nucliadb-models 6.9.6.post5453__py3-none-any.whl → 6.11.1.post5822__py3-none-any.whl

nucliadb_models/content_types.py

@@ -14,7 +14,6 @@
 
 
 import mimetypes
-from typing import Optional
 
 GENERIC_MIME_TYPE = "application/generic"
 
@@ -26,7 +25,9 @@ NUCLIA_CUSTOM_CONTENT_TYPES = {
 
 EXTRA_VALID_CONTENT_TYPES = {
     "application/font-woff",
+    "application/javascript",
     "application/mp4",
+    "application/rtf",
     "application/toml",
     "application/vnd.jgraph.mxfile",
     "application/vnd.ms-excel.sheet.macroenabled.12",
@@ -38,6 +39,7 @@ EXTRA_VALID_CONTENT_TYPES = {
     "application/x-git",
     "application/x-gzip",
     "application/x-iwork-pages-sffpages",
+    "application/x-javascript",
     "application/x-mach-binary",
     "application/x-mobipocket-ebook",
     "application/x-ms-shortcut",
@@ -46,10 +48,15 @@ EXTRA_VALID_CONTENT_TYPES = {
     "application/x-openscad",
     "application/x-sql",
     "application/x-zip-compressed",
+    "application/x-zip",
     "application/zstd",
+    "audio/m4a",
     "audio/vnd.dlna.adts",
     "audio/wav",
     "audio/x-m4a",
+    "image/svg+xml",
+    "image/tif",
+    "image/x-ico",
     "model/stl",
     "multipart/form-data",
     "text/jsx",
@@ -58,26 +65,21 @@ EXTRA_VALID_CONTENT_TYPES = {
     "text/rtf",
     "text/x-c++",
     "text/x-java-source",
+    "text/x-javascript",
     "text/x-log",
     "text/x-python-script",
     "text/x-ruby-script",
     "text/yaml",
-    "video/x-m4v",
-    "video/YouTube",
-    "image/tif",
+    "video/mkv",
     "video/qt",
     "video/webp",
-    "application/rtf",
-    "application/x-zip",
-    "video/mkv",
-    "image/x-ico",
-    "audio/m4a",
-    "image/svg+xml",
+    "video/x-m4v",
     "video/x-msvideo",
+    "video/YouTube",
 } | NUCLIA_CUSTOM_CONTENT_TYPES
 
 
-def guess(filename: str) -> Optional[str]:
+def guess(filename: str) -> str | None:
     """
     Guess the content type of a file based on its filename.
     Returns None if the content type could not be guessed.

nucliadb_models/conversation.py

@@ -14,7 +14,6 @@
 #
 from datetime import datetime
 from enum import Enum
-from typing import List, Optional
 
 from pydantic import BaseModel, Field, field_validator
 
@@ -37,10 +36,10 @@ class MessageFormat(Enum):
 
 
 class MessageContent(BaseModel):
-    text: Optional[str] = None
-    format: Optional[MessageFormat] = None
-    attachments: Optional[List[CloudLink]] = None
-    attachments_fields: List[FieldRef] = []
+    text: str | None = None
+    format: MessageFormat | None = None
+    attachments: list[CloudLink] | None = None
+    attachments_fields: list[FieldRef] = []
 
 
 class MessageType(Enum):
@@ -50,12 +49,12 @@ class MessageType(Enum):
 
 
 class Message(BaseModel):
-    timestamp: Optional[DateTime] = None
-    who: Optional[str] = None
-    to: Optional[List[str]] = []
+    timestamp: DateTime | None = None
+    who: str | None = None
+    to: list[str] | None = []
     content: MessageContent
-    ident: Optional[str] = None
-    type_: Optional[MessageType] = Field(None, alias="type")
+    ident: str | None = None
+    type_: MessageType | None = Field(None, alias="type")
 
 
 class Conversation(BaseModel):
@@ -64,7 +63,7 @@ class Conversation(BaseModel):
     a conversation in the field level.
     """
 
-    messages: Optional[List[Message]] = []
+    messages: list[Message] | None = []
 
 
 class FieldConversation(BaseModel):
@@ -75,11 +74,11 @@ class FieldConversation(BaseModel):
     This class is used mainly when exposing a conversation in the resource level
     """
 
-    pages: Optional[int] = None
-    size: Optional[int] = None
-    total: Optional[int] = None
-    extract_strategy: Optional[str] = None
-    split_strategy: Optional[str] = None
+    pages: int | None = None
+    size: int | None = None
+    total: int | None = None
+    extract_strategy: str | None = None
+    split_strategy: str | None = None
 
 
 # Creation and update classes (Those used on writer endpoints)
@@ -88,18 +87,18 @@ class FieldConversation(BaseModel):
 class InputMessageContent(BaseModel):
     text: str = Field()
     format: MessageFormat = MessageFormat.PLAIN
-    attachments: List[FileB64] = Field(default=[], max_length=50)
-    attachments_fields: List[FieldRef] = Field(default=[], max_length=50)
+    attachments: list[FileB64] = Field(default=[], max_length=50)
+    attachments_fields: list[FieldRef] = Field(default=[], max_length=50)
 
 
 class InputMessage(BaseModel):
-    timestamp: Optional[datetime] = Field(
+    timestamp: datetime | None = Field(
         default=None, description="Time at which the message was sent, in ISO 8601 format."
     )
-    who: Optional[str] = Field(
+    who: str | None = Field(
         default=None, description="Sender of the message, e.g. 'user' or 'assistant'"
     )
-    to: List[str] = Field(
+    to: list[str] = Field(
         default_factory=list,
         description="List of recipients of the message, e.g. ['assistant'] or ['user']",
         max_length=100,
@@ -109,7 +108,7 @@ class InputMessage(BaseModel):
         description="Unique identifier for the message. Must be unique within the conversation.",
         max_length=128,
     )
-    type_: Optional[MessageType] = Field(None, alias="type")
+    type_: MessageType | None = Field(None, alias="type")
 
     @field_validator("ident", mode="after")
     @classmethod
@@ -126,22 +125,22 @@ class InputMessage(BaseModel):
 
 
 class InputConversationField(BaseModel):
-    messages: List[InputMessage] = Field(
+    messages: list[InputMessage] = Field(
         default_factory=list,
         description="List of messages in the conversation field. Each message must have a unique ident. A single conversation can contain up to 51,200 messages. You can add up to 2,048 messages per request.",
     )
-    extract_strategy: Optional[str] = Field(
+    extract_strategy: str | None = Field(
         default=None,
         description="Id of the Nuclia extract strategy used at processing time. If not set, the default strategy was used. Extract strategies are defined at the learning configuration api.",
     )
-    split_strategy: Optional[str] = Field(
+    split_strategy: str | None = Field(
         default=None,
         description="Id of the Nuclia split strategy used at processing time. If not set, the default strategy was used. Split strategies are defined at the learning configuration api.",
     )
 
     @field_validator("messages", mode="after")
     @classmethod
-    def idents_are_unique(cls, value: List[InputMessage]) -> List[InputMessage]:
+    def idents_are_unique(cls, value: list[InputMessage]) -> list[InputMessage]:
         seen_idents = set()
         for message in value:
             if message.ident in seen_idents:

nucliadb_models/entities.py

@@ -13,7 +13,6 @@
 # limitations under the License.
 #
 
-from typing import Dict, List, Optional
 
 from pydantic import BaseModel, Field
 
@@ -21,50 +20,50 @@ from pydantic import BaseModel, Field
 class Entity(BaseModel):
     value: str
     merged: bool = False
-    represents: List[str] = []
+    represents: list[str] = []
 
 
 class EntitiesGroupSummary(BaseModel):
-    title: Optional[str] = Field(default=None, description="Title of the entities group")
-    color: Optional[str] = Field(
+    title: str | None = Field(default=None, description="Title of the entities group")
+    color: str | None = Field(
         default=None,
         description="Color of the entities group. This is for display purposes only.",
     )
     custom: bool = Field(default=False, description="Denotes if it has been created by the user")
 
-    entities: Dict[str, Entity] = Field(
+    entities: dict[str, Entity] = Field(
         default={},
         title="[Deprecated] Entities in the group",
-        description="This field is deprecated and will be removed in future versions. It will always be empty. Use the /api/v1/kb/{kbid}/entitiesgroup/{group} endpoint to get the entities of a group.",  # noqa: E501
+        description="This field is deprecated and will be removed in future versions. It will always be empty. Use the /api/v1/kb/{kbid}/entitiesgroup/{group} endpoint to get the entities of a group.",
     )
 
 
 class EntitiesGroup(BaseModel):
-    title: Optional[str] = Field(default=None, description="Title of the entities group")
-    color: Optional[str] = Field(
+    title: str | None = Field(default=None, description="Title of the entities group")
+    color: str | None = Field(
         default=None,
         description="Color of the entities group. This is for display purposes only.",
     )
     custom: bool = Field(default=False, description="Denotes if it has been created by the user")
-    entities: Dict[str, Entity] = {}
+    entities: dict[str, Entity] = {}
 
 
 class KnowledgeBoxEntities(BaseModel):
     uuid: str
-    groups: Dict[str, EntitiesGroupSummary] = {}
+    groups: dict[str, EntitiesGroupSummary] = {}
 
 
 class CreateEntitiesGroupPayload(BaseModel):
     group: str
-    entities: Dict[str, Entity] = {}
-    title: Optional[str] = None
-    color: Optional[str] = None
+    entities: dict[str, Entity] = {}
+    title: str | None = None
+    color: str | None = None
 
 
 class UpdateEntitiesGroupPayload(BaseModel):
-    title: Optional[str] = None
-    color: Optional[str] = None
+    title: str | None = None
+    color: str | None = None
 
-    add: Dict[str, Entity] = {}
-    update: Dict[str, Entity] = {}
-    delete: List[str] = []
+    add: dict[str, Entity] = {}
+    update: dict[str, Entity] = {}
+    delete: list[str] = []

nucliadb_models/external_index_providers.py

@@ -14,7 +14,6 @@
 #
 
 from enum import Enum
-from typing import Union
 
 from pydantic import BaseModel
 
@@ -36,4 +35,4 @@ class DummyIndexProvider(ExternalIndexProviderBase):
     type: ExternalIndexProviderType = ExternalIndexProviderType.UNSET
 
 
-ExternalIndexProvider = Union[DummyIndexProvider,]
+ExternalIndexProvider = DummyIndexProvider

nucliadb_models/extracted.py

@@ -13,9 +13,8 @@
 # limitations under the License.
 #
 from datetime import datetime
-from typing import Dict, List, Optional
 
-from pydantic import BaseModel
+from pydantic import BaseModel, Field
 
 from .common import (
     Classification,
@@ -27,27 +26,27 @@ from .metadata import Relation
 
 
 class ExtractedText(BaseModel):
-    text: Optional[str] = None
-    split_text: Optional[Dict[str, str]] = None
-    deleted_splits: Optional[List[str]] = None
+    text: str | None = None
+    split_text: dict[str, str] | None = None
+    deleted_splits: list[str] | None = None
 
 
 class Vector(BaseModel):
-    start: Optional[int] = None
-    end: Optional[int] = None
-    start_paragraph: Optional[int] = None
-    end_paragraph: Optional[int] = None
-    vector: Optional[List[float]] = None
+    start: int | None = None
+    end: int | None = None
+    start_paragraph: int | None = None
+    end_paragraph: int | None = None
+    vector: list[float] | None = None
 
 
 class Vectors(BaseModel):
-    vectors: Optional[List[Vector]] = None
+    vectors: list[Vector] | None = None
 
 
 class VectorObject(BaseModel):
-    vectors: Optional[Vectors] = None
-    split_vectors: Optional[Dict[str, Vectors]] = None
-    deleted_splits: Optional[List[str]] = None
+    vectors: Vectors | None = None
+    split_vectors: dict[str, Vectors] | None = None
+    deleted_splits: list[str] | None = None
 
 
 class Position(BaseModel):
@@ -56,14 +55,14 @@ class Position(BaseModel):
 
 
 class Positions(BaseModel):
-    position: List[Position]
+    position: list[Position]
     entity: str
 
 
 class FieldEntity(BaseModel):
     text: str
     label: str
-    positions: List[Position]
+    positions: list[Position]
 
 
 class FieldEntities(BaseModel):
@@ -71,91 +70,91 @@ class FieldEntities(BaseModel):
     Wrapper for the entities extracted from a field (required because protobuf doesn't support lists of lists)
     """
 
-    entities: List[FieldEntity]
+    entities: list[FieldEntity]
 
 
 class FieldMetadata(BaseModel):
-    links: List[str]
-    paragraphs: List[Paragraph]
-    ner: Dict[str, str]  # TODO: Remove once processor doesn't use this anymore
-    entities: Dict[str, FieldEntities]
-    classifications: List[Classification]
-    last_index: Optional[datetime] = None
-    last_understanding: Optional[datetime] = None
-    last_extract: Optional[datetime] = None
-    last_summary: Optional[datetime] = None
-    last_processing_start: Optional[datetime] = None
-    thumbnail: Optional[CloudLink] = None
-    language: Optional[str] = None
-    summary: Optional[str] = None
-    positions: Dict[str, Positions]  # TODO: Remove once processor doesn't use this anymore
-    relations: Optional[List[Relation]] = None
-    mime_type: Optional[str] = None
+    links: list[str]
+    paragraphs: list[Paragraph]
+    ner: dict[str, str]  # TODO: Remove once processor doesn't use this anymore
+    entities: dict[str, FieldEntities]
+    classifications: list[Classification]
+    last_index: datetime | None = None
+    last_understanding: datetime | None = None
+    last_extract: datetime | None = None
+    last_summary: datetime | None = None
+    last_processing_start: datetime | None = None
+    thumbnail: CloudLink | None = None
+    language: str | None = None
+    summary: str | None = None
+    positions: dict[str, Positions]  # TODO: Remove once processor doesn't use this anymore
+    relations: list[Relation] | None = None
+    mime_type: str | None = None
 
 
 class FieldComputedMetadata(BaseModel):
     metadata: FieldMetadata
-    split_metadata: Optional[Dict[str, FieldMetadata]] = None
-    deleted_splits: Optional[List[str]] = None
+    split_metadata: dict[str, FieldMetadata] | None = None
+    deleted_splits: list[str] | None = None
 
 
 class Entity(BaseModel):
-    token: Optional[str] = None
-    root: Optional[str] = None
-    type: Optional[str] = None
+    token: str | None = None
+    root: str | None = None
+    type: str | None = None
 
 
 class FieldLargeMetadata(BaseModel):
-    entities: Optional[List[Entity]] = None
-    tokens: Optional[Dict[str, int]] = None
+    entities: list[Entity] | None = None
+    tokens: dict[str, int] | None = None
 
 
 class LargeComputedMetadata(BaseModel):
-    metadata: Optional[FieldLargeMetadata] = None
-    split_metadata: Optional[Dict[str, FieldLargeMetadata]] = None
-    deleted_splits: Optional[List[str]] = None
+    metadata: FieldLargeMetadata | None = None
+    split_metadata: dict[str, FieldLargeMetadata] | None = None
+    deleted_splits: list[str] | None = None
 
 
 class LinkExtractedData(BaseModel):
-    date: Optional[datetime] = None
-    language: Optional[str] = None
-    title: Optional[str] = None
-    metadata: Optional[Dict[str, str]] = None
-    link_thumbnail: Optional[CloudLink] = None
-    link_preview: Optional[CloudLink] = None
-    field: Optional[str] = None
-    link_image: Optional[CloudLink] = None
-    description: Optional[str] = None
-    type: Optional[str] = None
-    embed: Optional[str] = None
-    file_generated: Optional[Dict[str, CloudLink]] = None
+    date: datetime | None = None
+    language: str | None = None
+    title: str | None = None
+    metadata: dict[str, str] | None = None
+    link_thumbnail: CloudLink | None = None
+    link_preview: CloudLink | None = None
+    field: str | None = Field(default=None, title="Link Extracted Data Field")
+    link_image: CloudLink | None = None
+    description: str | None = None
+    type: str | None = None
+    embed: str | None = None
+    file_generated: dict[str, CloudLink] | None = None
 
 
 class NestedPosition(BaseModel):
-    start: Optional[int] = None
-    end: Optional[int] = None
-    page: Optional[int] = None
+    start: int | None = None
+    end: int | None = None
+    page: int | None = Field(default=None, title="Position Page")
 
 
 class NestedListPosition(BaseModel):
-    positions: List[NestedPosition]
+    positions: list[NestedPosition]
 
 
 class Row(BaseModel):
-    cell: Optional[List[str]] = None
+    cell: list[str] | None = None
 
 
 class Sheet(BaseModel):
-    rows: Optional[List[Row]] = None
+    rows: list[Row] | None = None
 
 
 class RowsPreview(BaseModel):
-    sheets: Optional[Dict[str, Sheet]] = None
+    sheets: dict[str, Sheet] | None = None
 
 
 class PagePositions(BaseModel):
-    start: Optional[int] = None
-    end: Optional[int] = None
+    start: int | None = None
+    end: int | None = None
 
 
 class PageStructurePage(BaseModel):
@@ -174,32 +173,32 @@ class PageStructureToken(BaseModel):
 
 class PageStructure(BaseModel):
     page: PageStructurePage
-    tokens: List[PageStructureToken]
+    tokens: list[PageStructureToken]
 
 
 class FilePages(BaseModel):
-    pages: Optional[List[CloudLink]] = None
-    positions: Optional[List[PagePositions]] = None
-    structures: Optional[List[PageStructure]] = None
+    pages: list[CloudLink] | None = None
+    positions: list[PagePositions] | None = None
+    structures: list[PageStructure] | None = None
 
 
 class FileExtractedData(BaseModel):
-    language: Optional[str] = None
-    md5: Optional[str] = None
-    metadata: Optional[Dict[str, str]] = None
-    nested: Optional[Dict[str, str]] = None
-    file_generated: Optional[Dict[str, CloudLink]] = None
-    file_rows_previews: Optional[Dict[str, RowsPreview]] = None
-    file_preview: Optional[CloudLink] = None
-    file_pages_previews: Optional[FilePages] = None
-    file_thumbnail: Optional[CloudLink] = None
-    field: Optional[str] = None
-    icon: Optional[str] = None
-    nested_position: Optional[Dict[str, NestedPosition]] = None
-    nested_list_position: Optional[Dict[str, NestedListPosition]] = None
+    language: str | None = None
+    md5: str | None = None
+    metadata: dict[str, str] | None = None
+    nested: dict[str, str] | None = None
+    file_generated: dict[str, CloudLink] | None = None
+    file_rows_previews: dict[str, RowsPreview] | None = None
+    file_preview: CloudLink | None = None
+    file_pages_previews: FilePages | None = None
+    file_thumbnail: CloudLink | None = None
+    field: str | None = None
+    icon: str | None = None
+    nested_position: dict[str, NestedPosition] | None = None
+    nested_list_position: dict[str, NestedListPosition] | None = None
 
 
 class FieldQuestionAnswers(BaseModel):
     question_answers: QuestionAnswers
-    split_question_answers: Optional[Dict[str, QuestionAnswers]] = None
-    deleted_splits: Optional[List[str]] = None
+    split_question_answers: dict[str, QuestionAnswers] | None = None
+    deleted_splits: list[str] | None = None

nucliadb_models/file.py

@@ -13,7 +13,6 @@
 # limitations under the License.
 #
 from datetime import datetime
-from typing import Optional
 
 from pydantic import BaseModel, Field
 
@@ -26,16 +25,16 @@ from nucliadb_models.common import CloudLink, File
 
 
 class FieldFile(BaseModel):
-    added: Optional[datetime] = None
-    file: Optional[CloudLink] = None
-    language: Optional[str] = None
-    password: Optional[str] = None
+    added: datetime | None = None
+    file: CloudLink | None = None
+    language: str | None = None
+    password: str | None = None
     external: bool = False
-    extract_strategy: Optional[str] = Field(
+    extract_strategy: str | None = Field(
         default=None,
         description="Id of the Nuclia extract strategy used at processing time. If not set, the default strategy was used. Extract strategies are defined at the learning configuration api.",
     )
-    split_strategy: Optional[str] = Field(
+    split_strategy: str | None = Field(
         default=None,
         description="Id of the Nuclia split strategy used at processing time. If not set, the default strategy was used. Split strategies are defined at the learning configuration api.",
     )
@@ -45,14 +44,14 @@ class FieldFile(BaseModel):
 
 
 class FileField(BaseModel):
-    language: Optional[str] = None
-    password: Optional[str] = None
+    language: str | None = None
+    password: str | None = None
     file: File
-    extract_strategy: Optional[str] = Field(
+    extract_strategy: str | None = Field(
         default=None,
         description="Id of the Nuclia extract strategy to use at processing time. If not set, the default strategy will be used. Extract strategies are defined at the learning configuration api.",
     )
-    split_strategy: Optional[str] = Field(
+    split_strategy: str | None = Field(
         default=None,
         description="Id of the Nuclia split strategy used at processing time. If not set, the default strategy was used. Split strategies are defined at the learning configuration api.",
     )