usecortex-ai 0.3.6__py3-none-any.whl → 0.4.0__py3-none-any.whl

usecortex_ai/upload/client.py

@@ -5,14 +5,14 @@ import typing
 from .. import core
 from ..core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
 from ..core.request_options import RequestOptions
+from ..types.add_memory_response import AddMemoryResponse
 from ..types.app_sources_upload_data import AppSourcesUploadData
-from ..types.batch_upload_data import BatchUploadData
-from ..types.markdown_upload_request import MarkdownUploadRequest
+from ..types.delete_user_memory_response import DeleteUserMemoryResponse
+from ..types.memory_item import MemoryItem
 from ..types.processing_status import ProcessingStatus
-from ..types.single_upload_data import SingleUploadData
-from ..types.source_model import SourceModel
-from ..types.webpage_scrape_request import WebpageScrapeRequest
+from ..types.source_upload_response import SourceUploadResponse
 from .raw_client import AsyncRawUploadClient, RawUploadClient
+from .types.body_upload_app_ingestion_upload_app_post_app_sources import BodyUploadAppIngestionUploadAppPostAppSources
 
 # this is used as the default value for optional parameters
 OMIT = typing.cast(typing.Any, ...)
@@ -33,1784 +33,136 @@ class UploadClient:
         """
         return self._raw_client
 
-    def batch_upload(
-        self,
-        *,
-        tenant_id: str,
-        files: typing.List[core.File],
-        sub_tenant_id: typing.Optional[str] = None,
-        file_ids: typing.Optional[str] = OMIT,
-        tenant_metadata: typing.Optional[str] = OMIT,
-        document_metadata: typing.Optional[str] = OMIT,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> BatchUploadData:
-        """
-        Upload multiple documents simultaneously for efficient bulk processing.
-
-        This endpoint allows you to upload several files at once, which is ideal for large document collections or periodic data imports. Each file gets processed asynchronously, and you can track the progress of individual files using their returned file IDs.
-
-        The system automatically handles file parsing, content extraction, and indexing across all uploaded documents. You'll receive confirmation once all files are queued for processing.
-
-        Parameters
-        ----------
-        tenant_id : str
-            Unique identifier for the tenant/organization
-
-        files : typing.List[core.File]
-            See core.File for more documentation
-
-        sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
-
-        file_ids : typing.Optional[str]
-            Optional JSON string array of file IDs for the uploaded content. If not provided or empty, will be generated automatically.
-
-        tenant_metadata : typing.Optional[str]
-            JSON string containing tenant-level document metadata (e.g., department, compliance_tag)
-
-            Example: > "{"department":"Finance","compliance_tag":"GDPR"}"
-
-
-        document_metadata : typing.Optional[str]
-            JSON string containing document-specific metadata (e.g., title, author, file_id). If file_id is not provided, the system will generate an ID automatically.
-
-            Example: > "{"title":"Q1 Report.pdf","author":"Alice Smith","file_id":"custom_file_123"}"
-
-
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        BatchUploadData
-            Successful Response
-
-        Examples
-        --------
-        from usecortex-ai import CortexAI
-
-        client = CortexAI(token="YOUR_TOKEN", )
-        client.upload.batch_upload(tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', )
-        """
-        _response = self._raw_client.batch_upload(
-            tenant_id=tenant_id,
-            files=files,
-            sub_tenant_id=sub_tenant_id,
-            file_ids=file_ids,
-            tenant_metadata=tenant_metadata,
-            document_metadata=document_metadata,
-            request_options=request_options,
-        )
-        return _response.data
-
-    def batch_update(
-        self,
-        *,
-        tenant_id: str,
-        files: typing.List[core.File],
-        sub_tenant_id: typing.Optional[str] = None,
-        source_ids: typing.Optional[typing.List[str]] = OMIT,
-        tenant_metadata: typing.Optional[str] = OMIT,
-        document_metadata: typing.Optional[str] = OMIT,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> BatchUploadData:
-        """
-        Update multiple existing documents with new content and metadata.
-
-        Use this endpoint when you need to replace or modify several documents that are already in your knowledge base. Each file must correspond to an existing source ID, ensuring that updates are applied to the correct documents.
-
-        The system processes updates asynchronously, allowing you to continue working while your documents are re-indexed. Track the progress using the returned file IDs to know when updates are complete.
-
-        Parameters
-        ----------
-        tenant_id : str
-            Unique identifier for the tenant/organization
-
-        files : typing.List[core.File]
-            See core.File for more documentation
-
-        sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
-
-        source_ids : typing.Optional[typing.List[str]]
-            List of source IDs corresponding to the files being updated
-
-        tenant_metadata : typing.Optional[str]
-            JSON string containing tenant-level document metadata (e.g., department, compliance_tag)
-
-            Example: > "{"department":"Finance","compliance_tag":"GDPR"}"
-
-
-        document_metadata : typing.Optional[str]
-            JSON string containing document-specific metadata (e.g., title, author, file_id). If file_id is not provided, the system will generate an ID automatically.
-
-            Example: > "{"title":"Q1 Report.pdf","author":"Alice Smith","file_id":"custom_file_123"}"
-
-
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        BatchUploadData
-            Successful Response
-
-        Examples
-        --------
-        from usecortex-ai import CortexAI
-
-        client = CortexAI(token="YOUR_TOKEN", )
-        client.upload.batch_update(tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', )
-        """
-        _response = self._raw_client.batch_update(
-            tenant_id=tenant_id,
-            files=files,
-            sub_tenant_id=sub_tenant_id,
-            source_ids=source_ids,
-            tenant_metadata=tenant_metadata,
-            document_metadata=document_metadata,
-            request_options=request_options,
-        )
-        return _response.data
-
-    def upload_document(
-        self,
-        *,
-        tenant_id: str,
-        file: core.File,
-        sub_tenant_id: typing.Optional[str] = None,
-        file_id: typing.Optional[str] = OMIT,
-        tenant_metadata: typing.Optional[str] = OMIT,
-        document_metadata: typing.Optional[str] = OMIT,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> SingleUploadData:
-        """
-        Upload a single document for processing and indexing into your knowledge base.
-
-        This endpoint accepts documents in various formats and processes them for search and retrieval. You can include custom metadata to help organize and categorize your content.
-
-        The system extracts text content, processes it asynchronously, and makes it available for search queries. You can track the processing status using the returned file ID.
-
-        Parameters
-        ----------
-        tenant_id : str
-            Unique identifier for the tenant/organization
-
-        file : core.File
-            See core.File for more documentation
-
-        sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
-
-        file_id : typing.Optional[str]
-            Optional file ID for the uploaded content. If not provided, will be generated automatically.
-
-        tenant_metadata : typing.Optional[str]
-            JSON string containing tenant-level document metadata (e.g., department, compliance_tag)
-
-            Example: > "{"department":"Finance","compliance_tag":"GDPR"}"
-
-
-        document_metadata : typing.Optional[str]
-            JSON string containing document-specific metadata (e.g., title, author, file_id). If file_id is not provided, the system will generate an ID automatically.
-
-            Example: > "{"title":"Q1 Report.pdf","author":"Alice Smith","file_id":"custom_file_123"}"
-
-
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        SingleUploadData
-            Successful Response
-
-        Examples
-        --------
-        from usecortex-ai import CortexAI
-
-        client = CortexAI(token="YOUR_TOKEN", )
-        client.upload.upload_document(tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', )
-        """
-        _response = self._raw_client.upload_document(
-            tenant_id=tenant_id,
-            file=file,
-            sub_tenant_id=sub_tenant_id,
-            file_id=file_id,
-            tenant_metadata=tenant_metadata,
-            document_metadata=document_metadata,
-            request_options=request_options,
-        )
-        return _response.data
-
-    def update_document(
-        self,
-        *,
-        source_id: str,
-        tenant_id: str,
-        file: core.File,
-        sub_tenant_id: typing.Optional[str] = None,
-        tenant_metadata: typing.Optional[str] = OMIT,
-        document_metadata: typing.Optional[str] = OMIT,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> SingleUploadData:
-        """
-        Replace an existing document with updated content.
-
-        This endpoint allows you to update a specific document that's already in your knowledge base. Provide the source ID of the document you want to modify, along with the new file content.
-
-        The system will process your update asynchronously and re-index the document with the new content. You can monitor the progress using the returned file ID.
-
-        Parameters
-        ----------
-        source_id : str
-            The source ID of the document to update
-
-        tenant_id : str
-            Unique identifier for the tenant/organization
-
-        file : core.File
-            See core.File for more documentation
-
-        sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
-
-        tenant_metadata : typing.Optional[str]
-            JSON string containing tenant-level document metadata (e.g., department, compliance_tag)
-
-            Example: > "{"department":"Finance","compliance_tag":"GDPR"}"
-
-
-        document_metadata : typing.Optional[str]
-            JSON string containing document-specific metadata (e.g., title, author, file_id). If file_id is not provided, the system will generate an ID automatically.
-
-            Example: > "{"title":"Q1 Report.pdf","author":"Alice Smith","file_id":"custom_file_123"}"
-
-
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        SingleUploadData
-            Successful Response
-
-        Examples
-        --------
-        from usecortex-ai import CortexAI
-
-        client = CortexAI(token="YOUR_TOKEN", )
-        client.upload.update_document(source_id='CortexDoc1234', tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', )
-        """
-        _response = self._raw_client.update_document(
-            source_id=source_id,
-            tenant_id=tenant_id,
-            file=file,
-            sub_tenant_id=sub_tenant_id,
-            tenant_metadata=tenant_metadata,
-            document_metadata=document_metadata,
-            request_options=request_options,
-        )
-        return _response.data
-
-    def upload_app_sources(
-        self,
-        *,
-        tenant_id: str,
-        request: typing.Sequence[SourceModel],
-        sub_tenant_id: typing.Optional[str] = None,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> AppSourcesUploadData:
-        """
-        Upload structured data from applications or APIs for indexing.
-
-        This endpoint is designed for importing data from applications. If you are specifically using Cortex to provide search to an application, you should prefer this endpoint. It accepts structured source objects and allows you to clearly define contents of attachments
-
-        The system processes each source asynchronously and makes the content available for search and retrieval. Use this when you need to integrate search and indexing from data in your applications into your knowledge base.
-
-        Parameters
-        ----------
-        tenant_id : str
-            Unique identifier for the tenant/organization
-
-        request : typing.Sequence[SourceModel]
-
-        sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        AppSourcesUploadData
-            Successful Response
-
-        Examples
-        --------
-        from usecortex-ai import CortexAI, SourceModel
-
-        client = CortexAI(token="YOUR_TOKEN", )
-        client.upload.upload_app_sources(tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', request=[SourceModel()], )
-        """
-        _response = self._raw_client.upload_app_sources(
-            tenant_id=tenant_id, request=request, sub_tenant_id=sub_tenant_id, request_options=request_options
-        )
-        return _response.data
-
-    def upload_markdown(
-        self,
-        *,
-        tenant_id: str,
-        content: str,
-        sub_tenant_id: typing.Optional[str] = None,
-        file_id: typing.Optional[str] = OMIT,
-        tenant_metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
-        document_metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> SingleUploadData:
-        """
-        Upload text or markdown content directly for processing.
-
-        This endpoint accepts plain text or markdown-formatted content that you want to add to your knowledge base. It's perfect for notes, documentation, articles, or any text-based content you want to make searchable.
-
-        You can include custom metadata to help organize and categorize your content. You can track the processing status using the returned file ID.
-
-        Parameters
-        ----------
-        tenant_id : str
-            Unique identifier for the tenant/organization
-
-        content : str
-            The text or markdown content to upload
-
-        sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
-
-        file_id : typing.Optional[str]
-            Optional file ID for the uploaded content. If not provided, will be generated automatically.
-
-        tenant_metadata : typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]]
-            JSON string containing tenant-level document metadata (e.g., department, compliance_tag)
-
-            Example: > "{"department":"Finance","compliance_tag":"GDPR"}"
-
-        document_metadata : typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]]
-            JSON string containing document-specific metadata (e.g., title, author, file_id). If file_id is not provided, the system will generate an ID automatically.
-
-            Example: > "{"title":"Q1 Report.pdf","author":"Alice Smith","file_id":"custom_file_123"}"
-
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        SingleUploadData
-            Successful Response
-
-        Examples
-        --------
-        from usecortex-ai import CortexAI
-
-        client = CortexAI(token="YOUR_TOKEN", )
-        client.upload.upload_markdown(tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', content='<content>', )
-        """
-        _response = self._raw_client.upload_markdown(
-            tenant_id=tenant_id,
-            content=content,
-            sub_tenant_id=sub_tenant_id,
-            file_id=file_id,
-            tenant_metadata=tenant_metadata,
-            document_metadata=document_metadata,
-            request_options=request_options,
-        )
-        return _response.data
-
-    def upload_text(
-        self,
-        *,
-        tenant_id: str,
-        content: str,
-        sub_tenant_id: typing.Optional[str] = None,
-        file_id: typing.Optional[str] = OMIT,
-        tenant_metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
-        document_metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> SingleUploadData:
-        """
-        Upload text or markdown content directly for processing.
-
-        This endpoint accepts plain text or markdown-formatted content that you want to add to your knowledge base. It's perfect for notes, documentation, articles, or any text-based content you want to make searchable.
-
-        You can include custom metadata to help organize and categorize your content. You can track the processing status using the returned file ID.
-
-        Parameters
-        ----------
-        tenant_id : str
-            Unique identifier for the tenant/organization
-
-        content : str
-            The text or markdown content to upload
-
-        sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
-
-        file_id : typing.Optional[str]
-            Optional file ID for the uploaded content. If not provided, will be generated automatically.
-
-        tenant_metadata : typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]]
-            JSON string containing tenant-level document metadata (e.g., department, compliance_tag)
-
-            Example: > "{"department":"Finance","compliance_tag":"GDPR"}"
-
-        document_metadata : typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]]
-            JSON string containing document-specific metadata (e.g., title, author, file_id). If file_id is not provided, the system will generate an ID automatically.
-
-            Example: > "{"title":"Q1 Report.pdf","author":"Alice Smith","file_id":"custom_file_123"}"
-
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        SingleUploadData
-            Successful Response
-
-        Examples
-        --------
-        from usecortex-ai import CortexAI
-
-        client = CortexAI(token="YOUR_TOKEN", )
-        client.upload.upload_text(tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', content='<content>', )
-        """
-        _response = self._raw_client.upload_text(
-            tenant_id=tenant_id,
-            content=content,
-            sub_tenant_id=sub_tenant_id,
-            file_id=file_id,
-            tenant_metadata=tenant_metadata,
-            document_metadata=document_metadata,
-            request_options=request_options,
-        )
-        return _response.data
-
-    def update_markdown(
-        self,
-        *,
-        source_id: str,
-        tenant_id: str,
-        content: str,
-        sub_tenant_id: typing.Optional[str] = None,
-        file_id: typing.Optional[str] = OMIT,
-        tenant_metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
-        document_metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> SingleUploadData:
-        """
-        Update existing text or markdown content with new information.
-
-        This endpoint allows you to modify text or markdown content that's already in your knowledge base. Provide the source ID of the content you want to update, along with the new text.
-
-        The system will reprocess and re-index the updated content asynchronously. Use this when you need to correct information, add details, or refresh existing documentation.
-
-        Parameters
-        ----------
-        source_id : str
-            The source ID of the document to update
-
-        tenant_id : str
-            Unique identifier for the tenant/organization
-
-        content : str
-            The text or markdown content to upload
-
-        sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
-
-        file_id : typing.Optional[str]
-            Optional file ID for the uploaded content. If not provided, will be generated automatically.
-
-        tenant_metadata : typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]]
-            JSON string containing tenant-level document metadata (e.g., department, compliance_tag)
-
-            Example: > "{"department":"Finance","compliance_tag":"GDPR"}"
-
-        document_metadata : typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]]
-            JSON string containing document-specific metadata (e.g., title, author, file_id). If file_id is not provided, the system will generate an ID automatically.
-
-            Example: > "{"title":"Q1 Report.pdf","author":"Alice Smith","file_id":"custom_file_123"}"
-
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        SingleUploadData
-            Successful Response
-
-        Examples
-        --------
-        from usecortex-ai import CortexAI
-
-        client = CortexAI(token="YOUR_TOKEN", )
-        client.upload.update_markdown(source_id='CortexDoc1234', tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', content='<content>', )
-        """
-        _response = self._raw_client.update_markdown(
-            source_id=source_id,
-            tenant_id=tenant_id,
-            content=content,
-            sub_tenant_id=sub_tenant_id,
-            file_id=file_id,
-            tenant_metadata=tenant_metadata,
-            document_metadata=document_metadata,
-            request_options=request_options,
-        )
-        return _response.data
-
-    def update_text(
-        self,
-        *,
-        source_id: str,
-        tenant_id: str,
-        content: str,
-        sub_tenant_id: typing.Optional[str] = None,
-        file_id: typing.Optional[str] = OMIT,
-        tenant_metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
-        document_metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> SingleUploadData:
-        """
-        Update existing text or markdown content with new information.
-
-        This endpoint allows you to modify text or markdown content that's already in your knowledge base. Provide the source ID of the content you want to update, along with the new text.
-
-        The system will reprocess and re-index the updated content asynchronously. Use this when you need to correct information, add details, or refresh existing documentation.
-
-        Parameters
-        ----------
-        source_id : str
-            The source ID of the document to update
-
-        tenant_id : str
-            Unique identifier for the tenant/organization
-
-        content : str
-            The text or markdown content to upload
-
-        sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
-
-        file_id : typing.Optional[str]
-            Optional file ID for the uploaded content. If not provided, will be generated automatically.
-
-        tenant_metadata : typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]]
-            JSON string containing tenant-level document metadata (e.g., department, compliance_tag)
-
-            Example: > "{"department":"Finance","compliance_tag":"GDPR"}"
-
-        document_metadata : typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]]
-            JSON string containing document-specific metadata (e.g., title, author, file_id). If file_id is not provided, the system will generate an ID automatically.
-
-            Example: > "{"title":"Q1 Report.pdf","author":"Alice Smith","file_id":"custom_file_123"}"
-
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        SingleUploadData
-            Successful Response
-
-        Examples
-        --------
-        from usecortex-ai import CortexAI
-
-        client = CortexAI(token="YOUR_TOKEN", )
-        client.upload.update_text(source_id='CortexDoc1234', tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', content='<content>', )
-        """
-        _response = self._raw_client.update_text(
-            source_id=source_id,
-            tenant_id=tenant_id,
-            content=content,
-            sub_tenant_id=sub_tenant_id,
-            file_id=file_id,
-            tenant_metadata=tenant_metadata,
-            document_metadata=document_metadata,
-            request_options=request_options,
-        )
-        return _response.data
-
-    def batch_upload_markdown(
-        self,
-        *,
-        tenant_id: str,
-        request: typing.Sequence[MarkdownUploadRequest],
-        sub_tenant_id: typing.Optional[str] = None,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> BatchUploadData:
-        """
-        Upload multiple markdown/text documents simultaneously for efficient bulk processing.
-
-        This endpoint allows you to upload several markdown or text contents at once. Each content item gets processed asynchronously, and you can track the progress using their returned file IDs.
-
-        Parameters
-        ----------
-        tenant_id : str
-            Unique identifier for the tenant/organization
-
-        request : typing.Sequence[MarkdownUploadRequest]
-
-        sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        BatchUploadData
-            Successful Response
-
-        Examples
-        --------
-        from usecortex-ai import CortexAI, MarkdownUploadRequest
-
-        client = CortexAI(token="YOUR_TOKEN", )
-        client.upload.batch_upload_markdown(tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', request=[MarkdownUploadRequest(content='<content>', )], )
-        """
-        _response = self._raw_client.batch_upload_markdown(
-            tenant_id=tenant_id, request=request, sub_tenant_id=sub_tenant_id, request_options=request_options
-        )
-        return _response.data
-
-    def batch_upload_text(
-        self,
-        *,
-        tenant_id: str,
-        request: typing.Sequence[MarkdownUploadRequest],
-        sub_tenant_id: typing.Optional[str] = None,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> BatchUploadData:
-        """
-        Upload multiple markdown/text documents simultaneously for efficient bulk processing.
-
-        This endpoint allows you to upload several markdown or text contents at once. Each content item gets processed asynchronously, and you can track the progress using their returned file IDs.
-
-        Parameters
-        ----------
-        tenant_id : str
-            Unique identifier for the tenant/organization
-
-        request : typing.Sequence[MarkdownUploadRequest]
-
-        sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        BatchUploadData
-            Successful Response
-
-        Examples
-        --------
-        from usecortex-ai import CortexAI, MarkdownUploadRequest
-
-        client = CortexAI(token="YOUR_TOKEN", )
-        client.upload.batch_upload_text(tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', request=[MarkdownUploadRequest(content='<content>', )], )
-        """
-        _response = self._raw_client.batch_upload_text(
-            tenant_id=tenant_id, request=request, sub_tenant_id=sub_tenant_id, request_options=request_options
-        )
-        return _response.data
-
-    def upload_embeddings(
-        self,
-        *,
-        tenant_id: str,
-        embeddings: typing.Sequence[typing.Sequence[float]],
-        sub_tenant_id: typing.Optional[str] = None,
-        file_id: typing.Optional[str] = OMIT,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> SingleUploadData:
-        """
-        Upload pre-computed embeddings for advanced similarity search.
-
-        This endpoint accepts vector embeddings that you've generated externally, allowing you to integrate with custom embedding models or existing vector databases. The embeddings represent chunks of your content as numerical vectors.
-
-        The system stores these embeddings and makes them available for semantic search and similarity matching. Use this when you want to leverage specialized embedding models or have existing vector representations.
-
-        Parameters
-        ----------
-        tenant_id : str
-            Unique identifier for the tenant/organization
-
-        embeddings : typing.Sequence[typing.Sequence[float]]
-            The embeddings of source you want to index
-
-        sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
-
-        file_id : typing.Optional[str]
-            The Source ID of the target source you want to index
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        SingleUploadData
-            Successful Response
-
-        Examples
-        --------
-        from usecortex-ai import CortexAI
-
-        client = CortexAI(token="YOUR_TOKEN", )
-        client.upload.upload_embeddings(tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', embeddings=[[0.123413, 0.655367, 0.987654, 0.123456, 0.789012], [0.123413, 0.655367, 0.987654, 0.123456, 0.789012]], )
-        """
-        _response = self._raw_client.upload_embeddings(
-            tenant_id=tenant_id,
-            embeddings=embeddings,
-            sub_tenant_id=sub_tenant_id,
-            file_id=file_id,
-            request_options=request_options,
-        )
-        return _response.data
-
-    def update_embeddings(
-        self,
-        *,
-        tenant_id: str,
-        sub_tenant_id: typing.Optional[str] = None,
-        embeddings: typing.Optional[typing.Dict[str, typing.Sequence[float]]] = OMIT,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> SingleUploadData:
-        """
-        Update existing embeddings with new vector representations.
-
-        This endpoint allows you to modify embeddings that are already stored in your knowledge base. Provide updated vector representations for specific chunks of content, identified by their chunk IDs.
-
-        The system will replace the existing embeddings with your new ones, ensuring that similarity searches reflect the most current vector representations. Use this when you need to update embeddings due to model improvements or content changes.
-
-        Parameters
-        ----------
-        tenant_id : str
-            Unique identifier for the tenant/organization
-
-        sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
-
-        embeddings : typing.Optional[typing.Dict[str, typing.Sequence[float]]]
-            The embeddings of source you want to index
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        SingleUploadData
-            Successful Response
-
-        Examples
-        --------
-        from usecortex-ai import CortexAI
-
-        client = CortexAI(token="YOUR_TOKEN", )
-        client.upload.update_embeddings(tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', )
-        """
-        _response = self._raw_client.update_embeddings(
-            tenant_id=tenant_id, sub_tenant_id=sub_tenant_id, embeddings=embeddings, request_options=request_options
-        )
-        return _response.data
-
-    def scrape_webpage(
-        self,
-        *,
-        web_url: str,
-        tenant_id: str,
-        sub_tenant_id: typing.Optional[str] = None,
-        file_id: typing.Optional[str] = None,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> SingleUploadData:
-        """
-        Extract and index content from web pages automatically.
-
-        This endpoint initiates web scraping for the specified URL, extracting the main content, text, and structure from the webpage. It's perfect for capturing articles, documentation, or any web content you want to include in your knowledge base.
-
-        The system processes the webpage content asynchronously, cleaning and structuring the information for optimal search and retrieval. Use this when you need to add web content without manual copying and pasting.
-
-        Parameters
-        ----------
-        web_url : str
-            The URL of the webpage to scrape and index
-
-        tenant_id : str
-            Unique identifier for the tenant/organization
-
-        sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
-
-        file_id : typing.Optional[str]
-            Optional custom file ID for the scraped content. If not provided, a unique ID will be generated
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        SingleUploadData
-            Successful Response
-
-        Examples
-        --------
-        from usecortex-ai import CortexAI
-
-        client = CortexAI(token="YOUR_TOKEN", )
-        client.upload.scrape_webpage(web_url='https://www.usecortex.ai/', tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', file_id='CortexDoc1234', )
-        """
-        _response = self._raw_client.scrape_webpage(
-            web_url=web_url,
-            tenant_id=tenant_id,
-            sub_tenant_id=sub_tenant_id,
-            file_id=file_id,
-            request_options=request_options,
-        )
-        return _response.data
-
-    def update_webpage(
-        self,
-        *,
-        web_url: str,
-        source_id: str,
-        tenant_id: str,
-        sub_tenant_id: typing.Optional[str] = None,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> SingleUploadData:
-        """
-        Update web scraping content with fresh data from the source URL.
-
-        This endpoint refreshes the content for an existing web scraping job. Provide the source ID of the webpage content you want to update, and the system will re-scrape the URL to capture any changes.
-
-        The updated content gets processed asynchronously and re-indexed in your knowledge base. Use this to keep web content current when the source pages are frequently updated.
-
-        Parameters
-        ----------
-        web_url : str
-            The URL of the webpage to re-scrape
-
-        source_id : str
-            The file ID of the existing web scraping job to update
-
-        tenant_id : str
-            Unique identifier for the tenant/organization
-
-        sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        SingleUploadData
-            Successful Response
-
-        Examples
-        --------
-        from usecortex-ai import CortexAI
-
-        client = CortexAI(token="YOUR_TOKEN", )
-        client.upload.update_webpage(web_url='https://www.usecortex.ai/', source_id='CortexDoc1234', tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', )
-        """
-        _response = self._raw_client.update_webpage(
-            web_url=web_url,
-            source_id=source_id,
-            tenant_id=tenant_id,
-            sub_tenant_id=sub_tenant_id,
-            request_options=request_options,
-        )
-        return _response.data
-
-    def batch_scrape_webpage(
-        self,
-        *,
-        tenant_id: str,
-        request: typing.Sequence[WebpageScrapeRequest],
-        sub_tenant_id: typing.Optional[str] = None,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> BatchUploadData:
-        """
-        Extract and index content from multiple web pages simultaneously.
-
-        This endpoint initiates web scraping for multiple URLs at once, extracting the main content, text, and structure from each webpage. It's perfect for capturing multiple articles, documentation pages, or any web content you want to include in your knowledge base.
-
-        The system processes all webpage content asynchronously, cleaning and structuring the information for optimal search and retrieval.
-
-        Parameters
-        ----------
-        tenant_id : str
-            Unique identifier for the tenant/organization
-
-        request : typing.Sequence[WebpageScrapeRequest]
-
-        sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        BatchUploadData
-            Successful Response
-
-        Examples
-        --------
-        from usecortex-ai import CortexAI, WebpageScrapeRequest
-
-        client = CortexAI(token="YOUR_TOKEN", )
-        client.upload.batch_scrape_webpage(tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', request=[WebpageScrapeRequest(web_url='https://www.usecortex.ai/', )], )
-        """
-        _response = self._raw_client.batch_scrape_webpage(
-            tenant_id=tenant_id, request=request, sub_tenant_id=sub_tenant_id, request_options=request_options
-        )
-        return _response.data
-
-    def delete_source(
-        self,
-        *,
-        tenant_id: str,
-        source_ids: typing.Sequence[str],
-        sub_tenant_id: typing.Optional[str] = OMIT,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> typing.Optional[typing.Any]:
-        """
-        Remove documents and content from your knowledge base.
-
-        This endpoint permanently deletes the specified sources from your knowledge base. Once deleted, the content will no longer be available for search or retrieval.
-
-        Use this carefully as the action cannot be undone. The system will confirm successful deletion of each source ID you specify.
-
-        Parameters
-        ----------
-        tenant_id : str
-            Unique identifier for the tenant/organization
-
-        source_ids : typing.Sequence[str]
-            List of source IDs to delete
-
-        sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        typing.Optional[typing.Any]
-            Successful Response
-
-        Examples
-        --------
-        from usecortex-ai import CortexAI
-
-        client = CortexAI(token="YOUR_TOKEN", )
-        client.upload.delete_source(tenant_id='tenant_1234', source_ids=['CortexDoc1234', 'CortexDoc4567'], )
-        """
-        _response = self._raw_client.delete_source(
-            tenant_id=tenant_id, source_ids=source_ids, sub_tenant_id=sub_tenant_id, request_options=request_options
-        )
-        return _response.data
-
-    def delete_memory(
-        self,
-        *,
-        tenant_id: str,
-        source_ids: typing.Sequence[str],
-        sub_tenant_id: typing.Optional[str] = OMIT,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> typing.Optional[typing.Any]:
-        """
-        Remove documents and content from your knowledge base.
-
-        This endpoint permanently deletes the specified sources from your knowledge base. Once deleted, the content will no longer be available for search or retrieval.
-
-        Use this carefully as the action cannot be undone. The system will confirm successful deletion of each source ID you specify.
-
-        Parameters
-        ----------
-        tenant_id : str
-            Unique identifier for the tenant/organization
-
-        source_ids : typing.Sequence[str]
-            List of source IDs to delete
-
-        sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        typing.Optional[typing.Any]
-            Successful Response
-
-        Examples
-        --------
-        from usecortex-ai import CortexAI
-
-        client = CortexAI(token="YOUR_TOKEN", )
-        client.upload.delete_memory(tenant_id='tenant_1234', source_ids=['CortexDoc1234', 'CortexDoc4567'], )
-        """
-        _response = self._raw_client.delete_memory(
-            tenant_id=tenant_id, source_ids=source_ids, sub_tenant_id=sub_tenant_id, request_options=request_options
-        )
-        return _response.data
-
-    def verify_processing(
-        self,
-        *,
-        file_id: str,
-        tenant_id: typing.Optional[str] = None,
-        sub_tenant_id: typing.Optional[str] = None,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> ProcessingStatus:
-        """
-        Check the current processing status of your uploaded content.
-
-        This endpoint allows you to monitor the progress of documents, text, or other content you've uploaded. Simply provide the file ID to see whether processing is complete, still in progress, or if any errors occurred.
-
-        Use this to determine when your content is ready for search and retrieval, or to troubleshoot any processing issues.
-
-        Parameters
-        ----------
-        file_id : str
-            The file ID to check processing status for
-
-        tenant_id : typing.Optional[str]
-            Unique identifier for the tenant/organization
-
-        sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        ProcessingStatus
-            Successful Response
-
-        Examples
-        --------
-        from usecortex-ai import CortexAI
-
-        client = CortexAI(token="YOUR_TOKEN", )
-        client.upload.verify_processing(file_id='CortexDoc1234', tenant_id='tenant_1234', )
-        """
-        _response = self._raw_client.verify_processing(
-            file_id=file_id, tenant_id=tenant_id, sub_tenant_id=sub_tenant_id, request_options=request_options
-        )
-        return _response.data
-
-
-class AsyncUploadClient:
-    def __init__(self, *, client_wrapper: AsyncClientWrapper):
-        self._raw_client = AsyncRawUploadClient(client_wrapper=client_wrapper)
-
-    @property
-    def with_raw_response(self) -> AsyncRawUploadClient:
-        """
-        Retrieves a raw implementation of this client that returns raw responses.
-
-        Returns
-        -------
-        AsyncRawUploadClient
-        """
-        return self._raw_client
-
-    async def batch_upload(
-        self,
-        *,
-        tenant_id: str,
-        files: typing.List[core.File],
-        sub_tenant_id: typing.Optional[str] = None,
-        file_ids: typing.Optional[str] = OMIT,
-        tenant_metadata: typing.Optional[str] = OMIT,
-        document_metadata: typing.Optional[str] = OMIT,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> BatchUploadData:
-        """
-        Upload multiple documents simultaneously for efficient bulk processing.
-
-        This endpoint allows you to upload several files at once, which is ideal for large document collections or periodic data imports. Each file gets processed asynchronously, and you can track the progress of individual files using their returned file IDs.
-
-        The system automatically handles file parsing, content extraction, and indexing across all uploaded documents. You'll receive confirmation once all files are queued for processing.
-
-        Parameters
-        ----------
-        tenant_id : str
-            Unique identifier for the tenant/organization
-
-        files : typing.List[core.File]
-            See core.File for more documentation
-
-        sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
-
-        file_ids : typing.Optional[str]
-            Optional JSON string array of file IDs for the uploaded content. If not provided or empty, will be generated automatically.
-
-        tenant_metadata : typing.Optional[str]
-            JSON string containing tenant-level document metadata (e.g., department, compliance_tag)
-
-            Example: > "{"department":"Finance","compliance_tag":"GDPR"}"
-
-
-        document_metadata : typing.Optional[str]
-            JSON string containing document-specific metadata (e.g., title, author, file_id). If file_id is not provided, the system will generate an ID automatically.
-
-            Example: > "{"title":"Q1 Report.pdf","author":"Alice Smith","file_id":"custom_file_123"}"
-
-
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        BatchUploadData
-            Successful Response
-
-        Examples
-        --------
-        import asyncio
-
-        from usecortex-ai import AsyncCortexAI
-
-        client = AsyncCortexAI(token="YOUR_TOKEN", )
-        async def main() -> None:
-            await client.upload.batch_upload(tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', )
-        asyncio.run(main())
-        """
-        _response = await self._raw_client.batch_upload(
-            tenant_id=tenant_id,
-            files=files,
-            sub_tenant_id=sub_tenant_id,
-            file_ids=file_ids,
-            tenant_metadata=tenant_metadata,
-            document_metadata=document_metadata,
-            request_options=request_options,
-        )
-        return _response.data
-
-    async def batch_update(
-        self,
-        *,
-        tenant_id: str,
-        files: typing.List[core.File],
-        sub_tenant_id: typing.Optional[str] = None,
-        source_ids: typing.Optional[typing.List[str]] = OMIT,
-        tenant_metadata: typing.Optional[str] = OMIT,
-        document_metadata: typing.Optional[str] = OMIT,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> BatchUploadData:
-        """
-        Update multiple existing documents with new content and metadata.
-
-        Use this endpoint when you need to replace or modify several documents that are already in your knowledge base. Each file must correspond to an existing source ID, ensuring that updates are applied to the correct documents.
-
-        The system processes updates asynchronously, allowing you to continue working while your documents are re-indexed. Track the progress using the returned file IDs to know when updates are complete.
-
-        Parameters
-        ----------
-        tenant_id : str
-            Unique identifier for the tenant/organization
-
-        files : typing.List[core.File]
-            See core.File for more documentation
-
-        sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
-
-        source_ids : typing.Optional[typing.List[str]]
-            List of source IDs corresponding to the files being updated
-
-        tenant_metadata : typing.Optional[str]
-            JSON string containing tenant-level document metadata (e.g., department, compliance_tag)
-
-            Example: > "{"department":"Finance","compliance_tag":"GDPR"}"
-
-
-        document_metadata : typing.Optional[str]
-            JSON string containing document-specific metadata (e.g., title, author, file_id). If file_id is not provided, the system will generate an ID automatically.
-
-            Example: > "{"title":"Q1 Report.pdf","author":"Alice Smith","file_id":"custom_file_123"}"
-
-
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        BatchUploadData
-            Successful Response
-
-        Examples
-        --------
-        import asyncio
-
-        from usecortex-ai import AsyncCortexAI
-
-        client = AsyncCortexAI(token="YOUR_TOKEN", )
-        async def main() -> None:
-            await client.upload.batch_update(tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', )
-        asyncio.run(main())
-        """
-        _response = await self._raw_client.batch_update(
-            tenant_id=tenant_id,
-            files=files,
-            sub_tenant_id=sub_tenant_id,
-            source_ids=source_ids,
-            tenant_metadata=tenant_metadata,
-            document_metadata=document_metadata,
-            request_options=request_options,
-        )
-        return _response.data
-
-    async def upload_document(
-        self,
-        *,
-        tenant_id: str,
-        file: core.File,
-        sub_tenant_id: typing.Optional[str] = None,
-        file_id: typing.Optional[str] = OMIT,
-        tenant_metadata: typing.Optional[str] = OMIT,
-        document_metadata: typing.Optional[str] = OMIT,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> SingleUploadData:
-        """
-        Upload a single document for processing and indexing into your knowledge base.
-
-        This endpoint accepts documents in various formats and processes them for search and retrieval. You can include custom metadata to help organize and categorize your content.
-
-        The system extracts text content, processes it asynchronously, and makes it available for search queries. You can track the processing status using the returned file ID.
-
-        Parameters
-        ----------
-        tenant_id : str
-            Unique identifier for the tenant/organization
-
-        file : core.File
-            See core.File for more documentation
-
-        sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
-
-        file_id : typing.Optional[str]
-            Optional file ID for the uploaded content. If not provided, will be generated automatically.
-
-        tenant_metadata : typing.Optional[str]
-            JSON string containing tenant-level document metadata (e.g., department, compliance_tag)
-
-            Example: > "{"department":"Finance","compliance_tag":"GDPR"}"
-
-
-        document_metadata : typing.Optional[str]
-            JSON string containing document-specific metadata (e.g., title, author, file_id). If file_id is not provided, the system will generate an ID automatically.
-
-            Example: > "{"title":"Q1 Report.pdf","author":"Alice Smith","file_id":"custom_file_123"}"
-
-
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        SingleUploadData
-            Successful Response
-
-        Examples
-        --------
-        import asyncio
-
-        from usecortex-ai import AsyncCortexAI
-
-        client = AsyncCortexAI(token="YOUR_TOKEN", )
-        async def main() -> None:
-            await client.upload.upload_document(tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', )
-        asyncio.run(main())
-        """
-        _response = await self._raw_client.upload_document(
-            tenant_id=tenant_id,
-            file=file,
-            sub_tenant_id=sub_tenant_id,
-            file_id=file_id,
-            tenant_metadata=tenant_metadata,
-            document_metadata=document_metadata,
-            request_options=request_options,
-        )
-        return _response.data
-
-    async def update_document(
-        self,
-        *,
-        source_id: str,
-        tenant_id: str,
-        file: core.File,
-        sub_tenant_id: typing.Optional[str] = None,
-        tenant_metadata: typing.Optional[str] = OMIT,
-        document_metadata: typing.Optional[str] = OMIT,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> SingleUploadData:
-        """
-        Replace an existing document with updated content.
-
-        This endpoint allows you to update a specific document that's already in your knowledge base. Provide the source ID of the document you want to modify, along with the new file content.
-
-        The system will process your update asynchronously and re-index the document with the new content. You can monitor the progress using the returned file ID.
-
-        Parameters
-        ----------
-        source_id : str
-            The source ID of the document to update
-
-        tenant_id : str
-            Unique identifier for the tenant/organization
-
-        file : core.File
-            See core.File for more documentation
-
-        sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
-
-        tenant_metadata : typing.Optional[str]
-            JSON string containing tenant-level document metadata (e.g., department, compliance_tag)
-
-            Example: > "{"department":"Finance","compliance_tag":"GDPR"}"
-
-
-        document_metadata : typing.Optional[str]
-            JSON string containing document-specific metadata (e.g., title, author, file_id). If file_id is not provided, the system will generate an ID automatically.
-
-            Example: > "{"title":"Q1 Report.pdf","author":"Alice Smith","file_id":"custom_file_123"}"
-
-
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        SingleUploadData
-            Successful Response
-
-        Examples
-        --------
-        import asyncio
-
-        from usecortex-ai import AsyncCortexAI
-
-        client = AsyncCortexAI(token="YOUR_TOKEN", )
-        async def main() -> None:
-            await client.upload.update_document(source_id='CortexDoc1234', tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', )
-        asyncio.run(main())
-        """
-        _response = await self._raw_client.update_document(
-            source_id=source_id,
-            tenant_id=tenant_id,
-            file=file,
-            sub_tenant_id=sub_tenant_id,
-            tenant_metadata=tenant_metadata,
-            document_metadata=document_metadata,
-            request_options=request_options,
-        )
-        return _response.data
-
-    async def upload_app_sources(
-        self,
-        *,
-        tenant_id: str,
-        request: typing.Sequence[SourceModel],
-        sub_tenant_id: typing.Optional[str] = None,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> AppSourcesUploadData:
-        """
-        Upload structured data from applications or APIs for indexing.
-
-        This endpoint is designed for importing data from applications. If you are specifically using Cortex to provide search to an application, you should prefer this endpoint. It accepts structured source objects and allows you to clearly define contents of attachments
-
-        The system processes each source asynchronously and makes the content available for search and retrieval. Use this when you need to integrate search and indexing from data in your applications into your knowledge base.
-
-        Parameters
-        ----------
-        tenant_id : str
-            Unique identifier for the tenant/organization
-
-        request : typing.Sequence[SourceModel]
-
-        sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        AppSourcesUploadData
-            Successful Response
-
-        Examples
-        --------
-        import asyncio
-
-        from usecortex-ai import AsyncCortexAI, SourceModel
-
-        client = AsyncCortexAI(token="YOUR_TOKEN", )
-        async def main() -> None:
-            await client.upload.upload_app_sources(tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', request=[SourceModel()], )
-        asyncio.run(main())
-        """
-        _response = await self._raw_client.upload_app_sources(
-            tenant_id=tenant_id, request=request, sub_tenant_id=sub_tenant_id, request_options=request_options
-        )
-        return _response.data
-
-    async def upload_markdown(
-        self,
-        *,
-        tenant_id: str,
-        content: str,
-        sub_tenant_id: typing.Optional[str] = None,
-        file_id: typing.Optional[str] = OMIT,
-        tenant_metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
-        document_metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> SingleUploadData:
-        """
-        Upload text or markdown content directly for processing.
-
-        This endpoint accepts plain text or markdown-formatted content that you want to add to your knowledge base. It's perfect for notes, documentation, articles, or any text-based content you want to make searchable.
-
-        You can include custom metadata to help organize and categorize your content. You can track the processing status using the returned file ID.
-
-        Parameters
-        ----------
-        tenant_id : str
-            Unique identifier for the tenant/organization
-
-        content : str
-            The text or markdown content to upload
-
-        sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
-
-        file_id : typing.Optional[str]
-            Optional file ID for the uploaded content. If not provided, will be generated automatically.
-
-        tenant_metadata : typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]]
-            JSON string containing tenant-level document metadata (e.g., department, compliance_tag)
-
-            Example: > "{"department":"Finance","compliance_tag":"GDPR"}"
-
-        document_metadata : typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]]
-            JSON string containing document-specific metadata (e.g., title, author, file_id). If file_id is not provided, the system will generate an ID automatically.
-
-            Example: > "{"title":"Q1 Report.pdf","author":"Alice Smith","file_id":"custom_file_123"}"
-
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        SingleUploadData
-            Successful Response
-
-        Examples
-        --------
-        import asyncio
-
-        from usecortex-ai import AsyncCortexAI
-
-        client = AsyncCortexAI(token="YOUR_TOKEN", )
-        async def main() -> None:
-            await client.upload.upload_markdown(tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', content='<content>', )
-        asyncio.run(main())
-        """
-        _response = await self._raw_client.upload_markdown(
-            tenant_id=tenant_id,
-            content=content,
-            sub_tenant_id=sub_tenant_id,
-            file_id=file_id,
-            tenant_metadata=tenant_metadata,
-            document_metadata=document_metadata,
-            request_options=request_options,
-        )
-        return _response.data
-
-    async def upload_text(
-        self,
-        *,
-        tenant_id: str,
-        content: str,
-        sub_tenant_id: typing.Optional[str] = None,
-        file_id: typing.Optional[str] = OMIT,
-        tenant_metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
-        document_metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> SingleUploadData:
-        """
-        Upload text or markdown content directly for processing.
-
-        This endpoint accepts plain text or markdown-formatted content that you want to add to your knowledge base. It's perfect for notes, documentation, articles, or any text-based content you want to make searchable.
-
-        You can include custom metadata to help organize and categorize your content. You can track the processing status using the returned file ID.
-
-        Parameters
-        ----------
-        tenant_id : str
-            Unique identifier for the tenant/organization
-
-        content : str
-            The text or markdown content to upload
-
-        sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
-
-        file_id : typing.Optional[str]
-            Optional file ID for the uploaded content. If not provided, will be generated automatically.
-
-        tenant_metadata : typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]]
-            JSON string containing tenant-level document metadata (e.g., department, compliance_tag)
-
-            Example: > "{"department":"Finance","compliance_tag":"GDPR"}"
-
-        document_metadata : typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]]
-            JSON string containing document-specific metadata (e.g., title, author, file_id). If file_id is not provided, the system will generate an ID automatically.
-
-            Example: > "{"title":"Q1 Report.pdf","author":"Alice Smith","file_id":"custom_file_123"}"
-
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        SingleUploadData
-            Successful Response
-
-        Examples
-        --------
-        import asyncio
-
-        from usecortex-ai import AsyncCortexAI
-
-        client = AsyncCortexAI(token="YOUR_TOKEN", )
-        async def main() -> None:
-            await client.upload.upload_text(tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', content='<content>', )
-        asyncio.run(main())
-        """
-        _response = await self._raw_client.upload_text(
-            tenant_id=tenant_id,
-            content=content,
-            sub_tenant_id=sub_tenant_id,
-            file_id=file_id,
-            tenant_metadata=tenant_metadata,
-            document_metadata=document_metadata,
-            request_options=request_options,
-        )
-        return _response.data
-
-    async def update_markdown(
+    def upload_document(
         self,
         *,
-        source_id: str,
+        files: typing.List[core.File],
         tenant_id: str,
-        content: str,
-        sub_tenant_id: typing.Optional[str] = None,
-        file_id: typing.Optional[str] = OMIT,
-        tenant_metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
-        document_metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
+        sub_tenant_id: typing.Optional[str] = OMIT,
+        upsert: typing.Optional[bool] = OMIT,
+        file_metadata: typing.Optional[str] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
-    ) -> SingleUploadData:
+    ) -> SourceUploadResponse:
         """
-        Update existing text or markdown content with new information.
-
-        This endpoint allows you to modify text or markdown content that's already in your knowledge base. Provide the source ID of the content you want to update, along with the new text.
-
-        The system will reprocess and re-index the updated content asynchronously. Use this when you need to correct information, add details, or refresh existing documentation.
+        Upload one or more documents for ingestion.
+        Supports both single and batch uploads.
+        For single file: send one file with the 'files' field.
+        For batch: send multiple files with the 'files' field (FastAPI will parse as list).
 
         Parameters
         ----------
-        source_id : str
-            The source ID of the document to update
+        files : typing.List[core.File]
+            See core.File for more documentation
 
         tenant_id : str
             Unique identifier for the tenant/organization
 
-        content : str
-            The text or markdown content to upload
-
         sub_tenant_id : typing.Optional[str]
             Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
 
-        file_id : typing.Optional[str]
-            Optional file ID for the uploaded content. If not provided, will be generated automatically.
-
-        tenant_metadata : typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]]
-            JSON string containing tenant-level document metadata (e.g., department, compliance_tag)
-
-            Example: > "{"department":"Finance","compliance_tag":"GDPR"}"
-
-        document_metadata : typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]]
-            JSON string containing document-specific metadata (e.g., title, author, file_id). If file_id is not provided, the system will generate an ID automatically.
-
-            Example: > "{"title":"Q1 Report.pdf","author":"Alice Smith","file_id":"custom_file_123"}"
+        upsert : typing.Optional[bool]
 
+        file_metadata : typing.Optional[str]
+            JSON Array of file metadata objects
 
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
         Returns
         -------
-        SingleUploadData
+        SourceUploadResponse
             Successful Response
 
         Examples
         --------
-        import asyncio
-
-        from usecortex-ai import AsyncCortexAI
+        from usecortex-ai import CortexAI
 
-        client = AsyncCortexAI(token="YOUR_TOKEN", )
-        async def main() -> None:
-            await client.upload.update_markdown(source_id='CortexDoc1234', tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', content='<content>', )
-        asyncio.run(main())
+        client = CortexAI(token="YOUR_TOKEN", )
+        client.upload.upload_document(tenant_id='tenant_id', )
         """
-        _response = await self._raw_client.update_markdown(
-            source_id=source_id,
+        _response = self._raw_client.upload_document(
+            files=files,
             tenant_id=tenant_id,
-            content=content,
             sub_tenant_id=sub_tenant_id,
-            file_id=file_id,
-            tenant_metadata=tenant_metadata,
-            document_metadata=document_metadata,
+            upsert=upsert,
+            file_metadata=file_metadata,
             request_options=request_options,
         )
         return _response.data
 
-    async def update_text(
+    def upload_app_sources(
         self,
         *,
-        source_id: str,
+        app_sources: BodyUploadAppIngestionUploadAppPostAppSources,
         tenant_id: str,
-        content: str,
-        sub_tenant_id: typing.Optional[str] = None,
-        file_id: typing.Optional[str] = OMIT,
-        tenant_metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
-        document_metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
+        sub_tenant_id: typing.Optional[str] = OMIT,
+        upsert: typing.Optional[bool] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
-    ) -> SingleUploadData:
+    ) -> AppSourcesUploadData:
         """
-        Update existing text or markdown content with new information.
-
-        This endpoint allows you to modify text or markdown content that's already in your knowledge base. Provide the source ID of the content you want to update, along with the new text.
-
-        The system will reprocess and re-index the updated content asynchronously. Use this when you need to correct information, add details, or refresh existing documentation.
+        Upload structured sources generated by first-party or third-party apps.
+        Supports both single and batch uploads.
 
         Parameters
         ----------
-        source_id : str
-            The source ID of the document to update
+        app_sources : BodyUploadAppIngestionUploadAppPostAppSources
+            Single source object or list of structured source objects containing app-generated data to be indexed
 
         tenant_id : str
             Unique identifier for the tenant/organization
 
-        content : str
-            The text or markdown content to upload
-
         sub_tenant_id : typing.Optional[str]
             Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
 
-        file_id : typing.Optional[str]
-            Optional file ID for the uploaded content. If not provided, will be generated automatically.
-
-        tenant_metadata : typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]]
-            JSON string containing tenant-level document metadata (e.g., department, compliance_tag)
-
-            Example: > "{"department":"Finance","compliance_tag":"GDPR"}"
-
-        document_metadata : typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]]
-            JSON string containing document-specific metadata (e.g., title, author, file_id). If file_id is not provided, the system will generate an ID automatically.
-
-            Example: > "{"title":"Q1 Report.pdf","author":"Alice Smith","file_id":"custom_file_123"}"
-
+        upsert : typing.Optional[bool]
+            If true, update existing sources with the same source_id. Defaults to True.
 
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
         Returns
         -------
-        SingleUploadData
+        AppSourcesUploadData
             Successful Response
 
         Examples
         --------
-        import asyncio
-
-        from usecortex-ai import AsyncCortexAI
+        from usecortex-ai import CortexAI, SourceModel
 
-        client = AsyncCortexAI(token="YOUR_TOKEN", )
-        async def main() -> None:
-            await client.upload.update_text(source_id='CortexDoc1234', tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', content='<content>', )
-        asyncio.run(main())
+        client = CortexAI(token="YOUR_TOKEN", )
+        client.upload.upload_app_sources(app_sources=SourceModel(id='id', tenant_id='tenant_id', sub_tenant_id='sub_tenant_id', ), tenant_id='tenant_id', )
         """
-        _response = await self._raw_client.update_text(
-            source_id=source_id,
+        _response = self._raw_client.upload_app_sources(
+            app_sources=app_sources,
             tenant_id=tenant_id,
-            content=content,
             sub_tenant_id=sub_tenant_id,
-            file_id=file_id,
-            tenant_metadata=tenant_metadata,
-            document_metadata=document_metadata,
+            upsert=upsert,
             request_options=request_options,
         )
         return _response.data
 
-    async def batch_upload_markdown(
+    def verify_processing(
         self,
         *,
-        tenant_id: str,
-        request: typing.Sequence[MarkdownUploadRequest],
+        file_id: str,
+        tenant_id: typing.Optional[str] = None,
         sub_tenant_id: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
-    ) -> BatchUploadData:
+    ) -> ProcessingStatus:
         """
-        Upload multiple markdown/text documents simultaneously for efficient bulk processing.
+        Check the current processing status of your uploaded content.
+
+        This endpoint allows you to monitor the progress of documents, text, or other content you've uploaded. Simply provide the file ID to see whether processing is complete, still in progress, or if any errors occurred.
 
-        This endpoint allows you to upload several markdown or text contents at once. Each content item gets processed asynchronously, and you can track the progress using their returned file IDs.
+        Use this to determine when your content is ready for search and retrieval, or to troubleshoot any processing issues.
 
         Parameters
         ----------
-        tenant_id : str
-            Unique identifier for the tenant/organization
+        file_id : str
+            The file ID to check processing status for
 
-        request : typing.Sequence[MarkdownUploadRequest]
+        tenant_id : typing.Optional[str]
+            Unique identifier for the tenant/organization
 
         sub_tenant_id : typing.Optional[str]
             Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
@@ -1820,200 +172,171 @@ class AsyncUploadClient:
 
         Returns
         -------
-        BatchUploadData
+        ProcessingStatus
             Successful Response
 
         Examples
         --------
-        import asyncio
-
-        from usecortex-ai import AsyncCortexAI, MarkdownUploadRequest
+        from usecortex-ai import CortexAI
 
-        client = AsyncCortexAI(token="YOUR_TOKEN", )
-        async def main() -> None:
-            await client.upload.batch_upload_markdown(tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', request=[MarkdownUploadRequest(content='<content>', )], )
-        asyncio.run(main())
+        client = CortexAI(token="YOUR_TOKEN", )
+        client.upload.verify_processing(file_id='file_id', )
         """
-        _response = await self._raw_client.batch_upload_markdown(
-            tenant_id=tenant_id, request=request, sub_tenant_id=sub_tenant_id, request_options=request_options
+        _response = self._raw_client.verify_processing(
+            file_id=file_id, tenant_id=tenant_id, sub_tenant_id=sub_tenant_id, request_options=request_options
         )
         return _response.data
 
-    async def batch_upload_text(
+    def add_memory(
         self,
         *,
+        memories: typing.Sequence[MemoryItem],
         tenant_id: str,
-        request: typing.Sequence[MarkdownUploadRequest],
-        sub_tenant_id: typing.Optional[str] = None,
+        sub_tenant_id: typing.Optional[str] = OMIT,
+        upsert: typing.Optional[bool] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
-    ) -> BatchUploadData:
+    ) -> AddMemoryResponse:
         """
-        Upload multiple markdown/text documents simultaneously for efficient bulk processing.
+        Add memories for indexing and retrieval.
+
+            This API provides a unified entry point for ingesting various types of content:
+
+            **Content Types Supported:**
+            - Raw text content (`text` field)
+            - Markdown formatted content (`text` + `is_markdown=true`)
+            - User/assistant conversation pairs (`user_assistant_pairs` field)
 
-        This endpoint allows you to upload several markdown or text contents at once. Each content item gets processed asynchronously, and you can track the progress using their returned file IDs.
+            **Key Features:**
+            - **Inference Mode (`infer=true`)**: When enabled, the system extracts additional
+              insights and implicit information from your content. Useful for conversation
+              analysis and knowledge extraction.
+            - **Direct Mode (`infer=false`)**: Content is chunked and indexed as-is without
+              additional processing.
+
+            Use `/ingestion/verify-processing` endpoint to check the processing status.
 
         Parameters
         ----------
+        memories : typing.Sequence[MemoryItem]
+            List of memory items to ingest
+
         tenant_id : str
             Unique identifier for the tenant/organization
 
-        request : typing.Sequence[MarkdownUploadRequest]
-
         sub_tenant_id : typing.Optional[str]
             Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
 
+        upsert : typing.Optional[bool]
+            If true, update existing sources with the same source_id.
+
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
         Returns
         -------
-        BatchUploadData
+        AddMemoryResponse
             Successful Response
 
         Examples
         --------
-        import asyncio
-
-        from usecortex-ai import AsyncCortexAI, MarkdownUploadRequest
+        from usecortex-ai import CortexAI, MemoryItem
 
-        client = AsyncCortexAI(token="YOUR_TOKEN", )
-        async def main() -> None:
-            await client.upload.batch_upload_text(tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', request=[MarkdownUploadRequest(content='<content>', )], )
-        asyncio.run(main())
+        client = CortexAI(token="YOUR_TOKEN", )
+        client.upload.add_memory(memories=[MemoryItem()], tenant_id='tenant_id', )
         """
-        _response = await self._raw_client.batch_upload_text(
-            tenant_id=tenant_id, request=request, sub_tenant_id=sub_tenant_id, request_options=request_options
+        _response = self._raw_client.add_memory(
+            memories=memories,
+            tenant_id=tenant_id,
+            sub_tenant_id=sub_tenant_id,
+            upsert=upsert,
+            request_options=request_options,
         )
         return _response.data
 
-    async def upload_embeddings(
+    def delete_memory(
         self,
         *,
         tenant_id: str,
-        embeddings: typing.Sequence[typing.Sequence[float]],
+        memory_id: str,
         sub_tenant_id: typing.Optional[str] = None,
-        file_id: typing.Optional[str] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
-    ) -> SingleUploadData:
+    ) -> DeleteUserMemoryResponse:
         """
-        Upload pre-computed embeddings for advanced similarity search.
+        Permanently remove a specific memory from storage.
 
-        This endpoint accepts vector embeddings that you've generated externally, allowing you to integrate with custom embedding models or existing vector databases. The embeddings represent chunks of your content as numerical vectors.
+            This API allows you to delete a memory by its unique identifier.
+            Once deleted, the memory cannot be recovered, so use this operation carefully.
 
-        The system stores these embeddings and makes them available for semantic search and similarity matching. Use this when you want to leverage specialized embedding models or have existing vector representations.
+            The memory will be removed from your tenant's storage and will no longer
+            appear in search results or memory listings.
 
         Parameters
         ----------
         tenant_id : str
-            Unique identifier for the tenant/organization
+            Tenant ID
 
-        embeddings : typing.Sequence[typing.Sequence[float]]
-            The embeddings of source you want to index
+        memory_id : str
+            Unique identifier of the memory to delete
 
         sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
-
-        file_id : typing.Optional[str]
-            The Source ID of the target source you want to index
+            Sub-tenant ID
 
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
         Returns
         -------
-        SingleUploadData
+        DeleteUserMemoryResponse
             Successful Response
 
         Examples
         --------
-        import asyncio
-
-        from usecortex-ai import AsyncCortexAI
+        from usecortex-ai import CortexAI
 
-        client = AsyncCortexAI(token="YOUR_TOKEN", )
-        async def main() -> None:
-            await client.upload.upload_embeddings(tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', embeddings=[[0.123413, 0.655367, 0.987654, 0.123456, 0.789012], [0.123413, 0.655367, 0.987654, 0.123456, 0.789012]], )
-        asyncio.run(main())
+        client = CortexAI(token="YOUR_TOKEN", )
+        client.upload.delete_memory(tenant_id='tenant_id', memory_id='memory_id', )
         """
-        _response = await self._raw_client.upload_embeddings(
-            tenant_id=tenant_id,
-            embeddings=embeddings,
-            sub_tenant_id=sub_tenant_id,
-            file_id=file_id,
-            request_options=request_options,
+        _response = self._raw_client.delete_memory(
+            tenant_id=tenant_id, memory_id=memory_id, sub_tenant_id=sub_tenant_id, request_options=request_options
         )
         return _response.data
 
-    async def update_embeddings(
-        self,
-        *,
-        tenant_id: str,
-        sub_tenant_id: typing.Optional[str] = None,
-        embeddings: typing.Optional[typing.Dict[str, typing.Sequence[float]]] = OMIT,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> SingleUploadData:
-        """
-        Update existing embeddings with new vector representations.
-
-        This endpoint allows you to modify embeddings that are already stored in your knowledge base. Provide updated vector representations for specific chunks of content, identified by their chunk IDs.
-
-        The system will replace the existing embeddings with your new ones, ensuring that similarity searches reflect the most current vector representations. Use this when you need to update embeddings due to model improvements or content changes.
-
-        Parameters
-        ----------
-        tenant_id : str
-            Unique identifier for the tenant/organization
-
-        sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
 
-        embeddings : typing.Optional[typing.Dict[str, typing.Sequence[float]]]
-            The embeddings of source you want to index
+class AsyncUploadClient:
+    def __init__(self, *, client_wrapper: AsyncClientWrapper):
+        self._raw_client = AsyncRawUploadClient(client_wrapper=client_wrapper)
 
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
+    @property
+    def with_raw_response(self) -> AsyncRawUploadClient:
+        """
+        Retrieves a raw implementation of this client that returns raw responses.
 
         Returns
         -------
-        SingleUploadData
-            Successful Response
-
-        Examples
-        --------
-        import asyncio
-
-        from usecortex-ai import AsyncCortexAI
-
-        client = AsyncCortexAI(token="YOUR_TOKEN", )
-        async def main() -> None:
-            await client.upload.update_embeddings(tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', )
-        asyncio.run(main())
+        AsyncRawUploadClient
         """
-        _response = await self._raw_client.update_embeddings(
-            tenant_id=tenant_id, sub_tenant_id=sub_tenant_id, embeddings=embeddings, request_options=request_options
-        )
-        return _response.data
+        return self._raw_client
 
-    async def scrape_webpage(
+    async def upload_document(
         self,
         *,
-        web_url: str,
+        files: typing.List[core.File],
         tenant_id: str,
-        sub_tenant_id: typing.Optional[str] = None,
-        file_id: typing.Optional[str] = None,
+        sub_tenant_id: typing.Optional[str] = OMIT,
+        upsert: typing.Optional[bool] = OMIT,
+        file_metadata: typing.Optional[str] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
-    ) -> SingleUploadData:
+    ) -> SourceUploadResponse:
         """
-        Extract and index content from web pages automatically.
-
-        This endpoint initiates web scraping for the specified URL, extracting the main content, text, and structure from the webpage. It's perfect for capturing articles, documentation, or any web content you want to include in your knowledge base.
-
-        The system processes the webpage content asynchronously, cleaning and structuring the information for optimal search and retrieval. Use this when you need to add web content without manual copying and pasting.
+        Upload one or more documents for ingestion.
+        Supports both single and batch uploads.
+        For single file: send one file with the 'files' field.
+        For batch: send multiple files with the 'files' field (FastAPI will parse as list).
 
         Parameters
         ----------
-        web_url : str
-            The URL of the webpage to scrape and index
+        files : typing.List[core.File]
+            See core.File for more documentation
 
         tenant_id : str
             Unique identifier for the tenant/organization
@@ -2021,15 +344,17 @@ class AsyncUploadClient:
         sub_tenant_id : typing.Optional[str]
             Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
 
-        file_id : typing.Optional[str]
-            Optional custom file ID for the scraped content. If not provided, a unique ID will be generated
+        upsert : typing.Optional[bool]
+
+        file_metadata : typing.Optional[str]
+            JSON Array of file metadata objects
 
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
         Returns
         -------
-        SingleUploadData
+        SourceUploadResponse
             Successful Response
 
         Examples
@@ -2040,41 +365,36 @@ class AsyncUploadClient:
 
         client = AsyncCortexAI(token="YOUR_TOKEN", )
         async def main() -> None:
-            await client.upload.scrape_webpage(web_url='https://www.usecortex.ai/', tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', file_id='CortexDoc1234', )
+            await client.upload.upload_document(tenant_id='tenant_id', )
         asyncio.run(main())
         """
-        _response = await self._raw_client.scrape_webpage(
-            web_url=web_url,
+        _response = await self._raw_client.upload_document(
+            files=files,
             tenant_id=tenant_id,
             sub_tenant_id=sub_tenant_id,
-            file_id=file_id,
+            upsert=upsert,
+            file_metadata=file_metadata,
             request_options=request_options,
         )
         return _response.data
 
-    async def update_webpage(
+    async def upload_app_sources(
         self,
         *,
-        web_url: str,
-        source_id: str,
+        app_sources: BodyUploadAppIngestionUploadAppPostAppSources,
         tenant_id: str,
-        sub_tenant_id: typing.Optional[str] = None,
+        sub_tenant_id: typing.Optional[str] = OMIT,
+        upsert: typing.Optional[bool] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
-    ) -> SingleUploadData:
+    ) -> AppSourcesUploadData:
         """
-        Update web scraping content with fresh data from the source URL.
-
-        This endpoint refreshes the content for an existing web scraping job. Provide the source ID of the webpage content you want to update, and the system will re-scrape the URL to capture any changes.
-
-        The updated content gets processed asynchronously and re-indexed in your knowledge base. Use this to keep web content current when the source pages are frequently updated.
+        Upload structured sources generated by first-party or third-party apps.
+        Supports both single and batch uploads.
 
         Parameters
         ----------
-        web_url : str
-            The URL of the webpage to re-scrape
-
-        source_id : str
-            The file ID of the existing web scraping job to update
+        app_sources : BodyUploadAppIngestionUploadAppPostAppSources
+            Single source object or list of structured source objects containing app-generated data to be indexed
 
         tenant_id : str
             Unique identifier for the tenant/organization
@@ -2082,55 +402,59 @@ class AsyncUploadClient:
         sub_tenant_id : typing.Optional[str]
             Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
 
+        upsert : typing.Optional[bool]
+            If true, update existing sources with the same source_id. Defaults to True.
+
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
         Returns
         -------
-        SingleUploadData
+        AppSourcesUploadData
             Successful Response
 
         Examples
         --------
         import asyncio
 
-        from usecortex-ai import AsyncCortexAI
+        from usecortex-ai import AsyncCortexAI, SourceModel
 
         client = AsyncCortexAI(token="YOUR_TOKEN", )
         async def main() -> None:
-            await client.upload.update_webpage(web_url='https://www.usecortex.ai/', source_id='CortexDoc1234', tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', )
+            await client.upload.upload_app_sources(app_sources=SourceModel(id='id', tenant_id='tenant_id', sub_tenant_id='sub_tenant_id', ), tenant_id='tenant_id', )
         asyncio.run(main())
         """
-        _response = await self._raw_client.update_webpage(
-            web_url=web_url,
-            source_id=source_id,
+        _response = await self._raw_client.upload_app_sources(
+            app_sources=app_sources,
             tenant_id=tenant_id,
             sub_tenant_id=sub_tenant_id,
+            upsert=upsert,
             request_options=request_options,
         )
         return _response.data
 
-    async def batch_scrape_webpage(
+    async def verify_processing(
         self,
         *,
-        tenant_id: str,
-        request: typing.Sequence[WebpageScrapeRequest],
+        file_id: str,
+        tenant_id: typing.Optional[str] = None,
         sub_tenant_id: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
-    ) -> BatchUploadData:
+    ) -> ProcessingStatus:
         """
-        Extract and index content from multiple web pages simultaneously.
+        Check the current processing status of your uploaded content.
 
-        This endpoint initiates web scraping for multiple URLs at once, extracting the main content, text, and structure from each webpage. It's perfect for capturing multiple articles, documentation pages, or any web content you want to include in your knowledge base.
+        This endpoint allows you to monitor the progress of documents, text, or other content you've uploaded. Simply provide the file ID to see whether processing is complete, still in progress, or if any errors occurred.
 
-        The system processes all webpage content asynchronously, cleaning and structuring the information for optimal search and retrieval.
+        Use this to determine when your content is ready for search and retrieval, or to troubleshoot any processing issues.
 
         Parameters
         ----------
-        tenant_id : str
-            Unique identifier for the tenant/organization
+        file_id : str
+            The file ID to check processing status for
 
-        request : typing.Sequence[WebpageScrapeRequest]
+        tenant_id : typing.Optional[str]
+            Unique identifier for the tenant/organization
 
         sub_tenant_id : typing.Optional[str]
             Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
@@ -2140,72 +464,92 @@ class AsyncUploadClient:
 
         Returns
         -------
-        BatchUploadData
+        ProcessingStatus
             Successful Response
 
         Examples
         --------
         import asyncio
 
-        from usecortex-ai import AsyncCortexAI, WebpageScrapeRequest
+        from usecortex-ai import AsyncCortexAI
 
         client = AsyncCortexAI(token="YOUR_TOKEN", )
         async def main() -> None:
-            await client.upload.batch_scrape_webpage(tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', request=[WebpageScrapeRequest(web_url='https://www.usecortex.ai/', )], )
+            await client.upload.verify_processing(file_id='file_id', )
         asyncio.run(main())
         """
-        _response = await self._raw_client.batch_scrape_webpage(
-            tenant_id=tenant_id, request=request, sub_tenant_id=sub_tenant_id, request_options=request_options
+        _response = await self._raw_client.verify_processing(
+            file_id=file_id, tenant_id=tenant_id, sub_tenant_id=sub_tenant_id, request_options=request_options
         )
         return _response.data
 
-    async def delete_source(
+    async def add_memory(
         self,
         *,
+        memories: typing.Sequence[MemoryItem],
         tenant_id: str,
-        source_ids: typing.Sequence[str],
         sub_tenant_id: typing.Optional[str] = OMIT,
+        upsert: typing.Optional[bool] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
-    ) -> typing.Optional[typing.Any]:
+    ) -> AddMemoryResponse:
         """
-        Remove documents and content from your knowledge base.
+        Add memories for indexing and retrieval.
+
+            This API provides a unified entry point for ingesting various types of content:
+
+            **Content Types Supported:**
+            - Raw text content (`text` field)
+            - Markdown formatted content (`text` + `is_markdown=true`)
+            - User/assistant conversation pairs (`user_assistant_pairs` field)
 
-        This endpoint permanently deletes the specified sources from your knowledge base. Once deleted, the content will no longer be available for search or retrieval.
+            **Key Features:**
+            - **Inference Mode (`infer=true`)**: When enabled, the system extracts additional
+              insights and implicit information from your content. Useful for conversation
+              analysis and knowledge extraction.
+            - **Direct Mode (`infer=false`)**: Content is chunked and indexed as-is without
+              additional processing.
 
-        Use this carefully as the action cannot be undone. The system will confirm successful deletion of each source ID you specify.
+            Use `/ingestion/verify-processing` endpoint to check the processing status.
 
         Parameters
         ----------
+        memories : typing.Sequence[MemoryItem]
+            List of memory items to ingest
+
         tenant_id : str
             Unique identifier for the tenant/organization
 
-        source_ids : typing.Sequence[str]
-            List of source IDs to delete
-
         sub_tenant_id : typing.Optional[str]
             Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
 
+        upsert : typing.Optional[bool]
+            If true, update existing sources with the same source_id.
+
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
         Returns
         -------
-        typing.Optional[typing.Any]
+        AddMemoryResponse
             Successful Response
 
         Examples
         --------
         import asyncio
 
-        from usecortex-ai import AsyncCortexAI
+        from usecortex-ai import AsyncCortexAI, MemoryItem
 
         client = AsyncCortexAI(token="YOUR_TOKEN", )
         async def main() -> None:
-            await client.upload.delete_source(tenant_id='tenant_1234', source_ids=['CortexDoc1234', 'CortexDoc4567'], )
+            await client.upload.add_memory(memories=[MemoryItem()], tenant_id='tenant_id', )
         asyncio.run(main())
         """
-        _response = await self._raw_client.delete_source(
-            tenant_id=tenant_id, source_ids=source_ids, sub_tenant_id=sub_tenant_id, request_options=request_options
+        _response = await self._raw_client.add_memory(
+            memories=memories,
+            tenant_id=tenant_id,
+            sub_tenant_id=sub_tenant_id,
+            upsert=upsert,
+            request_options=request_options,
         )
         return _response.data
 
@@ -2213,34 +557,36 @@ class AsyncUploadClient:
         self,
         *,
         tenant_id: str,
-        source_ids: typing.Sequence[str],
-        sub_tenant_id: typing.Optional[str] = OMIT,
+        memory_id: str,
+        sub_tenant_id: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
-    ) -> typing.Optional[typing.Any]:
+    ) -> DeleteUserMemoryResponse:
         """
-        Remove documents and content from your knowledge base.
+        Permanently remove a specific memory from storage.
 
-        This endpoint permanently deletes the specified sources from your knowledge base. Once deleted, the content will no longer be available for search or retrieval.
+            This API allows you to delete a memory by its unique identifier.
+            Once deleted, the memory cannot be recovered, so use this operation carefully.
 
-        Use this carefully as the action cannot be undone. The system will confirm successful deletion of each source ID you specify.
+            The memory will be removed from your tenant's storage and will no longer
+            appear in search results or memory listings.
 
         Parameters
         ----------
         tenant_id : str
-            Unique identifier for the tenant/organization
+            Tenant ID
 
-        source_ids : typing.Sequence[str]
-            List of source IDs to delete
+        memory_id : str
+            Unique identifier of the memory to delete
 
         sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
+            Sub-tenant ID
 
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
         Returns
         -------
-        typing.Optional[typing.Any]
+        DeleteUserMemoryResponse
             Successful Response
 
         Examples
@@ -2251,60 +597,10 @@ class AsyncUploadClient:
 
         client = AsyncCortexAI(token="YOUR_TOKEN", )
         async def main() -> None:
-            await client.upload.delete_memory(tenant_id='tenant_1234', source_ids=['CortexDoc1234', 'CortexDoc4567'], )
+            await client.upload.delete_memory(tenant_id='tenant_id', memory_id='memory_id', )
         asyncio.run(main())
         """
         _response = await self._raw_client.delete_memory(
-            tenant_id=tenant_id, source_ids=source_ids, sub_tenant_id=sub_tenant_id, request_options=request_options
-        )
-        return _response.data
-
-    async def verify_processing(
-        self,
-        *,
-        file_id: str,
-        tenant_id: typing.Optional[str] = None,
-        sub_tenant_id: typing.Optional[str] = None,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> ProcessingStatus:
-        """
-        Check the current processing status of your uploaded content.
-
-        This endpoint allows you to monitor the progress of documents, text, or other content you've uploaded. Simply provide the file ID to see whether processing is complete, still in progress, or if any errors occurred.
-
-        Use this to determine when your content is ready for search and retrieval, or to troubleshoot any processing issues.
-
-        Parameters
-        ----------
-        file_id : str
-            The file ID to check processing status for
-
-        tenant_id : typing.Optional[str]
-            Unique identifier for the tenant/organization
-
-        sub_tenant_id : typing.Optional[str]
-            Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        ProcessingStatus
-            Successful Response
-
-        Examples
-        --------
-        import asyncio
-
-        from usecortex-ai import AsyncCortexAI
-
-        client = AsyncCortexAI(token="YOUR_TOKEN", )
-        async def main() -> None:
-            await client.upload.verify_processing(file_id='CortexDoc1234', tenant_id='tenant_1234', )
-        asyncio.run(main())
-        """
-        _response = await self._raw_client.verify_processing(
-            file_id=file_id, tenant_id=tenant_id, sub_tenant_id=sub_tenant_id, request_options=request_options
+            tenant_id=tenant_id, memory_id=memory_id, sub_tenant_id=sub_tenant_id, request_options=request_options
         )
         return _response.data