groundx 2.3.6__tar.gz → 2.3.8__tar.gz

{groundx-2.3.6 → groundx-2.3.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: groundx
-Version: 2.3.6
+Version: 2.3.8
 Summary: 
 License: MIT
 Requires-Python: >=3.8,<4.0

{groundx-2.3.6 → groundx-2.3.8}/pyproject.toml

@@ -3,7 +3,7 @@ name = "groundx"
 
 [tool.poetry]
 name = "groundx"
-version = "2.3.6"
+version = "2.3.8"
 description = ""
 readme = "README.md"
 authors = []

{groundx-2.3.6 → groundx-2.3.8}/src/groundx/core/client_wrapper.py

@@ -14,10 +14,10 @@ class BaseClientWrapper:
 
     def get_headers(self) -> typing.Dict[str, str]:
         headers: typing.Dict[str, str] = {
-            "User-Agent": "groundx/2.3.6",
+            "User-Agent": "groundx/2.3.8",
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "groundx",
-            "X-Fern-SDK-Version": "2.3.6",
+            "X-Fern-SDK-Version": "2.3.8",
         }
         headers["X-API-Key"] = self.api_key
         return headers

{groundx-2.3.6 → groundx-2.3.8}/src/groundx/documents/client.py

@@ -40,6 +40,8 @@ class DocumentsClient:
         self,
         *,
         documents: typing.Sequence[IngestRemoteDocument],
+        callback_url: typing.Optional[str] = OMIT,
+        callback_data: typing.Optional[str] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> IngestResponse:
         """
@@ -51,6 +53,12 @@ class DocumentsClient:
         ----------
         documents : typing.Sequence[IngestRemoteDocument]
 
+        callback_url : typing.Optional[str]
+            An endpoint that will receive processing event updates as POST.
+
+        callback_data : typing.Optional[str]
+            A string that is returned, along with processing event updates, to the callback URL.
+
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
@@ -77,7 +85,9 @@ class DocumentsClient:
             ],
         )
         """
-        _response = self._raw_client.ingest_remote(documents=documents, request_options=request_options)
+        _response = self._raw_client.ingest_remote(
+            documents=documents, callback_url=callback_url, callback_data=callback_data, request_options=request_options
+        )
         return _response.data
 
     def ingest_local(
@@ -124,7 +134,12 @@ class DocumentsClient:
         return _response.data
 
     def crawl_website(
-        self, *, websites: typing.Sequence[WebsiteSource], request_options: typing.Optional[RequestOptions] = None
+        self,
+        *,
+        websites: typing.Sequence[WebsiteSource],
+        callback_url: typing.Optional[str] = OMIT,
+        callback_data: typing.Optional[str] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
     ) -> IngestResponse:
         """
         Upload the content of a publicly accessible website for ingestion into a GroundX bucket. This is done by following links within a specified URL, recursively, up to a specified depth or number of pages.
@@ -138,6 +153,12 @@ class DocumentsClient:
         ----------
         websites : typing.Sequence[WebsiteSource]
 
+        callback_url : typing.Optional[str]
+            The URL that will receive processing event updates.
+
+        callback_data : typing.Optional[str]
+            A string that is returned, along with processing event updates, to the callback URL.
+
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
@@ -165,7 +186,9 @@ class DocumentsClient:
             ],
         )
         """
-        _response = self._raw_client.crawl_website(websites=websites, request_options=request_options)
+        _response = self._raw_client.crawl_website(
+            websites=websites, callback_url=callback_url, callback_data=callback_data, request_options=request_options
+        )
         return _response.data
 
     def list(
@@ -490,6 +513,8 @@ class AsyncDocumentsClient:
         self,
         *,
         documents: typing.Sequence[IngestRemoteDocument],
+        callback_url: typing.Optional[str] = OMIT,
+        callback_data: typing.Optional[str] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> IngestResponse:
         """
@@ -501,6 +526,12 @@ class AsyncDocumentsClient:
         ----------
         documents : typing.Sequence[IngestRemoteDocument]
 
+        callback_url : typing.Optional[str]
+            An endpoint that will receive processing event updates as POST.
+
+        callback_data : typing.Optional[str]
+            A string that is returned, along with processing event updates, to the callback URL.
+
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
@@ -535,7 +566,9 @@ class AsyncDocumentsClient:
 
         asyncio.run(main())
         """
-        _response = await self._raw_client.ingest_remote(documents=documents, request_options=request_options)
+        _response = await self._raw_client.ingest_remote(
+            documents=documents, callback_url=callback_url, callback_data=callback_data, request_options=request_options
+        )
         return _response.data
 
     async def ingest_local(
@@ -594,7 +627,12 @@ class AsyncDocumentsClient:
         return _response.data
 
     async def crawl_website(
-        self, *, websites: typing.Sequence[WebsiteSource], request_options: typing.Optional[RequestOptions] = None
+        self,
+        *,
+        websites: typing.Sequence[WebsiteSource],
+        callback_url: typing.Optional[str] = OMIT,
+        callback_data: typing.Optional[str] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
     ) -> IngestResponse:
         """
         Upload the content of a publicly accessible website for ingestion into a GroundX bucket. This is done by following links within a specified URL, recursively, up to a specified depth or number of pages.
@@ -608,6 +646,12 @@ class AsyncDocumentsClient:
         ----------
         websites : typing.Sequence[WebsiteSource]
 
+        callback_url : typing.Optional[str]
+            The URL that will receive processing event updates.
+
+        callback_data : typing.Optional[str]
+            A string that is returned, along with processing event updates, to the callback URL.
+
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
@@ -643,7 +687,9 @@ class AsyncDocumentsClient:
 
         asyncio.run(main())
         """
-        _response = await self._raw_client.crawl_website(websites=websites, request_options=request_options)
+        _response = await self._raw_client.crawl_website(
+            websites=websites, callback_url=callback_url, callback_data=callback_data, request_options=request_options
+        )
         return _response.data
 
     async def list(

{groundx-2.3.6 → groundx-2.3.8}/src/groundx/documents/raw_client.py

@@ -36,6 +36,8 @@ class RawDocumentsClient:
         self,
         *,
         documents: typing.Sequence[IngestRemoteDocument],
+        callback_url: typing.Optional[str] = OMIT,
+        callback_data: typing.Optional[str] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> HttpResponse[IngestResponse]:
         """
@@ -47,6 +49,12 @@ class RawDocumentsClient:
         ----------
         documents : typing.Sequence[IngestRemoteDocument]
 
+        callback_url : typing.Optional[str]
+            An endpoint that will receive processing event updates as POST.
+
+        callback_data : typing.Optional[str]
+            A string that is returned, along with processing event updates, to the callback URL.
+
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
@@ -62,6 +70,8 @@ class RawDocumentsClient:
                 "documents": convert_and_respect_annotation_metadata(
                     object_=documents, annotation=typing.Sequence[IngestRemoteDocument], direction="write"
                 ),
+                "callbackUrl": callback_url,
+                "callbackData": callback_data,
             },
             headers={
                 "content-type": "application/json",
@@ -176,7 +186,12 @@ class RawDocumentsClient:
         raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
 
     def crawl_website(
-        self, *, websites: typing.Sequence[WebsiteSource], request_options: typing.Optional[RequestOptions] = None
+        self,
+        *,
+        websites: typing.Sequence[WebsiteSource],
+        callback_url: typing.Optional[str] = OMIT,
+        callback_data: typing.Optional[str] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
     ) -> HttpResponse[IngestResponse]:
         """
         Upload the content of a publicly accessible website for ingestion into a GroundX bucket. This is done by following links within a specified URL, recursively, up to a specified depth or number of pages.
@@ -190,6 +205,12 @@ class RawDocumentsClient:
         ----------
         websites : typing.Sequence[WebsiteSource]
 
+        callback_url : typing.Optional[str]
+            The URL that will receive processing event updates.
+
+        callback_data : typing.Optional[str]
+            A string that is returned, along with processing event updates, to the callback URL.
+
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
@@ -205,6 +226,8 @@ class RawDocumentsClient:
                 "websites": convert_and_respect_annotation_metadata(
                     object_=websites, annotation=typing.Sequence[WebsiteSource], direction="write"
                 ),
+                "callbackUrl": callback_url,
+                "callbackData": callback_data,
             },
             headers={
                 "content-type": "application/json",
@@ -724,6 +747,8 @@ class AsyncRawDocumentsClient:
         self,
         *,
         documents: typing.Sequence[IngestRemoteDocument],
+        callback_url: typing.Optional[str] = OMIT,
+        callback_data: typing.Optional[str] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> AsyncHttpResponse[IngestResponse]:
         """
@@ -735,6 +760,12 @@ class AsyncRawDocumentsClient:
         ----------
         documents : typing.Sequence[IngestRemoteDocument]
 
+        callback_url : typing.Optional[str]
+            An endpoint that will receive processing event updates as POST.
+
+        callback_data : typing.Optional[str]
+            A string that is returned, along with processing event updates, to the callback URL.
+
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
@@ -750,6 +781,8 @@ class AsyncRawDocumentsClient:
                 "documents": convert_and_respect_annotation_metadata(
                     object_=documents, annotation=typing.Sequence[IngestRemoteDocument], direction="write"
                 ),
+                "callbackUrl": callback_url,
+                "callbackData": callback_data,
             },
             headers={
                 "content-type": "application/json",
@@ -864,7 +897,12 @@ class AsyncRawDocumentsClient:
         raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
 
     async def crawl_website(
-        self, *, websites: typing.Sequence[WebsiteSource], request_options: typing.Optional[RequestOptions] = None
+        self,
+        *,
+        websites: typing.Sequence[WebsiteSource],
+        callback_url: typing.Optional[str] = OMIT,
+        callback_data: typing.Optional[str] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
     ) -> AsyncHttpResponse[IngestResponse]:
         """
         Upload the content of a publicly accessible website for ingestion into a GroundX bucket. This is done by following links within a specified URL, recursively, up to a specified depth or number of pages.
@@ -878,6 +916,12 @@ class AsyncRawDocumentsClient:
         ----------
         websites : typing.Sequence[WebsiteSource]
 
+        callback_url : typing.Optional[str]
+            The URL that will receive processing event updates.
+
+        callback_data : typing.Optional[str]
+            A string that is returned, along with processing event updates, to the callback URL.
+
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
@@ -893,6 +937,8 @@ class AsyncRawDocumentsClient:
                 "websites": convert_and_respect_annotation_metadata(
                     object_=websites, annotation=typing.Sequence[WebsiteSource], direction="write"
                 ),
+                "callbackUrl": callback_url,
+                "callbackData": callback_data,
             },
             headers={
                 "content-type": "application/json",

{groundx-2.3.6 → groundx-2.3.8}/src/groundx/ingest.py

@@ -111,6 +111,7 @@ def prep_documents(
                 bucket_id=document.bucket_id,
                 file_name=document.file_name,
                 file_type=document.file_type,
+                filter=document.filter,
                 process_level=document.process_level,
                 search_data=document.search_data,
                 source_url=document.file_path,
@@ -431,6 +432,7 @@ class GroundX(GroundXBase):
                         bucket_id=d.bucket_id,
                         file_name=fn,
                         file_type=ft,
+                        filter=d.filter,
                         process_level=d.process_level,
                         search_data=d.search_data,
                         source_url=url,
@@ -610,6 +612,7 @@ class AsyncGroundX(AsyncGroundXBase):
                         bucket_id=d.bucket_id,
                         file_name=fn,
                         file_type=ft,
+                        filter=d.filter,
                         process_level=d.process_level,
                         search_data=d.search_data,
                         source_url=url,