unique_toolkit 1.80.0__tar.gz → 1.80.1__tar.gz

{unique_toolkit-1.80.0 → unique_toolkit-1.80.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: unique-toolkit
-Version: 1.80.0
+Version: 1.80.1
 Summary: 
 Author: Cedric Klinkert, Martin Fadler, Sadique Sheik, Fabian Schläpfer, Pascal Hauri, Ejiroghene Oki-Peter, Rami Azouz, Ricardo Visini, Sanzio Monti
 Author-email: Cedric Klinkert <cedric.klinkert@unique.ch>, Martin Fadler <martin.fadler@unique.ch>, Sadique Sheik <sadique@unique.ch>, Fabian Schläpfer <fabian@unique.ch>, Pascal Hauri <pascal@unique.ch>, Ejiroghene Oki-Peter <oki-peter.ejiroghene@unique.ai>, Rami Azouz <rami.ext@unique.ch>, Ricardo Visini <ricardo.visini@unique.ch>, Sanzio Monti <sanzio.monti@unique.ai>
@@ -16,7 +16,7 @@ Requires-Dist: sseclient>=0.0.27,<0.0.28
 Requires-Dist: openai>=1.105.0,<3
 Requires-Dist: platformdirs>=4.0.0,<5
 Requires-Dist: pillow>=12.1.1
-Requires-Dist: unique-sdk>=0.10.85,<0.12
+Requires-Dist: unique-sdk>=0.11.6,<0.12
 Requires-Dist: jambo>=0.1.2,<0.2
 Requires-Dist: jinja2>=3.1.6,<4
 Requires-Dist: docxtpl>=0.20.1,<0.21

{unique_toolkit-1.80.0 → unique_toolkit-1.80.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "unique_toolkit"
-version = "1.80.0"
+version = "1.80.1"
 description = ""
 readme = "README.md"
 requires-python = ">=3.12"
@@ -28,7 +28,7 @@ dependencies = [
     "openai>=1.105.0,<3",
     "platformdirs>=4.0.0,<5",
     "pillow>=12.1.1",
-    "unique-sdk>=0.10.85,<0.12",
+    "unique-sdk>=0.11.6,<0.12",
     "jambo>=0.1.2,<0.2",
     "jinja2>=3.1.6,<4",
     "docxtpl>=0.20.1,<0.21",

{unique_toolkit-1.80.0 → unique_toolkit-1.80.1}/unique_toolkit/_common/utils/files.py

@@ -28,35 +28,67 @@ class FileMimeType(StrEnum):
         mime_type, _ = mimetypes.guess_type(filepath)
         if mime_type is None:
             return None
+
+        return cls.from_mime_string(mime_type)
+
+    @classmethod
+    def from_mime_string(cls, mime: str) -> "FileMimeType | None":
         try:
-            return cls(mime_type)
+            return cls(mime)
         except ValueError:
             return None
 
+    @property
+    def is_docx(self) -> bool:
+        cls = self.__class__
+        return self in {cls.DOCX, cls.DOC}
+
+    @property
+    def is_pdf(self) -> bool:
+        return self == self.__class__.PDF
+
+    @property
+    def is_xlsx(self) -> bool:
+        cls = self.__class__
+        return self in {cls.XLSX, cls.XLS, cls.MSEXCEL, cls.EXCEL}
+
+    @property
+    def is_pptx(self) -> bool:
+        cls = self.__class__
+        return self in {cls.PPTX, cls.PPT, cls.MSPPT}
+
+    @property
+    def is_json(self) -> bool:
+        return self == self.__class__.JSON
+
+    @property
+    def is_csv(self) -> bool:
+        return self == self.__class__.CSV
+
     @classmethod
     def is_docx_mime(cls, filepath: Path) -> bool:
         mime_type = cls.get_mime_from_file_path(filepath)
-        return mime_type in {cls.DOCX, cls.DOC}
+        return mime_type is not None and mime_type.is_docx
 
     @classmethod
     def is_pdf_mime(cls, filepath: Path) -> bool:
         mime_type = cls.get_mime_from_file_path(filepath)
-        return mime_type == cls.PDF
+        return mime_type is not None and mime_type.is_pdf
 
     @classmethod
     def is_xlsx_mime(cls, filepath: Path) -> bool:
         mime_type = cls.get_mime_from_file_path(filepath)
-        return mime_type in {cls.XLSX, cls.XLS, cls.MSEXCEL, cls.EXCEL}
+        return mime_type is not None and mime_type.is_xlsx
 
     @classmethod
     def is_pptx_mime(cls, filepath: Path) -> bool:
         mime_type = cls.get_mime_from_file_path(filepath)
-        return mime_type in {cls.PPTX, cls.PPT, cls.MSPPT}
+        return mime_type is not None and mime_type.is_pptx
 
     @classmethod
     def is_json_mime(cls, filepath: Path) -> bool:
         mime_type = cls.get_mime_from_file_path(filepath)
-        return mime_type == cls.JSON
+        return mime_type is not None and mime_type.is_json
 
     @classmethod
     def is_valid_mime(cls, filepath: Path, valid_mimes: list[FileMimeType]) -> bool:

{unique_toolkit-1.80.0 → unique_toolkit-1.80.1}/unique_toolkit/content/schemas.py

@@ -10,6 +10,7 @@ from humps import camelize
 from pydantic import BaseModel, ConfigDict, Field
 
 from unique_toolkit._common.config_checker import register_config
+from unique_toolkit._common.utils.files import FileMimeType
 
 # set config to convert camelCase to snake_case
 model_config = ConfigDict(
@@ -142,6 +143,7 @@ class Content(BaseModel):
         description="The title of the content. For documents this is the title of the document.",
     )
     url: str | None = None
+    mime_type: str | None = None
     chunks: list[ContentChunk] = []
     write_url: str | None = None
     read_url: str | None = None
@@ -160,10 +162,22 @@ class Content(BaseModel):
         ):
             return default_if_unknown
 
-        return self.applied_ingestion_config["uniqueIngestionMode"] not in (
-            "SKIP_INGESTION",
-            "SKIP_EXCEL_INGESTION",
-        )
+        if self.applied_ingestion_config["uniqueIngestionMode"] == "SKIP_INGESTION":
+            return False
+
+        elif (
+            self.applied_ingestion_config["uniqueIngestionMode"]
+            == "SKIP_EXCEL_INGESTION"
+        ):
+            if (
+                self.mime_type is None
+                or (mime_type := FileMimeType.from_mime_string(self.mime_type)) is None
+            ):
+                return default_if_unknown
+
+            return not (mime_type.is_xlsx or mime_type.is_csv)
+
+        return True
 
 
 class ContentReference(BaseModel):

{unique_toolkit-1.80.0 → unique_toolkit-1.80.1}/unique_toolkit/content/utils.py

@@ -261,6 +261,7 @@ def map_content(content: dict[str, Any]):
         applied_ingestion_config=content.get("appliedIngestionConfig"),
         expired_at=content.get("expiredAt"),
         metadata=content.get("metadata"),
+        mime_type=content.get("mimeType"),
     )