unique_toolkit 1.12.1__tar.gz → 1.14.0__tar.gz

{unique_toolkit-1.12.1 → unique_toolkit-1.14.0}/CHANGELOG.md

@@ -5,6 +5,12 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), 
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.14.0] - 2025-10-07
+- Manipulate Metadata with knowledge base service
+
+## [1.13.0] - 2025-10-07
+- Delete contents with knowledge base service
+
 ## [1.12.1] - 2025-10-07
 - Fix bug where failed evaluations did not show an error to the user.
 

{unique_toolkit-1.12.1 → unique_toolkit-1.14.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: unique_toolkit
-Version: 1.12.1
+Version: 1.14.0
 Summary: 
 License: Proprietary
 Author: Cedric Klinkert
@@ -118,6 +118,12 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), 
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.14.0] - 2025-10-07
+- Manipulate Metadata with knowledge base service
+
+## [1.13.0] - 2025-10-07
+- Delete contents with knowledge base service
+
 ## [1.12.1] - 2025-10-07
 - Fix bug where failed evaluations did not show an error to the user.
 

{unique_toolkit-1.12.1 → unique_toolkit-1.14.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "unique_toolkit"
-version = "1.12.1"
+version = "1.14.0"
 description = ""
 authors = [
     "Cedric Klinkert <cedric.klinkert@unique.ch>",

{unique_toolkit-1.12.1 → unique_toolkit-1.14.0}/unique_toolkit/content/functions.py

@@ -16,6 +16,7 @@ from unique_toolkit.content.schemas import (
     ContentInfo,
     ContentRerankerConfig,
     ContentSearchType,
+    DeleteContentResponse,
     FolderInfo,
     PaginatedContentInfos,
 )
@@ -585,6 +586,7 @@ def download_content(
 def get_content_info(
     user_id: str,
     company_id: str,
+    *,
     metadata_filter: dict[str, Any] | None = None,
     skip: int | None = None,
     take: int | None = None,
@@ -610,7 +612,7 @@ def get_content_info(
     )
 
 
-def get_folder_info(user_id: str, company_id: str, scope_id: str) -> FolderInfo:
+def get_folder_info(user_id: str, company_id: str, *, scope_id: str) -> FolderInfo:
     info = unique_sdk.Folder.get_info(
         user_id=user_id, company_id=company_id, scopeId=scope_id
     )
@@ -648,3 +650,45 @@ def update_content(
         user_id=user_id, company_id=company_id, **update_params
     )
     return ContentInfo.model_validate(content_info, by_alias=True, by_name=True)
+
+
+def delete_content(
+    user_id: str,
+    company_id: str,
+    *,
+    content_id: str | None = None,
+    file_path: str | None = None,
+) -> DeleteContentResponse:
+    if content_id:
+        resp = unique_sdk.Content.delete(
+            user_id=user_id, company_id=company_id, contentId=content_id
+        )
+    elif file_path:
+        resp = unique_sdk.Content.delete(
+            user_id=user_id, company_id=company_id, filePath=file_path
+        )
+    else:
+        raise ValueError("content_id or file_path must be provided")
+
+    return DeleteContentResponse.model_validate(resp, by_alias=True, by_name=True)
+
+
+async def delete_content_async(
+    user_id: str,
+    company_id: str,
+    *,
+    content_id: str | None = None,
+    file_path: str | None = None,
+) -> DeleteContentResponse:
+    if content_id:
+        resp = await unique_sdk.Content.delete_async(
+            user_id=user_id, company_id=company_id, contentId=content_id
+        )
+    elif file_path:
+        resp = await unique_sdk.Content.delete_async(
+            user_id=user_id, company_id=company_id, filePath=file_path
+        )
+    else:
+        raise ValueError("content_id or file_path must be provided")
+
+    return DeleteContentResponse.model_validate(resp, by_alias=True, by_name=True)

{unique_toolkit-1.12.1 → unique_toolkit-1.14.0}/unique_toolkit/content/schemas.py

@@ -185,3 +185,8 @@ class FolderInfo(BaseModel):
     updatedAt: str | None
     parentId: str | None
     externalId: str | None
+
+
+class DeleteContentResponse(BaseModel):
+    model_config = model_config
+    id: str

{unique_toolkit-1.12.1 → unique_toolkit-1.14.0}/unique_toolkit/knowledge_base.py

@@ -1,7 +1,9 @@
+import asyncio
 import logging
 from pathlib import Path
 from typing import Any, overload
 
+import humps
 import unique_sdk
 
 from unique_toolkit._common.validate_required_values import validate_required_values
@@ -11,6 +13,8 @@ from unique_toolkit.content.constants import (
     DEFAULT_SEARCH_LANGUAGE,
 )
 from unique_toolkit.content.functions import (
+    delete_content,
+    delete_content_async,
     download_content_to_bytes,
     download_content_to_file_by_id,
     get_content_info,
@@ -29,6 +33,7 @@ from unique_toolkit.content.schemas import (
     ContentInfo,
     ContentRerankerConfig,
     ContentSearchType,
+    DeleteContentResponse,
     FolderInfo,
     PaginatedContentInfos,
 )
@@ -585,6 +590,261 @@ class KnowledgeBaseService:
 
         return self._resolve_visible_file_tree(content_infos=info.content_infos)
 
+    def _pop_forbidden_metadata_keys(self, metadata: dict[str, Any]) -> dict[str, Any]:
+        forbidden_keys = [
+            "key",
+            "url",
+            "title",
+            "folderId",
+            "mimeType",
+            "companyId",
+            "contentId",
+            "folderIdPath",
+            "externalFileOwner",
+        ]
+        for key in forbidden_keys:
+            metadata.pop(key, None)
+        return metadata
+
+    def update_content_metadata(
+        self,
+        *,
+        content_info: ContentInfo,
+        additional_metadata: dict[str, Any],
+    ) -> ContentInfo:
+        camelized_additional_metadata = humps.camelize(additional_metadata)
+        camelized_additional_metadata = self._pop_forbidden_metadata_keys(
+            camelized_additional_metadata
+        )
+
+        if content_info.metadata is not None:
+            content_info.metadata.update(camelized_additional_metadata)
+        else:
+            content_info.metadata = camelized_additional_metadata
+
+        return update_content(
+            user_id=self._user_id,
+            company_id=self._company_id,
+            content_id=content_info.id,
+            metadata=content_info.metadata,
+        )
+
+    def remove_content_metadata(
+        self,
+        *,
+        content_info: ContentInfo,
+        keys_to_remove: list[str],
+    ) -> ContentInfo:
+        """
+        Removes the specified keys irreversibly from the content metadata.
+        """
+
+        if content_info.metadata is None:
+            _LOGGER.warning(f"Content metadata is None for content {content_info.id}")
+            return content_info
+
+        for key in keys_to_remove:
+            content_info.metadata.pop(key, None)
+
+        return update_content(
+            user_id=self._user_id,
+            company_id=self._company_id,
+            content_id=content_info.id,
+            metadata=content_info.metadata or {},
+        )
+
+    @overload
+    def update_contents_metadata(
+        self,
+        *,
+        additional_metadata: dict[str, Any],
+        content_infos: list[ContentInfo],
+    ) -> list[ContentInfo]: ...
+
+    @overload
+    def update_contents_metadata(
+        self, *, additional_metadata: dict[str, Any], metadata_filter: dict[str, Any]
+    ) -> list[ContentInfo]: ...
+
+    def update_contents_metadata(
+        self,
+        *,
+        additional_metadata: dict[str, Any],
+        metadata_filter: dict[str, Any] | None = None,
+        content_infos: list[ContentInfo] | None = None,
+    ) -> list[ContentInfo]:
+        additional_metadata_camelized = humps.camelize(additional_metadata)
+        additional_metadata_camelized = self._pop_forbidden_metadata_keys(
+            additional_metadata_camelized
+        )
+
+        if content_infos is None:
+            content_infos = self.get_paginated_content_infos(
+                metadata_filter=metadata_filter,
+            ).content_infos
+
+        for info in content_infos:
+            self.update_content_metadata(
+                content_info=info, additional_metadata=additional_metadata_camelized
+            )
+
+        return content_infos
+
+    @overload
+    def remove_contents_metadata(
+        self,
+        *,
+        keys_to_remove: list[str],
+        content_infos: list[ContentInfo],
+    ) -> list[ContentInfo]: ...
+
+    @overload
+    def remove_contents_metadata(
+        self, *, keys_to_remove: list[str], metadata_filter: dict[str, Any]
+    ) -> list[ContentInfo]: ...
+
+    def remove_contents_metadata(
+        self,
+        *,
+        keys_to_remove: list[str],
+        metadata_filter: dict[str, Any] | None = None,
+        content_infos: list[ContentInfo] | None = None,
+    ) -> list[ContentInfo]:
+        if content_infos is None:
+            content_infos = self.get_paginated_content_infos(
+                metadata_filter=metadata_filter,
+            ).content_infos
+
+        for info in content_infos:
+            self.remove_content_metadata(
+                content_info=info, keys_to_remove=keys_to_remove
+            )
+
+        return content_infos
+
+    @overload
+    def delete_content(
+        self,
+        *,
+        content_id: str,
+    ) -> DeleteContentResponse: ...
+
+    """Delete content by id"""
+
+    @overload
+    def delete_content(
+        self,
+        *,
+        file_path: str,
+    ) -> DeleteContentResponse: ...
+
+    """Delete all content matching the file path"""
+
+    def delete_content(
+        self,
+        *,
+        content_id: str | None = None,
+        file_path: str | None = None,
+        metadata_filter: dict[str, Any] | None = None,
+    ) -> DeleteContentResponse:
+        """Delete content by id, file path or metadata filter"""
+        if metadata_filter:
+            infos = self.get_paginated_content_infos(
+                metadata_filter=metadata_filter,
+            )
+            for info in infos.content_infos:
+                delete_content(
+                    user_id=self._user_id,
+                    company_id=self._company_id,
+                    content_id=info.id,
+                )
+
+        return delete_content(
+            user_id=self._user_id,
+            company_id=self._company_id,
+            content_id=content_id,
+            file_path=file_path,
+        )
+
+    def delete_contents(
+        self,
+        *,
+        metadata_filter: dict[str, Any],
+    ) -> list[DeleteContentResponse]:
+        """Delete all content matching the metadata filter"""
+        resp: list[DeleteContentResponse] = []
+
+        if metadata_filter:
+            infos = self.get_paginated_content_infos(
+                metadata_filter=metadata_filter,
+            )
+
+            for info in infos.content_infos:
+                resp.append(
+                    delete_content(
+                        user_id=self._user_id,
+                        company_id=self._company_id,
+                        content_id=info.id,
+                    )
+                )
+
+        return resp
+
+    @overload
+    async def delete_content_async(
+        self,
+        *,
+        content_id: str,
+    ) -> DeleteContentResponse: ...
+
+    @overload
+    async def delete_content_async(
+        self,
+        *,
+        file_path: str,
+    ) -> DeleteContentResponse: ...
+
+    async def delete_content_async(
+        self,
+        *,
+        content_id: str | None = None,
+        file_path: str | None = None,
+    ) -> DeleteContentResponse:
+        return await delete_content_async(
+            user_id=self._user_id,
+            company_id=self._company_id,
+            content_id=content_id,
+            file_path=file_path,
+        )
+
+    async def delete_contents_async(
+        self,
+        *,
+        metadata_filter: dict[str, Any],
+    ) -> list[DeleteContentResponse]:
+        """Delete all content matching the metadata filter"""
+        if not metadata_filter:
+            return []
+
+        infos = self.get_paginated_content_infos(
+            metadata_filter=metadata_filter,
+        )
+
+        # Create all delete tasks without awaiting them
+        delete_tasks = [
+            delete_content_async(
+                user_id=self._user_id,
+                company_id=self._company_id,
+                content_id=info.id,
+            )
+            for info in infos.content_infos
+        ]
+
+        # Await all delete operations concurrently
+        resp = await asyncio.gather(*delete_tasks)
+
+        return list(resp)
+
 
 if __name__ == "__main__":
     kb_service = KnowledgeBaseService.from_settings()