nucliadb 6.4.0.post4317__py3-none-any.whl → 6.4.0.post4325__py3-none-any.whl

nucliadb/ingest/orm/brain_v2.py

@@ -215,7 +215,8 @@ class ResourceBrain:
         page_positions: Optional[FilePagePositions],
         user_field_metadata: Optional[UserFieldMetadata],
         replace_field: bool,
-        skip_index: Optional[bool],
+        skip_paragraphs_index: Optional[bool],
+        skip_texts_index: Optional[bool],
     ) -> None:
         # We need to add the extracted text to the texts section of the Resource so that
         # the paragraphs can be indexed
@@ -223,7 +224,7 @@ class ResourceBrain:
             field_key,
             extracted_text,
             replace_field=False,
-            skip_texts=None,
+            skip_texts=skip_texts_index,
         )
         self.apply_field_paragraphs(
             field_key,
@@ -232,7 +233,7 @@ class ResourceBrain:
             page_positions,
             user_field_metadata,
             replace_field=replace_field,
-            skip_paragraphs=skip_index,
+            skip_paragraphs=skip_paragraphs_index,
         )
 
     @observer.wrap({"type": "apply_field_paragraphs"})

nucliadb/ingest/orm/index_message.py

@@ -80,8 +80,8 @@ class IndexMessageBuilder:
         if texts or paragraphs:
             # We need to compute the texts when we're going to generate the paragraphs too, but we may not
             # want to index them always.
-            skip_index_texts = not texts
-            replace_texts = replace and not skip_index_texts
+            skip_texts_index = not texts
+            replace_texts = replace and not skip_texts_index
 
             if extracted_text is not None:
                 try:
@@ -96,13 +96,14 @@ class IndexMessageBuilder:
                     basic.usermetadata,
                     field_author,
                     replace_field=replace_texts,
-                    skip_index=skip_index_texts,
+                    skip_index=skip_texts_index,
                 )
         if paragraphs or vectors:
             # The paragraphs are needed to generate the vectors. However, we don't need to index them
             # in all cases.
-            skip_index_paragraphs = not paragraphs
-            replace_paragraphs = replace and not skip_index_paragraphs
+            skip_paragraphs_index = not paragraphs
+            skip_texts_index = not texts
+            replace_paragraphs = replace and not skip_paragraphs_index
 
             # We need to compute the paragraphs when we're going to generate the vectors too.
             if extracted_text is not None and field_computed_metadata is not None:
@@ -117,7 +118,8 @@ class IndexMessageBuilder:
                     page_positions,
                     user_field_metadata,
                     replace_field=replace_paragraphs,
-                    skip_index=skip_index_paragraphs,
+                    skip_paragraphs_index=skip_paragraphs_index,
+                    skip_texts_index=skip_texts_index,
                 )
         if vectors:
             assert vectorset_configs is not None

{nucliadb-6.4.0.post4317.dist-info → nucliadb-6.4.0.post4325.dist-info}/METADATA

@@ -1,9 +1,9 @@
 Metadata-Version: 2.4
 Name: nucliadb
-Version: 6.4.0.post4317
+Version: 6.4.0.post4325
 Summary: NucliaDB
 Author-email: Nuclia <nucliadb@nuclia.com>
-License: AGPL
+License-Expression: AGPL-3.0-or-later
 Project-URL: Nuclia, https://nuclia.com
 Project-URL: Github, https://github.com/nuclia/nucliadb
 Project-URL: Slack, https://nuclia-community.slack.com
@@ -11,7 +11,6 @@ Project-URL: API Reference, https://docs.nuclia.dev/docs/api
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Information Technology
-Classifier: License :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)
 Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
@@ -20,11 +19,11 @@ Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3 :: Only
 Requires-Python: <4,>=3.9
 Description-Content-Type: text/markdown
-Requires-Dist: nucliadb-telemetry[all]>=6.4.0.post4317
-Requires-Dist: nucliadb-utils[cache,fastapi,storages]>=6.4.0.post4317
-Requires-Dist: nucliadb-protos>=6.4.0.post4317
-Requires-Dist: nucliadb-models>=6.4.0.post4317
-Requires-Dist: nidx-protos>=6.4.0.post4317
+Requires-Dist: nucliadb-telemetry[all]>=6.4.0.post4325
+Requires-Dist: nucliadb-utils[cache,fastapi,storages]>=6.4.0.post4325
+Requires-Dist: nucliadb-protos>=6.4.0.post4325
+Requires-Dist: nucliadb-models>=6.4.0.post4325
+Requires-Dist: nidx-protos>=6.4.0.post4325
 Requires-Dist: nucliadb-admin-assets>=1.0.0.post1224
 Requires-Dist: nuclia-models>=0.24.2
 Requires-Dist: uvicorn[standard]

{nucliadb-6.4.0.post4317.dist-info → nucliadb-6.4.0.post4325.dist-info}/RECORD

@@ -147,11 +147,11 @@ nucliadb/ingest/fields/generic.py,sha256=elgtqv15aJUq3zY7X_g0bli_2BpcwPArVvzhe54
 nucliadb/ingest/fields/link.py,sha256=kN_gjRUEEj5cy8K_BwPijYg3TiWhedc24apXYlTbRJs,4172
 nucliadb/ingest/fields/text.py,sha256=2grxo8twWbpXEd_iwUMBw9q0dWorVmlPONmY5d1ThwQ,1684
 nucliadb/ingest/orm/__init__.py,sha256=cp15ZcFnHvpcu_5-aK2A4uUyvuZVV_MJn4bIXMa20ks,835
-nucliadb/ingest/orm/brain_v2.py,sha256=qX81wvU-KCcEZ-hNgkQOskMOlZmdbJqDyAfe7eXbGLw,33571
+nucliadb/ingest/orm/brain_v2.py,sha256=y_OQ-SXyClX_VSKFVkYYwdIDxmj6TAQLC7UdPJ0hOvE,33647
 nucliadb/ingest/orm/broker_message.py,sha256=XWaiZgDOz94NPOPT-hqbRr5ZkpVimUw6PjUJNftfoVw,7514
 nucliadb/ingest/orm/entities.py,sha256=kXyeF6XOpFKhEsGLcY-GLIk21Exp0cJst4XQQ9jJoug,14791
 nucliadb/ingest/orm/exceptions.py,sha256=k4Esv4NtL4TrGTcsQpwrSfDhPQpiYcRbB1SpYmBX5MY,1432
-nucliadb/ingest/orm/index_message.py,sha256=hI85nSNVChNLLdEFuEJvOt61Tsir-Gq-2_WZoayAdvk,15617
+nucliadb/ingest/orm/index_message.py,sha256=DWMTHJoVamUbK8opKl5csDvxfgz7c2j7phG1Ut4yIxk,15724
 nucliadb/ingest/orm/knowledgebox.py,sha256=_rkeTMIXMhR64gbYtZpFHoUHghV2DTJ2lUBqZsoqC_4,23898
 nucliadb/ingest/orm/metrics.py,sha256=OiuggTh-n3kZHA2G73NEUdIlh8c3yFrbusI88DK-Mko,1273
 nucliadb/ingest/orm/resource.py,sha256=hGELQgnzK2wIWgD478bR5OiVDyAxHn6WrFSq2YuHANU,36896
@@ -368,8 +368,8 @@ nucliadb/writer/tus/local.py,sha256=7jYa_w9b-N90jWgN2sQKkNcomqn6JMVBOVeDOVYJHto,
 nucliadb/writer/tus/s3.py,sha256=vF0NkFTXiXhXq3bCVXXVV-ED38ECVoUeeYViP8uMqcU,8357
 nucliadb/writer/tus/storage.py,sha256=ToqwjoYnjI4oIcwzkhha_MPxi-k4Jk3Lt55zRwaC1SM,2903
 nucliadb/writer/tus/utils.py,sha256=MSdVbRsRSZVdkaum69_0wku7X3p5wlZf4nr6E0GMKbw,2556
-nucliadb-6.4.0.post4317.dist-info/METADATA,sha256=d8tAT1pIjUuErJUdwLw2yt9bgSnVJn2U7KkhldSRAZU,4223
-nucliadb-6.4.0.post4317.dist-info/WHEEL,sha256=Nw36Djuh_5VDukK0H78QzOX-_FQEo6V37m3nkm96gtU,91
-nucliadb-6.4.0.post4317.dist-info/entry_points.txt,sha256=XqGfgFDuY3zXQc8ewXM2TRVjTModIq851zOsgrmaXx4,1268
-nucliadb-6.4.0.post4317.dist-info/top_level.txt,sha256=hwYhTVnX7jkQ9gJCkVrbqEG1M4lT2F_iPQND1fCzF80,20
-nucliadb-6.4.0.post4317.dist-info/RECORD,,
+nucliadb-6.4.0.post4325.dist-info/METADATA,sha256=EHNT9isM_3bXOQpMkbHnrEhR_wQ327foVOp_xfETAn4,4152
+nucliadb-6.4.0.post4325.dist-info/WHEEL,sha256=Nw36Djuh_5VDukK0H78QzOX-_FQEo6V37m3nkm96gtU,91
+nucliadb-6.4.0.post4325.dist-info/entry_points.txt,sha256=XqGfgFDuY3zXQc8ewXM2TRVjTModIq851zOsgrmaXx4,1268
+nucliadb-6.4.0.post4325.dist-info/top_level.txt,sha256=hwYhTVnX7jkQ9gJCkVrbqEG1M4lT2F_iPQND1fCzF80,20
+nucliadb-6.4.0.post4325.dist-info/RECORD,,