-edition-2024' into indexer-edition-2024-doc-chunks 2024-11-06 15:50:53 +01:00