llama-cloud 0.1.18__py3-none-any.whl → 0.1.20__py3-none-any.whl

llama_cloud/resources/parsing/client.py

@@ -9,6 +9,7 @@ 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.fail_page_mode import FailPageMode
 from ...types.http_validation_error import HttpValidationError
 from ...types.llama_parse_supported_file_extensions import LlamaParseSupportedFileExtensions
 from ...types.parser_languages import ParserLanguages
@@ -203,6 +204,7 @@ class ParsingClient:
         auto_mode_trigger_on_table_in_page: bool,
         auto_mode_trigger_on_text_in_page: str,
         auto_mode_trigger_on_regexp_in_page: str,
+        auto_mode_configuration_json: str,
         azure_openai_api_version: str,
         azure_openai_deployment_name: str,
         azure_openai_endpoint: str,
@@ -250,6 +252,10 @@ class ParsingClient:
         webhook_url: str,
         preset: str,
         parse_mode: typing.Optional[ParsingMode] = OMIT,
+        page_error_tolerance: float,
+        replace_failed_page_mode: typing.Optional[FailPageMode] = OMIT,
+        replace_failed_page_with_error_message_prefix: str,
+        replace_failed_page_with_error_message_suffix: str,
         system_prompt: str,
         system_prompt_append: str,
         user_prompt: str,
@@ -259,8 +265,10 @@ class ParsingClient:
         strict_mode_image_ocr: bool,
         strict_mode_reconstruction: bool,
         strict_mode_buggy_font: bool,
+        save_images: bool,
         ignore_document_elements_for_layout_detection: bool,
         output_tables_as_html: bool,
+        markdown_table_multiline_header_separator: str,
         use_vendor_multimodal_model: bool,
         bounding_box: str,
         gpt_4_o_mode: bool,
@@ -275,8 +283,6 @@ class ParsingClient:
         formatting_instruction: str,
     ) -> ParsingJob:
         """
-        Upload a file to s3 and create a job. return a job id
-
         Parameters:
             - organization_id: typing.Optional[str].
 
@@ -298,6 +304,8 @@ class ParsingClient:
 
             - auto_mode_trigger_on_regexp_in_page: str.
 
+            - auto_mode_configuration_json: str.
+
             - azure_openai_api_version: str.
 
             - azure_openai_deployment_name: str.
@@ -392,6 +400,14 @@ class ParsingClient:
 
             - parse_mode: typing.Optional[ParsingMode].
 
+            - page_error_tolerance: float.
+
+            - replace_failed_page_mode: typing.Optional[FailPageMode].
+
+            - replace_failed_page_with_error_message_prefix: str.
+
+            - replace_failed_page_with_error_message_suffix: str.
+
             - system_prompt: str.
 
             - system_prompt_append: str.
@@ -410,10 +426,14 @@ class ParsingClient:
 
             - strict_mode_buggy_font: bool.
 
+            - save_images: bool.
+
             - ignore_document_elements_for_layout_detection: bool.
 
             - output_tables_as_html: bool.
 
+            - markdown_table_multiline_header_separator: str.
+
             - use_vendor_multimodal_model: bool.
 
             - bounding_box: str.
@@ -446,6 +466,7 @@ class ParsingClient:
             "auto_mode_trigger_on_table_in_page": auto_mode_trigger_on_table_in_page,
             "auto_mode_trigger_on_text_in_page": auto_mode_trigger_on_text_in_page,
             "auto_mode_trigger_on_regexp_in_page": auto_mode_trigger_on_regexp_in_page,
+            "auto_mode_configuration_json": auto_mode_configuration_json,
             "azure_openai_api_version": azure_openai_api_version,
             "azure_openai_deployment_name": azure_openai_deployment_name,
             "azure_openai_endpoint": azure_openai_endpoint,
@@ -491,6 +512,9 @@ class ParsingClient:
             "model": model,
             "webhook_url": webhook_url,
             "preset": preset,
+            "page_error_tolerance": page_error_tolerance,
+            "replace_failed_page_with_error_message_prefix": replace_failed_page_with_error_message_prefix,
+            "replace_failed_page_with_error_message_suffix": replace_failed_page_with_error_message_suffix,
             "system_prompt": system_prompt,
             "system_prompt_append": system_prompt_append,
             "user_prompt": user_prompt,
@@ -500,8 +524,10 @@ class ParsingClient:
             "strict_mode_image_ocr": strict_mode_image_ocr,
             "strict_mode_reconstruction": strict_mode_reconstruction,
             "strict_mode_buggy_font": strict_mode_buggy_font,
+            "save_images": save_images,
             "ignore_document_elements_for_layout_detection": ignore_document_elements_for_layout_detection,
             "output_tables_as_HTML": output_tables_as_html,
+            "markdown_table_multiline_header_separator": markdown_table_multiline_header_separator,
             "use_vendor_multimodal_model": use_vendor_multimodal_model,
             "bounding_box": bounding_box,
             "gpt4o_mode": gpt_4_o_mode,
@@ -521,6 +547,8 @@ class ParsingClient:
             _request["max_pages"] = max_pages
         if parse_mode is not OMIT:
             _request["parse_mode"] = parse_mode
+        if replace_failed_page_mode is not OMIT:
+            _request["replace_failed_page_mode"] = replace_failed_page_mode
         _response = self._client_wrapper.httpx_client.request(
             "POST",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/parsing/upload"),
@@ -571,6 +599,38 @@ 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_parameters(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_parameters(
+            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}/parameters"),
+            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_parsing_job_details(self, job_id: str) -> typing.Any:
         """
         Get a job by id
@@ -1155,6 +1215,7 @@ class AsyncParsingClient:
         auto_mode_trigger_on_table_in_page: bool,
         auto_mode_trigger_on_text_in_page: str,
         auto_mode_trigger_on_regexp_in_page: str,
+        auto_mode_configuration_json: str,
         azure_openai_api_version: str,
         azure_openai_deployment_name: str,
         azure_openai_endpoint: str,
@@ -1202,6 +1263,10 @@ class AsyncParsingClient:
         webhook_url: str,
         preset: str,
         parse_mode: typing.Optional[ParsingMode] = OMIT,
+        page_error_tolerance: float,
+        replace_failed_page_mode: typing.Optional[FailPageMode] = OMIT,
+        replace_failed_page_with_error_message_prefix: str,
+        replace_failed_page_with_error_message_suffix: str,
         system_prompt: str,
         system_prompt_append: str,
         user_prompt: str,
@@ -1211,8 +1276,10 @@ class AsyncParsingClient:
         strict_mode_image_ocr: bool,
         strict_mode_reconstruction: bool,
         strict_mode_buggy_font: bool,
+        save_images: bool,
         ignore_document_elements_for_layout_detection: bool,
         output_tables_as_html: bool,
+        markdown_table_multiline_header_separator: str,
         use_vendor_multimodal_model: bool,
         bounding_box: str,
         gpt_4_o_mode: bool,
@@ -1227,8 +1294,6 @@ class AsyncParsingClient:
         formatting_instruction: str,
     ) -> ParsingJob:
         """
-        Upload a file to s3 and create a job. return a job id
-
         Parameters:
             - organization_id: typing.Optional[str].
 
@@ -1250,6 +1315,8 @@ class AsyncParsingClient:
 
             - auto_mode_trigger_on_regexp_in_page: str.
 
+            - auto_mode_configuration_json: str.
+
             - azure_openai_api_version: str.
 
             - azure_openai_deployment_name: str.
@@ -1344,6 +1411,14 @@ class AsyncParsingClient:
 
             - parse_mode: typing.Optional[ParsingMode].
 
+            - page_error_tolerance: float.
+
+            - replace_failed_page_mode: typing.Optional[FailPageMode].
+
+            - replace_failed_page_with_error_message_prefix: str.
+
+            - replace_failed_page_with_error_message_suffix: str.
+
             - system_prompt: str.
 
             - system_prompt_append: str.
@@ -1362,10 +1437,14 @@ class AsyncParsingClient:
 
             - strict_mode_buggy_font: bool.
 
+            - save_images: bool.
+
             - ignore_document_elements_for_layout_detection: bool.
 
             - output_tables_as_html: bool.
 
+            - markdown_table_multiline_header_separator: str.
+
             - use_vendor_multimodal_model: bool.
 
             - bounding_box: str.
@@ -1398,6 +1477,7 @@ class AsyncParsingClient:
             "auto_mode_trigger_on_table_in_page": auto_mode_trigger_on_table_in_page,
             "auto_mode_trigger_on_text_in_page": auto_mode_trigger_on_text_in_page,
             "auto_mode_trigger_on_regexp_in_page": auto_mode_trigger_on_regexp_in_page,
+            "auto_mode_configuration_json": auto_mode_configuration_json,
             "azure_openai_api_version": azure_openai_api_version,
             "azure_openai_deployment_name": azure_openai_deployment_name,
             "azure_openai_endpoint": azure_openai_endpoint,
@@ -1443,6 +1523,9 @@ class AsyncParsingClient:
             "model": model,
             "webhook_url": webhook_url,
             "preset": preset,
+            "page_error_tolerance": page_error_tolerance,
+            "replace_failed_page_with_error_message_prefix": replace_failed_page_with_error_message_prefix,
+            "replace_failed_page_with_error_message_suffix": replace_failed_page_with_error_message_suffix,
             "system_prompt": system_prompt,
             "system_prompt_append": system_prompt_append,
             "user_prompt": user_prompt,
@@ -1452,8 +1535,10 @@ class AsyncParsingClient:
             "strict_mode_image_ocr": strict_mode_image_ocr,
             "strict_mode_reconstruction": strict_mode_reconstruction,
             "strict_mode_buggy_font": strict_mode_buggy_font,
+            "save_images": save_images,
             "ignore_document_elements_for_layout_detection": ignore_document_elements_for_layout_detection,
             "output_tables_as_HTML": output_tables_as_html,
+            "markdown_table_multiline_header_separator": markdown_table_multiline_header_separator,
             "use_vendor_multimodal_model": use_vendor_multimodal_model,
             "bounding_box": bounding_box,
             "gpt4o_mode": gpt_4_o_mode,
@@ -1473,6 +1558,8 @@ class AsyncParsingClient:
             _request["max_pages"] = max_pages
         if parse_mode is not OMIT:
             _request["parse_mode"] = parse_mode
+        if replace_failed_page_mode is not OMIT:
+            _request["replace_failed_page_mode"] = replace_failed_page_mode
         _response = await self._client_wrapper.httpx_client.request(
             "POST",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/parsing/upload"),
@@ -1523,6 +1610,38 @@ 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_parameters(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_parameters(
+            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}/parameters"),
+            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_parsing_job_details(self, job_id: str) -> typing.Any:
         """
         Get a job by id

llama_cloud/resources/pipelines/client.py

@@ -12,9 +12,9 @@ from ...errors.unprocessable_entity_error import UnprocessableEntityError
 from ...types.chat_data import ChatData
 from ...types.cloud_document import CloudDocument
 from ...types.cloud_document_create import CloudDocumentCreate
-from ...types.configured_transformation_item import ConfiguredTransformationItem
 from ...types.data_sink_create import DataSinkCreate
 from ...types.eval_execution_params import EvalExecutionParams
+from ...types.file_count_by_status_response import FileCountByStatusResponse
 from ...types.http_validation_error import HttpValidationError
 from ...types.input_message import InputMessage
 from ...types.llama_parse_parameters import LlamaParseParameters
@@ -29,6 +29,7 @@ from ...types.pipeline_data_source_create import PipelineDataSourceCreate
 from ...types.pipeline_deployment import PipelineDeployment
 from ...types.pipeline_file import PipelineFile
 from ...types.pipeline_file_create import PipelineFileCreate
+from ...types.pipeline_metadata_config import PipelineMetadataConfig
 from ...types.pipeline_type import PipelineType
 from ...types.playground_session import PlaygroundSession
 from ...types.preset_retrieval_params import PresetRetrievalParams
@@ -209,13 +210,14 @@ class PipelinesClient:
         *,
         embedding_config: typing.Optional[PipelineUpdateEmbeddingConfig] = OMIT,
         transform_config: typing.Optional[PipelineUpdateTransformConfig] = OMIT,
-        configured_transformations: typing.Optional[typing.List[ConfiguredTransformationItem]] = OMIT,
         data_sink_id: typing.Optional[str] = OMIT,
         embedding_model_config_id: typing.Optional[str] = OMIT,
         data_sink: typing.Optional[DataSinkCreate] = OMIT,
         preset_retrieval_parameters: typing.Optional[PresetRetrievalParams] = OMIT,
         eval_parameters: typing.Optional[EvalExecutionParams] = OMIT,
         llama_parse_parameters: typing.Optional[LlamaParseParameters] = OMIT,
+        status: typing.Optional[str] = OMIT,
+        metadata_config: typing.Optional[PipelineMetadataConfig] = OMIT,
         name: typing.Optional[str] = OMIT,
         managed_pipeline_id: typing.Optional[str] = OMIT,
     ) -> Pipeline:
@@ -229,8 +231,6 @@ class PipelinesClient:
 
             - transform_config: typing.Optional[PipelineUpdateTransformConfig]. Configuration for the transformation.
 
-            - configured_transformations: typing.Optional[typing.List[ConfiguredTransformationItem]].
-
             - data_sink_id: typing.Optional[str].
 
             - embedding_model_config_id: typing.Optional[str].
@@ -243,6 +243,10 @@ class PipelinesClient:
 
             - llama_parse_parameters: typing.Optional[LlamaParseParameters].
 
+            - status: typing.Optional[str].
+
+            - metadata_config: typing.Optional[PipelineMetadataConfig].
+
             - name: typing.Optional[str].
 
             - managed_pipeline_id: typing.Optional[str].
@@ -252,8 +256,6 @@ class PipelinesClient:
             _request["embedding_config"] = embedding_config
         if transform_config is not OMIT:
             _request["transform_config"] = transform_config
-        if configured_transformations is not OMIT:
-            _request["configured_transformations"] = configured_transformations
         if data_sink_id is not OMIT:
             _request["data_sink_id"] = data_sink_id
         if embedding_model_config_id is not OMIT:
@@ -266,6 +268,10 @@ class PipelinesClient:
             _request["eval_parameters"] = eval_parameters
         if llama_parse_parameters is not OMIT:
             _request["llama_parse_parameters"] = llama_parse_parameters
+        if status is not OMIT:
+            _request["status"] = status
+        if metadata_config is not OMIT:
+            _request["metadata_config"] = metadata_config
         if name is not OMIT:
             _request["name"] = name
         if managed_pipeline_id is not OMIT:
@@ -559,6 +565,53 @@ class PipelinesClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    def get_pipeline_file_status_counts(
+        self,
+        pipeline_id: str,
+        *,
+        data_source_id: typing.Optional[str] = None,
+        only_manually_uploaded: typing.Optional[bool] = None,
+    ) -> FileCountByStatusResponse:
+        """
+        Get files for a pipeline.
+
+        Parameters:
+            - pipeline_id: str.
+
+            - data_source_id: typing.Optional[str].
+
+            - only_manually_uploaded: typing.Optional[bool].
+        ---
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.pipelines.get_pipeline_file_status_counts(
+            pipeline_id="string",
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/pipelines/{pipeline_id}/files/status-counts"
+            ),
+            params=remove_none_from_dict(
+                {"data_source_id": data_source_id, "only_manually_uploaded": only_manually_uploaded}
+            ),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(FileCountByStatusResponse, _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_pipeline_file_status(self, file_id: str, pipeline_id: str) -> ManagedIngestionStatusResponse:
         """
         Get status of a file for a pipeline.
@@ -1764,13 +1817,14 @@ class AsyncPipelinesClient:
         *,
         embedding_config: typing.Optional[PipelineUpdateEmbeddingConfig] = OMIT,
         transform_config: typing.Optional[PipelineUpdateTransformConfig] = OMIT,
-        configured_transformations: typing.Optional[typing.List[ConfiguredTransformationItem]] = OMIT,
         data_sink_id: typing.Optional[str] = OMIT,
         embedding_model_config_id: typing.Optional[str] = OMIT,
         data_sink: typing.Optional[DataSinkCreate] = OMIT,
         preset_retrieval_parameters: typing.Optional[PresetRetrievalParams] = OMIT,
         eval_parameters: typing.Optional[EvalExecutionParams] = OMIT,
         llama_parse_parameters: typing.Optional[LlamaParseParameters] = OMIT,
+        status: typing.Optional[str] = OMIT,
+        metadata_config: typing.Optional[PipelineMetadataConfig] = OMIT,
         name: typing.Optional[str] = OMIT,
         managed_pipeline_id: typing.Optional[str] = OMIT,
     ) -> Pipeline:
@@ -1784,8 +1838,6 @@ class AsyncPipelinesClient:
 
             - transform_config: typing.Optional[PipelineUpdateTransformConfig]. Configuration for the transformation.
 
-            - configured_transformations: typing.Optional[typing.List[ConfiguredTransformationItem]].
-
             - data_sink_id: typing.Optional[str].
 
             - embedding_model_config_id: typing.Optional[str].
@@ -1798,6 +1850,10 @@ class AsyncPipelinesClient:
 
             - llama_parse_parameters: typing.Optional[LlamaParseParameters].
 
+            - status: typing.Optional[str].
+
+            - metadata_config: typing.Optional[PipelineMetadataConfig].
+
             - name: typing.Optional[str].
 
             - managed_pipeline_id: typing.Optional[str].
@@ -1807,8 +1863,6 @@ class AsyncPipelinesClient:
             _request["embedding_config"] = embedding_config
         if transform_config is not OMIT:
             _request["transform_config"] = transform_config
-        if configured_transformations is not OMIT:
-            _request["configured_transformations"] = configured_transformations
         if data_sink_id is not OMIT:
             _request["data_sink_id"] = data_sink_id
         if embedding_model_config_id is not OMIT:
@@ -1821,6 +1875,10 @@ class AsyncPipelinesClient:
             _request["eval_parameters"] = eval_parameters
         if llama_parse_parameters is not OMIT:
             _request["llama_parse_parameters"] = llama_parse_parameters
+        if status is not OMIT:
+            _request["status"] = status
+        if metadata_config is not OMIT:
+            _request["metadata_config"] = metadata_config
         if name is not OMIT:
             _request["name"] = name
         if managed_pipeline_id is not OMIT:
@@ -2114,6 +2172,53 @@ class AsyncPipelinesClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    async def get_pipeline_file_status_counts(
+        self,
+        pipeline_id: str,
+        *,
+        data_source_id: typing.Optional[str] = None,
+        only_manually_uploaded: typing.Optional[bool] = None,
+    ) -> FileCountByStatusResponse:
+        """
+        Get files for a pipeline.
+
+        Parameters:
+            - pipeline_id: str.
+
+            - data_source_id: typing.Optional[str].
+
+            - only_manually_uploaded: typing.Optional[bool].
+        ---
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.pipelines.get_pipeline_file_status_counts(
+            pipeline_id="string",
+        )
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/pipelines/{pipeline_id}/files/status-counts"
+            ),
+            params=remove_none_from_dict(
+                {"data_source_id": data_source_id, "only_manually_uploaded": only_manually_uploaded}
+            ),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(FileCountByStatusResponse, _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_pipeline_file_status(self, file_id: str, pipeline_id: str) -> ManagedIngestionStatusResponse:
         """
         Get status of a file for a pipeline.