Louis Dureuil
6641c3f59b
Remove all autogenerated tests
2024-11-20 13:16:34 +01:00
Louis Dureuil
07a72824b7
Subfields of _vectors are no longer part of the fid map
2024-11-20 13:16:34 +01:00
Louis Dureuil
000eb55c4e
fix one
2024-11-20 13:16:34 +01:00
Louis Dureuil
1aef0e4037
documents! macro accepts a single object again
2024-11-20 13:16:33 +01:00
Clément Renault
32d0e50a75
Fix all the benchmark compilation errors
2024-11-20 13:16:32 +01:00
Louis Dureuil
df5884b0c1
Fix settings test
2024-11-20 13:16:32 +01:00
Louis Dureuil
9e0eb5ebb0
Removed some warnings
2024-11-20 13:16:32 +01:00
Clément Renault
3cf1352ae1
Fix the benchmark tests
2024-11-20 13:16:31 +01:00
Clément Renault
aba8a0e9e0
Fix some tests but not all of them
2024-11-20 13:16:31 +01:00
Clément Renault
670aff5553
Remove useless Transform methods
2024-11-20 13:16:08 +01:00
Tamo
229fa0f902
implements the batch details
2024-11-20 10:51:06 +01:00
Lukas Kalbertodt
057fcb3993
Add indices field to _matchesPosition to specify where in an array a match comes from ( #5005 )
...
Indexing bench (push) / Run and upload benchmarks (push) Waiting to run
Benchmarks of indexing (push) / Run and upload benchmarks (push) Waiting to run
Benchmarks of search for geo (push) / Run and upload benchmarks (push) Waiting to run
Benchmarks of search for songs (push) / Run and upload benchmarks (push) Waiting to run
Benchmarks of search for Wikipedia articles (push) / Run and upload benchmarks (push) Waiting to run
Run the indexing fuzzer / Setup the action (push) Successful in 1h4m31s
* Remove unreachable code
* Add `indices` field to `MatchBounds`
For matches inside arrays, this field holds the indices of the array
elements that matched. For example, searching for `cat` inside
`{ "a": ["dog", "cat", "fox"] }` would return `indices: [1]`. For nested
arrays, this contains multiple indices, starting with the one for the
top-most array. For matches in fields without arrays, `indices` is not
serialized (does not exist) to save space.
2024-11-20 01:00:43 +01:00
ManyTheFish
41dbdd2d18
Fix filtered_placeholder_search_should_not_return_deleted_documents and word_scale_set_and_reset
2024-11-19 16:08:25 +01:00
Louis Dureuil
c782c09208
Move step to a dedicated mod and replace it with an enum
2024-11-18 18:22:13 +01:00
Louis Dureuil
75943a5a9b
Add TODO to remember replacing steps with an enum
2024-11-18 17:40:51 +01:00
Louis Dureuil
04c38220ca
Move MostlySend, ThreadLocal, FullySend to their own commit
2024-11-18 16:43:05 +01:00
Louis Dureuil
5f93651cef
fixes
2024-11-18 16:23:11 +01:00
ManyTheFish
510ca99996
Fixes #4974
2024-11-18 16:08:55 +01:00
ManyTheFish
e0c3f3d560
Fix #4984
2024-11-18 16:08:53 +01:00
Louis Dureuil
0a21d9bfb3
Fix double borrow of new fields id map
2024-11-18 15:56:01 +01:00
Louis Dureuil
e736a74729
Remove infinite loop in import_vectors
2024-11-18 12:50:56 +01:00
Louis Dureuil
e9d17136b2
Add deadline of 3 seconds to embedding requests made in the context of hybrid search
2024-11-18 12:15:11 +01:00
ManyTheFish
cd796b0f4b
Fix SDK test
2024-11-18 11:46:00 +01:00
Louis Dureuil
6570da3bcb
Retry in case where the JSON deserialization fails
2024-11-18 11:33:09 +01:00
Clément Renault
5b4c06c24c
Plug the grenad max memory parameter
2024-11-18 11:28:04 +01:00
Louis Dureuil
3a8051866a
Use return_keyword_results function instead of returning raw keyword results when the embedder is broken
2024-11-18 11:17:15 +01:00
Louis Dureuil
c202f3dbe2
fix tests and revert change in behavior when primary_key_from_op != primary_key_from_db && index.is_empty()
2024-11-18 10:59:05 +01:00
Clément Renault
677d7293f5
Fix a lot of primary key related tests
2024-11-18 10:59:05 +01:00
Clément Renault
83865d2ebd
Expose intermediate errors when processing batches
2024-11-18 10:59:05 +01:00
ManyTheFish
4ff2b3c2ee
Fix test on locales
2024-11-14 15:45:04 +01:00
ManyTheFish
91c58cfa38
Fix positional databases
2024-11-14 11:40:12 +01:00
Clément Renault
9e8367f1e6
Move the rayon thread pool outside the extract method
2024-11-14 10:40:32 +01:00
Louis Dureuil
0e3c5d91ab
Document deletion test passes
2024-11-14 08:42:56 +01:00
Louis Dureuil
695c2c6b99
Cosmetic fix
2024-11-14 08:42:39 +01:00
Louis Dureuil
40dd25d6b2
Fix issue with Replace document method when adding and deleting a document in the same batch
2024-11-13 22:10:00 +01:00
Clément Renault
8e5b1a3ec1
Compute the field distribution and convert _geo into an f64s
2024-11-13 17:44:05 +01:00
ManyTheFish
e627e182ce
Fix facet strings
2024-11-13 17:43:02 +01:00
ManyTheFish
51b6293738
Add linear facet databases
2024-11-13 17:43:02 +01:00
Clément Renault
b17896d899
Finialize the GeoExtractor
2024-11-13 17:43:02 +01:00
Louis Dureuil
7accfea624
Don't short circuit when we encounter a semantic error while extracting fields and external docid
2024-11-13 10:33:59 +01:00
Louis Dureuil
3b0cb5b487
Fix vector error messages
2024-11-12 23:26:16 +01:00
Louis Dureuil
bfdcd1cf33
Space changes
2024-11-12 22:52:45 +01:00
Louis Dureuil
c4e9f761e9
Emit better error messages when parsing vectors
2024-11-12 22:49:22 +01:00
Louis Dureuil
8a6e61c77f
InvalidVectorsEmbedderConf error takes a String rather than a deserr error
2024-11-12 22:47:57 +01:00
Louis Dureuil
980921e078
Vector fixes
2024-11-12 16:31:22 +01:00
Louis Dureuil
6094bb299a
Fix user_provided vectors
2024-11-12 10:15:55 +01:00
Louis Dureuil
bef8fc6cf1
Fix hf embedder
2024-11-08 13:10:17 +01:00
Louis Dureuil
5185aa21b8
Know if your vectors are implicit when writing them back in documents + don't write empty _vectors
2024-11-08 00:05:36 +01:00
Louis Dureuil
8a314ab81d
Fix primary key fid order
2024-11-08 00:05:12 +01:00
Louis Dureuil
4706a0eb49
Fix vector parsing
2024-11-07 23:26:20 +01:00
