usecortex-ai 0.3.4__py3-none-any.whl → 0.3.5__py3-none-any.whl

usecortex_ai/types/webpage_scrape_request.py

@@ -0,0 +1,27 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+
+
+class WebpageScrapeRequest(UniversalBaseModel):
+    web_url: str = pydantic.Field()
+    """
+    The URL of the webpage to scrape and index
+    """
+
+    file_id: typing.Optional[str] = pydantic.Field(default=None)
+    """
+    Optional custom file ID for the scraped content. If not provided, a unique ID will be generated
+    """
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

usecortex_ai/upload/client.py

@@ -7,9 +7,11 @@ from ..core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
 from ..core.request_options import RequestOptions
 from ..types.app_sources_upload_data import AppSourcesUploadData
 from ..types.batch_upload_data import BatchUploadData
+from ..types.markdown_upload_request import MarkdownUploadRequest
 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 .raw_client import AsyncRawUploadClient, RawUploadClient
 
 # this is used as the default value for optional parameters
@@ -646,6 +648,92 @@ class UploadClient:
         )
         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,
         *,
@@ -854,6 +942,51 @@ class UploadClient:
         )
         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,
         *,
@@ -1659,6 +1792,100 @@ class AsyncUploadClient:
         )
         return _response.data
 
+    async 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
+        --------
+        import asyncio
+
+        from usecortex-ai import AsyncCortexAI, MarkdownUploadRequest
+
+        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())
+        """
+        _response = await 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
+
+    async 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
+        --------
+        import asyncio
+
+        from usecortex-ai import AsyncCortexAI, MarkdownUploadRequest
+
+        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())
+        """
+        _response = await 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
+
     async def upload_embeddings(
         self,
         *,
@@ -1883,6 +2110,55 @@ class AsyncUploadClient:
         )
         return _response.data
 
+    async 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
+        --------
+        import asyncio
+
+        from usecortex-ai import AsyncCortexAI, WebpageScrapeRequest
+
+        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/', )], )
+        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
+        )
+        return _response.data
+
     async def delete_source(
         self,
         *,