nucliadb 6.1.0.post2589__py3-none-any.whl → 6.1.0.post2602__py3-none-any.whl

nucliadb/common/ids.py

@@ -215,3 +215,26 @@ class VectorId:
         index = int(parts[-2])
         field_id = FieldId.from_string("/".join(parts[:-2]))
         return cls(field_id=field_id, index=index, vector_start=start, vector_end=end)
+
+
+def extract_data_augmentation_id(generated_field_id: str) -> Optional[str]:
+    """Data augmentation generated fields have a strict id with the following
+    format:
+    `da-{task_id}-{original:field_type}-{original:field_id}[-{original:split}]`
+
+    @return the `task_id`
+
+    ATENTION: we are assuming ids have been properly generated and `-` is not a
+    valid character, otherwise, this extraction would be wrong and a partial id
+    would be returned.
+
+    """
+    parts = generated_field_id.split("-")
+
+    if len(parts) < 4:
+        return None
+
+    if parts[0] != "da":
+        return None
+
+    return parts[1] or None

nucliadb/ingest/fields/base.py

@@ -21,9 +21,9 @@ from __future__ import annotations
 
 import enum
 from datetime import datetime
-from typing import Any, Optional, Type
+from typing import Any, Generic, Optional, Type, TypeVar
 
-from google.protobuf.message import DecodeError
+from google.protobuf.message import DecodeError, Message
 
 from nucliadb.common import datamanagers
 from nucliadb.ingest.fields.exceptions import InvalidFieldClass, InvalidPBClass
@@ -31,6 +31,7 @@ from nucliadb_protos.resources_pb2 import (
     CloudFile,
     ExtractedTextWrapper,
     ExtractedVectorsWrapper,
+    FieldAuthor,
     FieldComputedMetadata,
     FieldComputedMetadataWrapper,
     FieldQuestionAnswers,
@@ -56,8 +57,11 @@ class FieldTypes(str, enum.Enum):
     QUESTION_ANSWERS = "question_answers"
 
 
-class Field:
-    pbklass: Type
+PbType = TypeVar("PbType", bound=Message)
+
+
+class Field(Generic[PbType]):
+    pbklass: Type[PbType]
     type: str = "x"
     value: Optional[Any]
     extracted_text: Optional[ExtractedText]
@@ -122,7 +126,7 @@ class Field:
             key = FieldTypes.FIELD_VECTORS.value
         return self.storage.file_extracted(self.kbid, self.uuid, self.type, self.id, key)
 
-    async def db_get_value(self):
+    async def db_get_value(self) -> Optional[PbType]:
         if self.value is None:
             payload = await datamanagers.fields.get_raw(
                 self.resource.txn,
@@ -132,7 +136,7 @@ class Field:
                 field_id=self.id,
             )
             if payload is None:
-                return
+                return None
 
             self.value = self.pbklass()
             self.value.ParseFromString(payload)
@@ -470,6 +474,11 @@ class Field:
                 self.large_computed_metadata = payload
         return self.large_computed_metadata
 
+    async def generated_by(self) -> FieldAuthor:
+        author = FieldAuthor()
+        author.user.SetInParent()
+        return author
+
     def serialize(self):
         return self.value.SerializeToString()
 

nucliadb/ingest/fields/conversation.py

@@ -34,7 +34,7 @@ class PageNotFound(Exception):
     pass
 
 
-class Conversation(Field):
+class Conversation(Field[PBConversation]):
     pbklass = PBConversation
     type: str = "c"
     value: dict[int, PBConversation]

nucliadb/ingest/fields/file.py

@@ -26,7 +26,7 @@ from nucliadb_utils.storages.storage import StorageField
 FILE_METADATA = "file_metadata"
 
 
-class File(Field):
+class File(Field[FieldFile]):
     pbklass = FieldFile
     value: FieldFile
     type: str = "f"
@@ -57,7 +57,7 @@ class File(Field):
 
         await self.db_set_value(payload)
 
-    async def get_value(self) -> FieldFile:
+    async def get_value(self) -> Optional[FieldFile]:
         return await self.db_get_value()
 
     async def set_file_extracted_data(self, file_extracted_data: FileExtractedData):

nucliadb/ingest/fields/link.py

@@ -26,7 +26,7 @@ from nucliadb_utils.storages.storage import StorageField
 LINK_METADATA = "link_metadata"
 
 
-class Link(Field):
+class Link(Field[FieldLink]):
     pbklass = FieldLink
     value: FieldLink
     type: str = "u"
@@ -45,7 +45,7 @@ class Link(Field):
     async def set_value(self, payload: FieldLink):
         await self.db_set_value(payload)
 
-    async def get_value(self) -> FieldLink:
+    async def get_value(self) -> Optional[FieldLink]:
         return await self.db_get_value()
 
     async def set_link_extracted_data(self, link_extracted_data: LinkExtractedData):

nucliadb/ingest/fields/text.py

@@ -19,20 +19,26 @@
 #
 
 import hashlib
+from typing import Optional
 
 from nucliadb.ingest.fields.base import Field
-from nucliadb_protos.resources_pb2 import FieldText
+from nucliadb_protos.resources_pb2 import FieldAuthor, FieldText
 
 
-class Text(Field):
+class Text(Field[FieldText]):
     pbklass = FieldText
     value: FieldText
     type: str = "t"
 
+    async def generated_by(self) -> FieldAuthor:
+        value = await self.get_value()
+        assert value is not None, "Can't know who generated the field if it has no value!"
+        return value.generated_by
+
     async def set_value(self, payload: FieldText):
         if payload.md5 == "":
             payload.md5 = hashlib.md5(payload.body.encode()).hexdigest()
         await self.db_set_value(payload)
 
-    async def get_value(self) -> FieldText:
+    async def get_value(self) -> Optional[FieldText]:
         return await self.db_get_value()

nucliadb/ingest/orm/brain.py

@@ -39,6 +39,7 @@ from nucliadb_protos.noderesources_pb2 import Resource as PBBrainResource
 from nucliadb_protos.resources_pb2 import (
     Basic,
     ExtractedText,
+    FieldAuthor,
     FieldComputedMetadata,
     FieldMetadata,
     Metadata,
@@ -558,6 +559,7 @@ class ResourceBrain:
         field_key: str,
         metadata: Optional[FieldComputedMetadata],
         uuid: str,
+        generated_by: FieldAuthor,
         basic_user_metadata: Optional[UserMetadata] = None,
         basic_user_fieldmetadata: Optional[UserFieldMetadata] = None,
     ):
@@ -573,6 +575,7 @@ class ResourceBrain:
             "l": set(),  # classification labels
             "e": set(),  # entities
             "mt": set(),  # mime type
+            "g/da": set(),  # generated by
         }
         if metadata is not None:
             for meta in metadata.split_metadata.values():
@@ -623,6 +626,20 @@ class ResourceBrain:
                                 paragraph_annotation.key
                             ].labels.append(label)
 
+        if generated_by.WhichOneof("author") == "data_augmentation":
+            field_type, field_id = field_key.split("/")
+            da_task_id = ids.extract_data_augmentation_id(field_id)
+            if da_task_id is None:  # pragma: nocover
+                logger.warning(
+                    "Data augmentation field id has an unexpected format! Skipping label",
+                    extra={
+                        "rid": uuid,
+                        "field_id": field_id,
+                    },
+                )
+            else:
+                labels["g/da"].add(da_task_id)
+
         self.brain.texts[field_key].labels.extend(flatten_resource_labels(labels))
 
 

nucliadb/ingest/orm/processor/processor.py

@@ -300,6 +300,11 @@ class Processor:
                             await send_generated_fields_to_process(
                                 kbid, resource, generated_fields, message
                             )
+                            # TODO: remove this when processor sends the field set
+                            for generated_text in generated_fields.texts:
+                                message.texts[
+                                    generated_text
+                                ].generated_by.data_augmentation.SetInParent()
 
                     else:
                         raise InvalidBrokerMessage(f"Unknown broker message source: {message.source}")

nucliadb/ingest/orm/resource.py

@@ -820,10 +820,13 @@ class Resource:
                 ):
                     valid_user_field_metadata = user_field_metadata
                     break
+
+            generated_by = await fieldobj.generated_by()
             brain.apply_field_labels(
                 fieldkey,
                 extracted_metadata,
                 self.uuid,
+                generated_by,
                 basic.usermetadata,
                 valid_user_field_metadata,
             )

nucliadb/ingest/processing.py

@@ -114,6 +114,10 @@ class PushPayload(BaseModel):
 
 
 async def start_processing_engine():
+    processing_engine = get_utility(Utility.PROCESSING)
+    if processing_engine is not None:
+        return
+
     if nuclia_settings.dummy_processing:
         processing_engine = DummyProcessingEngine()
     else:

nucliadb/search/api/v1/find.py

@@ -82,8 +82,6 @@ async def find_knowledgebox(
     query: str = fastapi_query(SearchParamDefaults.query),
     fields: list[str] = fastapi_query(SearchParamDefaults.fields),
     filters: list[str] = fastapi_query(SearchParamDefaults.filters),
-    page_number: int = fastapi_query(SearchParamDefaults.page_number),
-    page_size: int = fastapi_query(SearchParamDefaults.page_size),
     top_k: Optional[int] = fastapi_query(SearchParamDefaults.top_k),
     min_score: Optional[float] = Query(
         default=None,
@@ -141,9 +139,7 @@ async def find_knowledgebox(
             query=query,
             fields=fields,
             filters=filters,
-            page_number=page_number,
-            page_size=page_size,
-            top_k=top_k,
+            top_k=top_k,  # type: ignore
             min_score=min_score_from_query_params(min_score_bm25, min_score_semantic, min_score),
             vectorset=vectorset,
             range_creation_end=range_creation_end,

nucliadb/search/api/v1/resource/search.py

@@ -17,7 +17,7 @@
 # You should have received a copy of the GNU Affero General Public License
 # along with this program. If not, see <http://www.gnu.org/licenses/>.
 #
-from typing import Optional, Union
+from typing import Optional, Union, cast
 
 from fastapi import Header, Request, Response
 from fastapi_versioning import version
@@ -64,8 +64,6 @@ async def resource_search(
     faceted: list[str] = fastapi_query(SearchParamDefaults.faceted),
     sort: Optional[SortField] = fastapi_query(SearchParamDefaults.sort_field, alias="sort_field"),
     sort_order: SortOrder = fastapi_query(SearchParamDefaults.sort_order),
-    page_number: int = fastapi_query(SearchParamDefaults.page_number),
-    page_size: int = fastapi_query(SearchParamDefaults.page_size),
     top_k: Optional[int] = fastapi_query(SearchParamDefaults.top_k),
     range_creation_start: Optional[DateTime] = fastapi_query(SearchParamDefaults.range_creation_start),
     range_creation_end: Optional[DateTime] = fastapi_query(SearchParamDefaults.range_creation_end),
@@ -80,9 +78,9 @@ async def resource_search(
     debug: bool = fastapi_query(SearchParamDefaults.debug),
     shards: list[str] = fastapi_query(SearchParamDefaults.shards),
 ) -> Union[ResourceSearchResults, HTTPClientError]:
-    if top_k is not None:
-        page_number = 0
-        page_size = top_k
+    top_k = top_k or SearchParamDefaults.top_k  # type: ignore
+    top_k = cast(int, top_k)
+
     with cache.request_caches():
         try:
             pb_query = await paragraph_query_to_pb(
@@ -92,8 +90,8 @@ async def resource_search(
                 fields,
                 filters,
                 faceted,
-                page_number,
-                page_size,
+                0,
+                top_k,
                 range_creation_start,
                 range_creation_end,
                 range_modification_start,
@@ -111,8 +109,8 @@ async def resource_search(
         # We need to merge
         search_results = await merge_paragraphs_results(
             results,
-            count=page_size,
-            page=page_number,
+            count=top_k,
+            page=0,
             kbid=kbid,
             highlight_split=highlight,
             min_score=0.0,

nucliadb/search/api/v1/search.py

@@ -113,8 +113,6 @@ async def search_knowledgebox(
     sort_field: SortField = fastapi_query(SearchParamDefaults.sort_field),
     sort_limit: Optional[int] = fastapi_query(SearchParamDefaults.sort_limit),
     sort_order: SortOrder = fastapi_query(SearchParamDefaults.sort_order),
-    page_number: int = fastapi_query(SearchParamDefaults.page_number, deprecated=True),
-    page_size: int = fastapi_query(SearchParamDefaults.page_size, deprecated=True),
     top_k: int = fastapi_query(SearchParamDefaults.top_k),
     min_score: Optional[float] = Query(
         default=None,
@@ -178,8 +176,6 @@ async def search_knowledgebox(
                 if sort_field is not None
                 else None
             ),
-            page_number=page_number,
-            page_size=page_size,
             top_k=top_k,
             min_score=min_score_from_query_params(min_score_bm25, min_score_semantic, min_score),
             vectorset=vectorset,
@@ -227,8 +223,8 @@ async def catalog_get(
     sort_field: SortField = fastapi_query(SearchParamDefaults.sort_field),
     sort_limit: Optional[int] = fastapi_query(SearchParamDefaults.sort_limit),
     sort_order: SortOrder = fastapi_query(SearchParamDefaults.sort_order),
-    page_number: int = fastapi_query(SearchParamDefaults.page_number),
-    page_size: int = fastapi_query(SearchParamDefaults.page_size),
+    page_number: int = fastapi_query(SearchParamDefaults.catalog_page_number),
+    page_size: int = fastapi_query(SearchParamDefaults.catalog_page_size),
     shards: list[str] = fastapi_query(SearchParamDefaults.shards, deprecated=True),
     with_status: Optional[ResourceProcessingStatus] = fastapi_query(
         SearchParamDefaults.with_status, deprecated="Use filters instead"
@@ -417,9 +413,6 @@ async def search(
     do_audit: bool = True,
     with_status: Optional[ResourceProcessingStatus] = None,
 ) -> tuple[KnowledgeboxSearchResults, bool]:
-    if item.page_number > 0:
-        logger.warning("Someone is still using pagination!", extra={"kbid": kbid, "endpoint": "search"})
-
     audit = get_audit()
     start_time = time()
 
@@ -438,8 +431,8 @@ async def search(
         keyword_filters=[],
         faceted=item.faceted,
         sort=item.sort,
-        page_number=item.page_number,
-        page_size=item.page_size,
+        page_number=0,
+        page_size=item.top_k,
         min_score=item.min_score,
         range_creation_start=item.range_creation_start,
         range_creation_end=item.range_creation_end,
@@ -468,8 +461,8 @@ async def search(
     # We need to merge
     search_results = await merge_results(
         results,
-        count=item.page_size,
-        page=item.page_number,
+        count=item.top_k,
+        page=0,
         kbid=kbid,
         show=item.show,
         field_type_filter=item.field_type_filter,

nucliadb/search/search/chat/ask.py

@@ -883,8 +883,7 @@ def calculate_prequeries_for_json_schema(
             features=features,
             filters=[],
             keyword_filters=[],
-            page_number=0,
-            page_size=10,
+            top_k=10,
             min_score=ask_request.min_score,
             vectorset=ask_request.vectorset,
             highlight=False,

nucliadb/search/search/find.py

@@ -38,14 +38,12 @@ from nucliadb.search.search.metrics import (
     RAGMetrics,
 )
 from nucliadb.search.search.query import QueryParser
-from nucliadb.search.search.query_parser import models as parser_models
 from nucliadb.search.search.query_parser.parser import parse_find
 from nucliadb.search.search.rank_fusion import (
     RankFusionAlgorithm,
     get_rank_fusion,
 )
 from nucliadb.search.search.rerankers import (
-    NoopReranker,
     Reranker,
     RerankingOptions,
     get_reranker,
@@ -77,9 +75,6 @@ async def find(
     generative_model: Optional[str] = None,
     metrics: RAGMetrics = RAGMetrics(),
 ) -> tuple[KnowledgeboxFindResults, bool, QueryParser]:
-    if item.page_number > 0:
-        logger.warning("Someone is still using pagination!", extra={"kbid": kbid, "endpoint": "find"})
-
     external_index_manager = await get_external_index_manager(kbid=kbid)
     if external_index_manager is not None:
         return await _external_index_retrieval(
@@ -127,8 +122,8 @@ async def _index_node_retrieval(
             relation_subgraph_query=pb_query.relations.subgraph,
             min_score_bm25=pb_query.min_score_bm25,
             min_score_semantic=pb_query.min_score_semantic,
-            page_size=item.page_size,
-            page_number=item.page_number,
+            page_size=item.top_k,
+            page_number=0,
             show=item.show,
             extracted=item.extracted,
             field_type_filter=item.field_type_filter,
@@ -232,7 +227,7 @@ async def _external_index_retrieval(
         query=item.query,
         total=0,
         page_number=0,
-        page_size=(item.page_number + 1) * item.page_size,
+        page_size=item.top_k,
         relations=None,  # Not implemented for external indexes yet
         autofilters=[],  # Not implemented for external indexes yet
         min_score=results_min_score,
@@ -268,16 +263,7 @@ async def query_parser_from_find_request(
     parsed = parse_find(item)
 
     rank_fusion = get_rank_fusion(parsed.rank_fusion)
-
-    reranker: Reranker
-    if item.page_number > 0 and isinstance(parsed.reranker, parser_models.Reranker):
-        logger.warning(
-            "Trying to use predict reranker with pagination. Reranker won't be used",
-            extra={"kbid": kbid},
-        )
-        reranker = NoopReranker()
-    else:
-        reranker = get_reranker(parsed.reranker)
+    reranker = get_reranker(parsed.reranker)
 
     query_parser = QueryParser(
         kbid=kbid,
@@ -287,8 +273,8 @@ async def query_parser_from_find_request(
         keyword_filters=item.keyword_filters,
         faceted=None,
         sort=None,
-        page_number=item.page_number,
-        page_size=item.page_size,
+        page_number=0,
+        page_size=item.top_k,
         min_score=item.min_score,
         range_creation_start=item.range_creation_start,
         range_creation_end=item.range_creation_end,

nucliadb/search/search/query_parser/parser.py

@@ -72,7 +72,8 @@ class _FindParser:
         # while pagination is still there, FindRequest has a validator that converts
         # top_k to page_number and page_size. To get top_k, we can compute it from
         # those
-        top_k = (self.item.page_number + 1) * self.item.page_size
+        assert self.item.top_k is not None, "top_k must have an int value"
+        top_k = self.item.top_k
         return top_k
 
     def _parse_rank_fusion(self) -> RankFusion:

{nucliadb-6.1.0.post2589.dist-info → nucliadb-6.1.0.post2602.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nucliadb
-Version: 6.1.0.post2589
+Version: 6.1.0.post2602
 Home-page: https://docs.nuclia.dev/docs/management/nucliadb/intro
 Author: NucliaDB Community
 Author-email: nucliadb@nuclia.com
@@ -22,10 +22,10 @@ Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3 :: Only
 Requires-Python: >=3.9, <4
 Description-Content-Type: text/markdown
-Requires-Dist: nucliadb-telemetry[all]>=6.1.0.post2589
-Requires-Dist: nucliadb-utils[cache,fastapi,storages]>=6.1.0.post2589
-Requires-Dist: nucliadb-protos>=6.1.0.post2589
-Requires-Dist: nucliadb-models>=6.1.0.post2589
+Requires-Dist: nucliadb-telemetry[all]>=6.1.0.post2602
+Requires-Dist: nucliadb-utils[cache,fastapi,storages]>=6.1.0.post2602
+Requires-Dist: nucliadb-protos>=6.1.0.post2602
+Requires-Dist: nucliadb-models>=6.1.0.post2602
 Requires-Dist: nucliadb-admin-assets>=1.0.0.post1224
 Requires-Dist: nucliadb-node-binding>=2.26.0
 Requires-Dist: uvicorn

{nucliadb-6.1.0.post2589.dist-info → nucliadb-6.1.0.post2602.dist-info}/RECORD

@@ -37,7 +37,7 @@ nucliadb/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nucliadb/common/__init__.py,sha256=cp15ZcFnHvpcu_5-aK2A4uUyvuZVV_MJn4bIXMa20ks,835
 nucliadb/common/constants.py,sha256=QpigxJh_CtD85Evy0PtV5cVq6x0U_f9xfIcXz1ymkUg,869
 nucliadb/common/counters.py,sha256=yhJEmmrglTSrDmB8OjaFLkZ__TwhTxayyQrtacnB55I,957
-nucliadb/common/ids.py,sha256=M7yoc8rLBRIPD-zu36OIruRq17ejAfrgeLFUleKWtA8,6810
+nucliadb/common/ids.py,sha256=P92d9aNJCd1VpGgbqnab6g35iQalpUIW_eaaxEin2mE,7439
 nucliadb/common/locking.py,sha256=RL0CabZVPzxHZyUjYeUyLvsJTm7W3J9o4fEgsY_ufNc,5896
 nucliadb/common/nidx.py,sha256=D74oNdniWjbc6gBBDwZP74NH-egTIORHhbfzgIto8DE,8667
 nucliadb/common/cluster/__init__.py,sha256=cp15ZcFnHvpcu_5-aK2A4uUyvuZVV_MJn4bIXMa20ks,835
@@ -108,7 +108,7 @@ nucliadb/ingest/__init__.py,sha256=fsw3C38VP50km3R-nHL775LNGPpJ4JxqXJ2Ib1f5SqE,1
 nucliadb/ingest/app.py,sha256=L8MDbURnSdD6yI4yCnSbmnNccsnha-zJEkKSaGk1xMg,7612
 nucliadb/ingest/cache.py,sha256=w7jMMzamOmQ7gwXna6Dqm6isRNBVv6l5BTBlTxaYWjE,1005
 nucliadb/ingest/partitions.py,sha256=2NIhMYbNT0TNBL6bX1UMSi7vxFGICstCKEqsB0TXHOE,2410
-nucliadb/ingest/processing.py,sha256=lo9NSv11-FznCFW-ZfVbkuVqj2r6mlvfYYBm030PFfM,20144
+nucliadb/ingest/processing.py,sha256=x8FGnq2epsGl0QEzdYlgCys9MpxtV5_WO09hc7Wy150,20254
 nucliadb/ingest/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nucliadb/ingest/serialize.py,sha256=GSDfrO4JLm-QLKw8LJ7TD1JFcXXvwm-ugXzbCfGh3Fk,15492
 nucliadb/ingest/settings.py,sha256=SDQpMRsTsNyi6IDxCJy6BZVUSKUzwAMuxf6ktp31VMM,3130
@@ -123,27 +123,27 @@ nucliadb/ingest/consumer/service.py,sha256=EZM1sABW_7bj6j2UgKUHUuK-EGIEYnLdtPAn8
 nucliadb/ingest/consumer/shard_creator.py,sha256=19wf-Bu_9hb_muCDVblamWuvLr09e5dMu9Id5I4-rGw,4324
 nucliadb/ingest/consumer/utils.py,sha256=jpX8D4lKzuPCpArQLZeX_Zczq3pfen_zAf8sPJfOEZU,2642
 nucliadb/ingest/fields/__init__.py,sha256=cp15ZcFnHvpcu_5-aK2A4uUyvuZVV_MJn4bIXMa20ks,835
-nucliadb/ingest/fields/base.py,sha256=FbXfETEjm2YYzANdUVAaUcSn2_g14AiyyTIb9vs3e6E,18982
-nucliadb/ingest/fields/conversation.py,sha256=PtGlEZXnidjtMFAbX_XiLLSCEbrXef9eJorpj3RvQcQ,7005
+nucliadb/ingest/fields/base.py,sha256=EdWrNWG7-W5ehyPyJrNULLtoApT_AEsKCcfXwzxYMhU,19257
+nucliadb/ingest/fields/conversation.py,sha256=OcQOHvi72Pm0OyNGwxLo9gONo8f1NhwASq0_gS-E64A,7021
 nucliadb/ingest/fields/exceptions.py,sha256=LBZ-lw11f42Pk-ck-NSN9mSJ2kOw-NeRwb-UE31ILTQ,1171
-nucliadb/ingest/fields/file.py,sha256=Hr3Wc1TOW_XH04JFIojTlS9VYqw-1YDZfAK4o9rhlOI,4719
+nucliadb/ingest/fields/file.py,sha256=1v4jLg3balUua2VmSV8hHkAwPFShTUCOzufZvIUQcQw,4740
 nucliadb/ingest/fields/generic.py,sha256=elgtqv15aJUq3zY7X_g0bli_2BpcwPArVvzhe54Y4Ig,1547
-nucliadb/ingest/fields/link.py,sha256=xgOdgQJUOE4CcI9jkl_JReGY0DlqxNjNFxBWX9s1-wE,4151
-nucliadb/ingest/fields/text.py,sha256=q7Rk5Ah6XSPGUN7vKECXfiaBvtFAaNeAbv_a2mboJFY,1318
+nucliadb/ingest/fields/link.py,sha256=kN_gjRUEEj5cy8K_BwPijYg3TiWhedc24apXYlTbRJs,4172
+nucliadb/ingest/fields/text.py,sha256=tFvSQJAe0W7ePpp2_WDfLiE2yglR1OTU0Zht9acvOFw,1594
 nucliadb/ingest/orm/__init__.py,sha256=cp15ZcFnHvpcu_5-aK2A4uUyvuZVV_MJn4bIXMa20ks,835
-nucliadb/ingest/orm/brain.py,sha256=5Y7xLacn6Y_VGtvH1ED3Qt_xoTRSvJsQ2uZUvve1X3k,27891
+nucliadb/ingest/orm/brain.py,sha256=TtHPKZzv_Yz-tYkB1QjzPWUxA7Z_naMVXAfo8iov9Gw,28574
 nucliadb/ingest/orm/broker_message.py,sha256=JYYUJIZEL_EqovQuw6u-FmEkjyoYlxIXJq9hFekOiks,6441
 nucliadb/ingest/orm/entities.py,sha256=xWhp_JXxHjUJ-m3I08tLqkpIrThHH0LJDvIVgK4q7wA,15769
 nucliadb/ingest/orm/exceptions.py,sha256=k4Esv4NtL4TrGTcsQpwrSfDhPQpiYcRbB1SpYmBX5MY,1432
 nucliadb/ingest/orm/knowledgebox.py,sha256=hKKqvZUG4tdPO3Z29_qvz5-dcX5_X2x5pkNQhDGnR7Q,22746
 nucliadb/ingest/orm/metrics.py,sha256=OkwMSPKLZcKba0ZTwtTiIxwBgaLMX5ydhGieKvi2y7E,1096
-nucliadb/ingest/orm/resource.py,sha256=cW_19P2grUOY255pZXvgF13SEyPCy_e8JMogIRqWXxA,53772
+nucliadb/ingest/orm/resource.py,sha256=_m4B14dSpO-lszpoqlhXYL3LrplB9p3NrDZC5kQbXHs,53860
 nucliadb/ingest/orm/utils.py,sha256=vCe_9UxHu26JDFGLwQ0wH-XyzJIpQCTK-Ow9dtZR5Vg,2716
 nucliadb/ingest/orm/processor/__init__.py,sha256=Aqd9wCNTvggkMkCY3WvoI8spdr94Jnqk-0iq9XpLs18,922
 nucliadb/ingest/orm/processor/auditing.py,sha256=TeYhXGJRyQ7ROytbb2u8R0fIh_FYi3HgTu3S1ribY3U,4623
 nucliadb/ingest/orm/processor/data_augmentation.py,sha256=ZF66gfHHMHCh9n9XXoTSdTXhETnzJlcylfQqhFq54Pw,5775
 nucliadb/ingest/orm/processor/pgcatalog.py,sha256=f32PIEXWktWzGDws6Ffife37OAfrseP5IOti_Cb4ir8,3012
-nucliadb/ingest/orm/processor/processor.py,sha256=uXZFLqyCyatoaQt1hpcwZjKU8w1GEwWufEbt3Qj-tpQ,30483
+nucliadb/ingest/orm/processor/processor.py,sha256=Wmh_7KUT2U0oX1pMyzw1jVHNMVGoaBn-6cDYqNoTHtA,30817
 nucliadb/ingest/orm/processor/sequence_manager.py,sha256=uqEphtI1Ir_yk9jRl2gPf7BlzzXWovbARY5MNZSBI_8,1704
 nucliadb/ingest/service/__init__.py,sha256=MME_G_ERxzJR6JW_hfE2qcfXpmpH1kdG-S0a-M0qRm8,2043
 nucliadb/ingest/service/exceptions.py,sha256=cp15ZcFnHvpcu_5-aK2A4uUyvuZVV_MJn4bIXMa20ks,835
@@ -193,17 +193,17 @@ nucliadb/search/api/__init__.py,sha256=cp15ZcFnHvpcu_5-aK2A4uUyvuZVV_MJn4bIXMa20
 nucliadb/search/api/v1/__init__.py,sha256=Xep7u4Q7ygHvTGRn2CzRwJRVX1jtoSxUg8usQcVbC2s,1219
 nucliadb/search/api/v1/ask.py,sha256=Od2U_gaOZK6dJZ1eDGQQJ3xUVnbBih58VPYVAsQErOw,3902
 nucliadb/search/api/v1/feedback.py,sha256=yrOZeElw6XLu6j_6m3QGHKjEMwZPWa9vtdCud4dNilU,2547
-nucliadb/search/api/v1/find.py,sha256=WlpNQCTTegiqgI5STLEUONNCAzETxloZvRoS6Mw_Yjg,9496
+nucliadb/search/api/v1/find.py,sha256=DsnWkySu_cFajDWJIxN8DYvLL_Rm2yiCjHD8TsqPfRk,9304
 nucliadb/search/api/v1/knowledgebox.py,sha256=PKT1V3vZUnBkGfkxnFGjWPuHwQarVxREDY7lAT_9k1w,8764
 nucliadb/search/api/v1/predict_proxy.py,sha256=QrGzo0hKjtmyGZ6pjlJHYAh4hxwVUIOTcVcerRCw7eE,3047
 nucliadb/search/api/v1/router.py,sha256=mtT07rBZcVfpa49doaw9b1tj3sdi3qLH0gn9Io6NYM0,988
-nucliadb/search/api/v1/search.py,sha256=G2vn-OUHTRGGJzCKQ4MLaRq82oXXqEPedvLPq6OitA8,20263
+nucliadb/search/api/v1/search.py,sha256=9QO2-AI1b2WJX8gmURB02cih1ONWjHe0-qnL1SXbF_E,19864
 nucliadb/search/api/v1/suggest.py,sha256=SXxRVKT5hDSHNKlBYo8XozHHq9bGyvJOlo286lEruLE,5979
 nucliadb/search/api/v1/summarize.py,sha256=VAHJvE6V3xUgEBfqNKhgoxmDqCvh30RnrEIBVhMcNLU,2499
 nucliadb/search/api/v1/utils.py,sha256=5Ve-frn7LAE2jqAgB85F8RSeqxDlyA08--gS-AdOLS4,1434
 nucliadb/search/api/v1/resource/__init__.py,sha256=cp15ZcFnHvpcu_5-aK2A4uUyvuZVV_MJn4bIXMa20ks,835
 nucliadb/search/api/v1/resource/ask.py,sha256=XMEP9_Uwy37yaXLcIYKMXGiZYNASD8RTByzQGjd9LPQ,3847
-nucliadb/search/api/v1/resource/search.py,sha256=2AjOcdeeLZHJLLQPdOJfXAIHH0hQKvKcUJ4BfaYLEKk,4994
+nucliadb/search/api/v1/resource/search.py,sha256=jgYJnSSult2ah_Jfd78vbGT5URyZPDsX1Gbdj-sQgCE,4851
 nucliadb/search/requesters/__init__.py,sha256=itSI7dtTwFP55YMX4iK7JzdMHS5CQVUiB1XzQu4UBh8,833
 nucliadb/search/requesters/utils.py,sha256=7ovWSGzhLpZGTMi9x9nMOi7QNCgt2qah-7Kam-cIvUg,8468
 nucliadb/search/search/__init__.py,sha256=cp15ZcFnHvpcu_5-aK2A4uUyvuZVV_MJn4bIXMa20ks,835
@@ -212,7 +212,7 @@ nucliadb/search/search/cut.py,sha256=1lmQpc8p5G8okHcPZ5GKH1F60Qr72HpKGoZI7H15Wzs
 nucliadb/search/search/exceptions.py,sha256=mbToQ-ghrv8ukLEv8S_-EZrgweWaIZZ5SIpoeuGDk6s,1154
 nucliadb/search/search/fetch.py,sha256=XJHIFnZmXM_8Kb37lb4lg1GYG7cZ1plT-qAIb_QziX4,6184
 nucliadb/search/search/filters.py,sha256=1MkHlJjAQqoRCj7e5cEzK2HvBxGLE17I_omsjiklbtw,6476
-nucliadb/search/search/find.py,sha256=ZLonG02Ob_7PxltGmEQp9i6SajtpeXj1pb9ETb-HOgY,10492
+nucliadb/search/search/find.py,sha256=KvRuPwvaZCxgxpHQtetPt9gy5DS9cszLu2oKyiDc3Cg,9891
 nucliadb/search/search/find_merge.py,sha256=oM71fbLamlVmwTuSQm9Z2lRNU63Ak7iHL_6mxwvVwB4,17218
 nucliadb/search/search/hydrator.py,sha256=7Zi44uf2m9b2X_b1aOV2lrWu1Vmbo9lXYgPVUGK0RGI,6728
 nucliadb/search/search/merge.py,sha256=SfAzDKUEAQ2JUf6K6MEhGZZCJXwdsN9vusRIhdg7ajI,20325
@@ -227,7 +227,7 @@ nucliadb/search/search/shards.py,sha256=mM2aCHWhl_gwkCENXDShPukS-_qnB5tFS3UAJuzM
 nucliadb/search/search/summarize.py,sha256=ksmYPubEQvAQgfPdZHfzB_rR19B2ci4IYZ6jLdHxZo8,4996
 nucliadb/search/search/utils.py,sha256=iF2tbBA56gRMJH1TlE2hMrqeXqjoeOPt4KgRdp2m9Ek,3313
 nucliadb/search/search/chat/__init__.py,sha256=cp15ZcFnHvpcu_5-aK2A4uUyvuZVV_MJn4bIXMa20ks,835
-nucliadb/search/search/chat/ask.py,sha256=2ZIz3TbCG18X0eJZSfLc8nHyKToyrlv_SPFzOOcc5wU,33865
+nucliadb/search/search/chat/ask.py,sha256=tUPsJpRCj7Sw7wHTpp5Mq1G9UDrYliCkYiIFdZ7qv_Y,33834
 nucliadb/search/search/chat/exceptions.py,sha256=Siy4GXW2L7oPhIR86H3WHBhE9lkV4A4YaAszuGGUf54,1356
 nucliadb/search/search/chat/images.py,sha256=PA8VWxT5_HUGfW1ULhKTK46UBsVyINtWWqEM1ulzX1E,3095
 nucliadb/search/search/chat/prompt.py,sha256=TIzjI_882hJ--KLKCY8rJomtJ_CMJ-MHYtHqivgG8Lk,46819
@@ -235,7 +235,7 @@ nucliadb/search/search/chat/query.py,sha256=gKtlj2ms81m417Id29-DtHFxE3M4TtJvYNB0
 nucliadb/search/search/query_parser/__init__.py,sha256=cp15ZcFnHvpcu_5-aK2A4uUyvuZVV_MJn4bIXMa20ks,835
 nucliadb/search/search/query_parser/exceptions.py,sha256=tuzl7ZyvVsRz6u0_3zMe60vx39nd3pi641prs-5nC0E,872
 nucliadb/search/search/query_parser/models.py,sha256=BNHwpItSLCZIDclcDpwDiu-BBQfmEn6xkxCErrMPgVU,1590
-nucliadb/search/search/query_parser/parser.py,sha256=ZqyzI8R5b_xV1nRxN6iy6w4t8tatF5zzPhn3-I9a_7M,4849
+nucliadb/search/search/query_parser/parser.py,sha256=DGVtph_ZlRiLQJJdoH07qrUvur6LQpiozwtgbO-SNqs,4890
 nucliadb/standalone/__init__.py,sha256=cp15ZcFnHvpcu_5-aK2A4uUyvuZVV_MJn4bIXMa20ks,835
 nucliadb/standalone/api_router.py,sha256=zR03TQ-Pd2kXx1jeV83Puw19112Z8Jhln7p1cAn69kg,6699
 nucliadb/standalone/app.py,sha256=mAApNK_iVsQgJyd-mtwCeZq5csSimwnXmlQGH9a70pE,5586
@@ -331,9 +331,9 @@ 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-6.1.0.post2589.dist-info/METADATA,sha256=5_p7lJIL-VwcBCwoMdXU6Kfnm5xpIXdbAb6xuACFIQU,4390
-nucliadb-6.1.0.post2589.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
-nucliadb-6.1.0.post2589.dist-info/entry_points.txt,sha256=XqGfgFDuY3zXQc8ewXM2TRVjTModIq851zOsgrmaXx4,1268
-nucliadb-6.1.0.post2589.dist-info/top_level.txt,sha256=hwYhTVnX7jkQ9gJCkVrbqEG1M4lT2F_iPQND1fCzF80,20
-nucliadb-6.1.0.post2589.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-nucliadb-6.1.0.post2589.dist-info/RECORD,,
+nucliadb-6.1.0.post2602.dist-info/METADATA,sha256=33LSAfHphDUPl-cBPDvkh3CzM5h5lYAb3NZafBn9LdY,4390
+nucliadb-6.1.0.post2602.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+nucliadb-6.1.0.post2602.dist-info/entry_points.txt,sha256=XqGfgFDuY3zXQc8ewXM2TRVjTModIq851zOsgrmaXx4,1268
+nucliadb-6.1.0.post2602.dist-info/top_level.txt,sha256=hwYhTVnX7jkQ9gJCkVrbqEG1M4lT2F_iPQND1fCzF80,20
+nucliadb-6.1.0.post2602.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
+nucliadb-6.1.0.post2602.dist-info/RECORD,,