nucliadb 6.4.0.post4319__py3-none-any.whl → 6.4.0.post4329__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- nucliadb/ingest/orm/brain_v2.py +4 -3
- nucliadb/ingest/orm/index_message.py +8 -6
- {nucliadb-6.4.0.post4319.dist-info → nucliadb-6.4.0.post4329.dist-info}/METADATA +6 -6
- {nucliadb-6.4.0.post4319.dist-info → nucliadb-6.4.0.post4329.dist-info}/RECORD +7 -7
- {nucliadb-6.4.0.post4319.dist-info → nucliadb-6.4.0.post4329.dist-info}/WHEEL +0 -0
- {nucliadb-6.4.0.post4319.dist-info → nucliadb-6.4.0.post4329.dist-info}/entry_points.txt +0 -0
- {nucliadb-6.4.0.post4319.dist-info → nucliadb-6.4.0.post4329.dist-info}/top_level.txt +0 -0
nucliadb/ingest/orm/brain_v2.py
CHANGED
@@ -215,7 +215,8 @@ class ResourceBrain:
|
|
215
215
|
page_positions: Optional[FilePagePositions],
|
216
216
|
user_field_metadata: Optional[UserFieldMetadata],
|
217
217
|
replace_field: bool,
|
218
|
-
|
218
|
+
skip_paragraphs_index: Optional[bool],
|
219
|
+
skip_texts_index: Optional[bool],
|
219
220
|
) -> None:
|
220
221
|
# We need to add the extracted text to the texts section of the Resource so that
|
221
222
|
# the paragraphs can be indexed
|
@@ -223,7 +224,7 @@ class ResourceBrain:
|
|
223
224
|
field_key,
|
224
225
|
extracted_text,
|
225
226
|
replace_field=False,
|
226
|
-
skip_texts=
|
227
|
+
skip_texts=skip_texts_index,
|
227
228
|
)
|
228
229
|
self.apply_field_paragraphs(
|
229
230
|
field_key,
|
@@ -232,7 +233,7 @@ class ResourceBrain:
|
|
232
233
|
page_positions,
|
233
234
|
user_field_metadata,
|
234
235
|
replace_field=replace_field,
|
235
|
-
skip_paragraphs=
|
236
|
+
skip_paragraphs=skip_paragraphs_index,
|
236
237
|
)
|
237
238
|
|
238
239
|
@observer.wrap({"type": "apply_field_paragraphs"})
|
@@ -80,8 +80,8 @@ class IndexMessageBuilder:
|
|
80
80
|
if texts or paragraphs:
|
81
81
|
# We need to compute the texts when we're going to generate the paragraphs too, but we may not
|
82
82
|
# want to index them always.
|
83
|
-
|
84
|
-
replace_texts = replace and not
|
83
|
+
skip_texts_index = not texts
|
84
|
+
replace_texts = replace and not skip_texts_index
|
85
85
|
|
86
86
|
if extracted_text is not None:
|
87
87
|
try:
|
@@ -96,13 +96,14 @@ class IndexMessageBuilder:
|
|
96
96
|
basic.usermetadata,
|
97
97
|
field_author,
|
98
98
|
replace_field=replace_texts,
|
99
|
-
skip_index=
|
99
|
+
skip_index=skip_texts_index,
|
100
100
|
)
|
101
101
|
if paragraphs or vectors:
|
102
102
|
# The paragraphs are needed to generate the vectors. However, we don't need to index them
|
103
103
|
# in all cases.
|
104
|
-
|
105
|
-
|
104
|
+
skip_paragraphs_index = not paragraphs
|
105
|
+
skip_texts_index = not texts
|
106
|
+
replace_paragraphs = replace and not skip_paragraphs_index
|
106
107
|
|
107
108
|
# We need to compute the paragraphs when we're going to generate the vectors too.
|
108
109
|
if extracted_text is not None and field_computed_metadata is not None:
|
@@ -117,7 +118,8 @@ class IndexMessageBuilder:
|
|
117
118
|
page_positions,
|
118
119
|
user_field_metadata,
|
119
120
|
replace_field=replace_paragraphs,
|
120
|
-
|
121
|
+
skip_paragraphs_index=skip_paragraphs_index,
|
122
|
+
skip_texts_index=skip_texts_index,
|
121
123
|
)
|
122
124
|
if vectors:
|
123
125
|
assert vectorset_configs is not None
|
@@ -1,6 +1,6 @@
|
|
1
1
|
Metadata-Version: 2.4
|
2
2
|
Name: nucliadb
|
3
|
-
Version: 6.4.0.
|
3
|
+
Version: 6.4.0.post4329
|
4
4
|
Summary: NucliaDB
|
5
5
|
Author-email: Nuclia <nucliadb@nuclia.com>
|
6
6
|
License-Expression: AGPL-3.0-or-later
|
@@ -19,11 +19,11 @@ Classifier: Programming Language :: Python :: 3.12
|
|
19
19
|
Classifier: Programming Language :: Python :: 3 :: Only
|
20
20
|
Requires-Python: <4,>=3.9
|
21
21
|
Description-Content-Type: text/markdown
|
22
|
-
Requires-Dist: nucliadb-telemetry[all]>=6.4.0.
|
23
|
-
Requires-Dist: nucliadb-utils[cache,fastapi,storages]>=6.4.0.
|
24
|
-
Requires-Dist: nucliadb-protos>=6.4.0.
|
25
|
-
Requires-Dist: nucliadb-models>=6.4.0.
|
26
|
-
Requires-Dist: nidx-protos>=6.4.0.
|
22
|
+
Requires-Dist: nucliadb-telemetry[all]>=6.4.0.post4329
|
23
|
+
Requires-Dist: nucliadb-utils[cache,fastapi,storages]>=6.4.0.post4329
|
24
|
+
Requires-Dist: nucliadb-protos>=6.4.0.post4329
|
25
|
+
Requires-Dist: nucliadb-models>=6.4.0.post4329
|
26
|
+
Requires-Dist: nidx-protos>=6.4.0.post4329
|
27
27
|
Requires-Dist: nucliadb-admin-assets>=1.0.0.post1224
|
28
28
|
Requires-Dist: nuclia-models>=0.24.2
|
29
29
|
Requires-Dist: uvicorn[standard]
|
@@ -147,11 +147,11 @@ nucliadb/ingest/fields/generic.py,sha256=elgtqv15aJUq3zY7X_g0bli_2BpcwPArVvzhe54
|
|
147
147
|
nucliadb/ingest/fields/link.py,sha256=kN_gjRUEEj5cy8K_BwPijYg3TiWhedc24apXYlTbRJs,4172
|
148
148
|
nucliadb/ingest/fields/text.py,sha256=2grxo8twWbpXEd_iwUMBw9q0dWorVmlPONmY5d1ThwQ,1684
|
149
149
|
nucliadb/ingest/orm/__init__.py,sha256=cp15ZcFnHvpcu_5-aK2A4uUyvuZVV_MJn4bIXMa20ks,835
|
150
|
-
nucliadb/ingest/orm/brain_v2.py,sha256=
|
150
|
+
nucliadb/ingest/orm/brain_v2.py,sha256=y_OQ-SXyClX_VSKFVkYYwdIDxmj6TAQLC7UdPJ0hOvE,33647
|
151
151
|
nucliadb/ingest/orm/broker_message.py,sha256=XWaiZgDOz94NPOPT-hqbRr5ZkpVimUw6PjUJNftfoVw,7514
|
152
152
|
nucliadb/ingest/orm/entities.py,sha256=kXyeF6XOpFKhEsGLcY-GLIk21Exp0cJst4XQQ9jJoug,14791
|
153
153
|
nucliadb/ingest/orm/exceptions.py,sha256=k4Esv4NtL4TrGTcsQpwrSfDhPQpiYcRbB1SpYmBX5MY,1432
|
154
|
-
nucliadb/ingest/orm/index_message.py,sha256=
|
154
|
+
nucliadb/ingest/orm/index_message.py,sha256=DWMTHJoVamUbK8opKl5csDvxfgz7c2j7phG1Ut4yIxk,15724
|
155
155
|
nucliadb/ingest/orm/knowledgebox.py,sha256=_rkeTMIXMhR64gbYtZpFHoUHghV2DTJ2lUBqZsoqC_4,23898
|
156
156
|
nucliadb/ingest/orm/metrics.py,sha256=OiuggTh-n3kZHA2G73NEUdIlh8c3yFrbusI88DK-Mko,1273
|
157
157
|
nucliadb/ingest/orm/resource.py,sha256=hGELQgnzK2wIWgD478bR5OiVDyAxHn6WrFSq2YuHANU,36896
|
@@ -368,8 +368,8 @@ nucliadb/writer/tus/local.py,sha256=7jYa_w9b-N90jWgN2sQKkNcomqn6JMVBOVeDOVYJHto,
|
|
368
368
|
nucliadb/writer/tus/s3.py,sha256=vF0NkFTXiXhXq3bCVXXVV-ED38ECVoUeeYViP8uMqcU,8357
|
369
369
|
nucliadb/writer/tus/storage.py,sha256=ToqwjoYnjI4oIcwzkhha_MPxi-k4Jk3Lt55zRwaC1SM,2903
|
370
370
|
nucliadb/writer/tus/utils.py,sha256=MSdVbRsRSZVdkaum69_0wku7X3p5wlZf4nr6E0GMKbw,2556
|
371
|
-
nucliadb-6.4.0.
|
372
|
-
nucliadb-6.4.0.
|
373
|
-
nucliadb-6.4.0.
|
374
|
-
nucliadb-6.4.0.
|
375
|
-
nucliadb-6.4.0.
|
371
|
+
nucliadb-6.4.0.post4329.dist-info/METADATA,sha256=7q-NzZGycWXVtZ6akhOdxYQFPtXxVL_Zl3OFvKXqFoo,4152
|
372
|
+
nucliadb-6.4.0.post4329.dist-info/WHEEL,sha256=Nw36Djuh_5VDukK0H78QzOX-_FQEo6V37m3nkm96gtU,91
|
373
|
+
nucliadb-6.4.0.post4329.dist-info/entry_points.txt,sha256=XqGfgFDuY3zXQc8ewXM2TRVjTModIq851zOsgrmaXx4,1268
|
374
|
+
nucliadb-6.4.0.post4329.dist-info/top_level.txt,sha256=hwYhTVnX7jkQ9gJCkVrbqEG1M4lT2F_iPQND1fCzF80,20
|
375
|
+
nucliadb-6.4.0.post4329.dist-info/RECORD,,
|
File without changes
|
File without changes
|
File without changes
|