llama-cloud 0.1.4__py3-none-any.whl → 0.1.5__py3-none-any.whl

llama_cloud/resources/organizations/client.py

@@ -10,6 +10,7 @@ from ...core.jsonable_encoder import jsonable_encoder
 from ...core.remove_none_from_dict import remove_none_from_dict
 from ...errors.unprocessable_entity_error import UnprocessableEntityError
 from ...types.http_validation_error import HttpValidationError
+from ...types.interval_usage_and_plan import IntervalUsageAndPlan
 from ...types.organization import Organization
 from ...types.organization_create import OrganizationCreate
 from ...types.project import Project
@@ -298,6 +299,38 @@ class OrganizationsClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    def get_organization_usage(self, organization_id: typing.Optional[str]) -> IntervalUsageAndPlan:
+        """
+        Get usage for a project
+
+        Parameters:
+            - organization_id: typing.Optional[str].
+        ---
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.organizations.get_organization_usage()
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/organizations/{organization_id}/usage"
+            ),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(IntervalUsageAndPlan, _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
     def list_organization_users(self, organization_id: str) -> typing.List[UserOrganization]:
         """
         Get all users in an organization.
@@ -959,6 +992,38 @@ class AsyncOrganizationsClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    async def get_organization_usage(self, organization_id: typing.Optional[str]) -> IntervalUsageAndPlan:
+        """
+        Get usage for a project
+
+        Parameters:
+            - organization_id: typing.Optional[str].
+        ---
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.organizations.get_organization_usage()
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/organizations/{organization_id}/usage"
+            ),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(IntervalUsageAndPlan, _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
     async def list_organization_users(self, organization_id: str) -> typing.List[UserOrganization]:
         """
         Get all users in an organization.

llama_cloud/resources/parsing/client.py

@@ -7,6 +7,7 @@ from json.decoder import JSONDecodeError
 from ...core.api_error import ApiError
 from ...core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
 from ...core.jsonable_encoder import jsonable_encoder
+from ...core.remove_none_from_dict import remove_none_from_dict
 from ...errors.unprocessable_entity_error import UnprocessableEntityError
 from ...types.http_validation_error import HttpValidationError
 from ...types.llama_parse_supported_file_extensions import LlamaParseSupportedFileExtensions
@@ -101,6 +102,8 @@ class ParsingClient:
     def upload_file(
         self,
         *,
+        project_id: typing.Optional[str] = None,
+        organization_id: typing.Optional[str] = None,
         language: typing.List[ParserLanguages],
         parsing_instruction: str,
         skip_diagonal_text: bool,
@@ -112,6 +115,7 @@ class ParsingClient:
         continuous_mode: bool,
         gpt_4_o_api_key: str,
         do_not_unroll_columns: bool,
+        guess_xlsx_sheet_name: bool,
         page_separator: str,
         bounding_box: str,
         target_pages: str,
@@ -126,18 +130,30 @@ class ParsingClient:
         disable_ocr: bool,
         annotate_links: bool,
         disable_reconstruction: bool,
+        disable_image_extraction: bool,
         input_s_3_path: str,
         output_s_3_path_prefix: str,
         azure_openai_deployment_name: str,
         azure_openai_endpoint: str,
         azure_openai_api_version: str,
         azure_openai_key: str,
+        auto_mode: bool,
+        auto_mode_trigger_on_regexp_in_page: str,
+        auto_mode_trigger_on_text_in_page: str,
+        auto_mode_trigger_on_table_in_page: bool,
+        auto_mode_trigger_on_image_in_page: bool,
         file: typing.Optional[str] = OMIT,
+        input_url: str,
+        http_proxy: str,
     ) -> ParsingJob:
         """
         Upload a file to s3 and create a job. return a job id
 
         Parameters:
+            - project_id: typing.Optional[str].
+
+            - organization_id: typing.Optional[str].
+
             - language: typing.List[ParserLanguages].
 
             - parsing_instruction: str.
@@ -160,6 +176,8 @@ class ParsingClient:
 
             - do_not_unroll_columns: bool.
 
+            - guess_xlsx_sheet_name: bool.
+
             - page_separator: str.
 
             - bounding_box: str.
@@ -188,6 +206,8 @@ class ParsingClient:
 
             - disable_reconstruction: bool.
 
+            - disable_image_extraction: bool.
+
             - input_s_3_path: str.
 
             - output_s_3_path_prefix: str.
@@ -200,7 +220,21 @@ class ParsingClient:
 
             - azure_openai_key: str.
 
+            - auto_mode: bool.
+
+            - auto_mode_trigger_on_regexp_in_page: str.
+
+            - auto_mode_trigger_on_text_in_page: str.
+
+            - auto_mode_trigger_on_table_in_page: bool.
+
+            - auto_mode_trigger_on_image_in_page: bool.
+
             - file: typing.Optional[str].
+
+            - input_url: str.
+
+            - http_proxy: str.
         """
         _request: typing.Dict[str, typing.Any] = {
             "language": language,
@@ -214,6 +248,7 @@ class ParsingClient:
             "continuous_mode": continuous_mode,
             "gpt4o_api_key": gpt_4_o_api_key,
             "do_not_unroll_columns": do_not_unroll_columns,
+            "guess_xlsx_sheet_name": guess_xlsx_sheet_name,
             "page_separator": page_separator,
             "bounding_box": bounding_box,
             "target_pages": target_pages,
@@ -228,18 +263,27 @@ class ParsingClient:
             "disable_ocr": disable_ocr,
             "annotate_links": annotate_links,
             "disable_reconstruction": disable_reconstruction,
+            "disable_image_extraction": disable_image_extraction,
             "input_s3_path": input_s_3_path,
             "output_s3_path_prefix": output_s_3_path_prefix,
             "azure_openai_deployment_name": azure_openai_deployment_name,
             "azure_openai_endpoint": azure_openai_endpoint,
             "azure_openai_api_version": azure_openai_api_version,
             "azure_openai_key": azure_openai_key,
+            "auto_mode": auto_mode,
+            "auto_mode_trigger_on_regexp_in_page": auto_mode_trigger_on_regexp_in_page,
+            "auto_mode_trigger_on_text_in_page": auto_mode_trigger_on_text_in_page,
+            "auto_mode_trigger_on_table_in_page": auto_mode_trigger_on_table_in_page,
+            "auto_mode_trigger_on_image_in_page": auto_mode_trigger_on_image_in_page,
+            "input_url": input_url,
+            "http_proxy": http_proxy,
         }
         if file is not OMIT:
             _request["file"] = file
         _response = self._client_wrapper.httpx_client.request(
             "POST",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/parsing/upload"),
+            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
             json=jsonable_encoder(_request),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
@@ -256,6 +300,7 @@ class ParsingClient:
 
     def usage(self) -> ParsingUsage:
         """
+        DEPRECATED: use either /organizations/{organization_id}/usage or /projects/{project_id}/usage instead
         Get parsing usage for user
 
         ---
@@ -412,6 +457,40 @@ class ParsingClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    def get_job_raw_xlsx_result(self, job_id: str) -> typing.Any:
+        """
+        Get a job by id
+
+        Parameters:
+            - job_id: str.
+        ---
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.parsing.get_job_raw_xlsx_result(
+            job_id="string",
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/raw/xlsx"
+            ),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(typing.Any, _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
     def get_job_result(self, job_id: str) -> ParsingJobMarkdownResult:
         """
         Get a job by id
@@ -682,6 +761,8 @@ class AsyncParsingClient:
     async def upload_file(
         self,
         *,
+        project_id: typing.Optional[str] = None,
+        organization_id: typing.Optional[str] = None,
         language: typing.List[ParserLanguages],
         parsing_instruction: str,
         skip_diagonal_text: bool,
@@ -693,6 +774,7 @@ class AsyncParsingClient:
         continuous_mode: bool,
         gpt_4_o_api_key: str,
         do_not_unroll_columns: bool,
+        guess_xlsx_sheet_name: bool,
         page_separator: str,
         bounding_box: str,
         target_pages: str,
@@ -707,18 +789,30 @@ class AsyncParsingClient:
         disable_ocr: bool,
         annotate_links: bool,
         disable_reconstruction: bool,
+        disable_image_extraction: bool,
         input_s_3_path: str,
         output_s_3_path_prefix: str,
         azure_openai_deployment_name: str,
         azure_openai_endpoint: str,
         azure_openai_api_version: str,
         azure_openai_key: str,
+        auto_mode: bool,
+        auto_mode_trigger_on_regexp_in_page: str,
+        auto_mode_trigger_on_text_in_page: str,
+        auto_mode_trigger_on_table_in_page: bool,
+        auto_mode_trigger_on_image_in_page: bool,
         file: typing.Optional[str] = OMIT,
+        input_url: str,
+        http_proxy: str,
     ) -> ParsingJob:
         """
         Upload a file to s3 and create a job. return a job id
 
         Parameters:
+            - project_id: typing.Optional[str].
+
+            - organization_id: typing.Optional[str].
+
             - language: typing.List[ParserLanguages].
 
             - parsing_instruction: str.
@@ -741,6 +835,8 @@ class AsyncParsingClient:
 
             - do_not_unroll_columns: bool.
 
+            - guess_xlsx_sheet_name: bool.
+
             - page_separator: str.
 
             - bounding_box: str.
@@ -769,6 +865,8 @@ class AsyncParsingClient:
 
             - disable_reconstruction: bool.
 
+            - disable_image_extraction: bool.
+
             - input_s_3_path: str.
 
             - output_s_3_path_prefix: str.
@@ -781,7 +879,21 @@ class AsyncParsingClient:
 
             - azure_openai_key: str.
 
+            - auto_mode: bool.
+
+            - auto_mode_trigger_on_regexp_in_page: str.
+
+            - auto_mode_trigger_on_text_in_page: str.
+
+            - auto_mode_trigger_on_table_in_page: bool.
+
+            - auto_mode_trigger_on_image_in_page: bool.
+
             - file: typing.Optional[str].
+
+            - input_url: str.
+
+            - http_proxy: str.
         """
         _request: typing.Dict[str, typing.Any] = {
             "language": language,
@@ -795,6 +907,7 @@ class AsyncParsingClient:
             "continuous_mode": continuous_mode,
             "gpt4o_api_key": gpt_4_o_api_key,
             "do_not_unroll_columns": do_not_unroll_columns,
+            "guess_xlsx_sheet_name": guess_xlsx_sheet_name,
             "page_separator": page_separator,
             "bounding_box": bounding_box,
             "target_pages": target_pages,
@@ -809,18 +922,27 @@ class AsyncParsingClient:
             "disable_ocr": disable_ocr,
             "annotate_links": annotate_links,
             "disable_reconstruction": disable_reconstruction,
+            "disable_image_extraction": disable_image_extraction,
             "input_s3_path": input_s_3_path,
             "output_s3_path_prefix": output_s_3_path_prefix,
             "azure_openai_deployment_name": azure_openai_deployment_name,
             "azure_openai_endpoint": azure_openai_endpoint,
             "azure_openai_api_version": azure_openai_api_version,
             "azure_openai_key": azure_openai_key,
+            "auto_mode": auto_mode,
+            "auto_mode_trigger_on_regexp_in_page": auto_mode_trigger_on_regexp_in_page,
+            "auto_mode_trigger_on_text_in_page": auto_mode_trigger_on_text_in_page,
+            "auto_mode_trigger_on_table_in_page": auto_mode_trigger_on_table_in_page,
+            "auto_mode_trigger_on_image_in_page": auto_mode_trigger_on_image_in_page,
+            "input_url": input_url,
+            "http_proxy": http_proxy,
         }
         if file is not OMIT:
             _request["file"] = file
         _response = await self._client_wrapper.httpx_client.request(
             "POST",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/parsing/upload"),
+            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
             json=jsonable_encoder(_request),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
@@ -837,6 +959,7 @@ class AsyncParsingClient:
 
     async def usage(self) -> ParsingUsage:
         """
+        DEPRECATED: use either /organizations/{organization_id}/usage or /projects/{project_id}/usage instead
         Get parsing usage for user
 
         ---
@@ -993,6 +1116,40 @@ class AsyncParsingClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    async def get_job_raw_xlsx_result(self, job_id: str) -> typing.Any:
+        """
+        Get a job by id
+
+        Parameters:
+            - job_id: str.
+        ---
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.parsing.get_job_raw_xlsx_result(
+            job_id="string",
+        )
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/raw/xlsx"
+            ),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(typing.Any, _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
     async def get_job_result(self, job_id: str) -> ParsingJobMarkdownResult:
         """
         Get a job by id