llama-cloud 0.1.5__py3-none-any.whl → 0.1.7__py3-none-any.whl

llama_cloud/resources/parsing/client.py

@@ -16,6 +16,7 @@ from ...types.parsing_history_item import ParsingHistoryItem
 from ...types.parsing_job import ParsingJob
 from ...types.parsing_job_json_result import ParsingJobJsonResult
 from ...types.parsing_job_markdown_result import ParsingJobMarkdownResult
+from ...types.parsing_job_structured_result import ParsingJobStructuredResult
 from ...types.parsing_job_text_result import ParsingJobTextResult
 from ...types.parsing_usage import ParsingUsage
 from ...types.presigned_url import PresignedUrl
@@ -104,47 +105,61 @@ class ParsingClient:
         *,
         project_id: typing.Optional[str] = None,
         organization_id: typing.Optional[str] = None,
-        language: typing.List[ParserLanguages],
-        parsing_instruction: str,
-        skip_diagonal_text: bool,
-        invalidate_cache: bool,
-        do_not_cache: bool,
-        gpt_4_o_mode: bool,
-        fast_mode: bool,
-        premium_mode: bool,
+        file: typing.Optional[str] = OMIT,
+        annotate_links: bool,
+        auto_mode: bool,
+        auto_mode_trigger_on_image_in_page: bool,
+        auto_mode_trigger_on_table_in_page: bool,
+        auto_mode_trigger_on_text_in_page: str,
+        auto_mode_trigger_on_regexp_in_page: str,
+        azure_openai_api_version: str,
+        azure_openai_deployment_name: str,
+        azure_openai_endpoint: str,
+        azure_openai_key: str,
+        bbox_bottom: float,
+        bbox_left: float,
+        bbox_right: float,
+        bbox_top: float,
         continuous_mode: bool,
-        gpt_4_o_api_key: str,
+        disable_ocr: bool,
+        disable_reconstruction: bool,
+        disable_image_extraction: bool,
+        do_not_cache: bool,
         do_not_unroll_columns: bool,
+        extract_charts: bool,
+        fast_mode: bool,
         guess_xlsx_sheet_name: bool,
+        html_make_all_elements_visible: bool,
+        html_remove_fixed_elements: bool,
+        html_remove_navigation_elements: bool,
+        http_proxy: str,
+        input_s_3_path: str,
+        input_url: str,
+        invalidate_cache: bool,
+        is_formatting_instruction: bool,
+        language: typing.List[ParserLanguages],
+        extract_layout: bool,
+        max_pages: typing.Optional[int] = OMIT,
+        output_pdf_of_document: bool,
+        output_s_3_path_prefix: str,
+        page_prefix: str,
         page_separator: str,
-        bounding_box: str,
+        page_suffix: str,
+        parsing_instruction: str,
+        premium_mode: bool,
+        skip_diagonal_text: bool,
+        structured_output: bool,
+        structured_output_json_schema: str,
+        structured_output_json_schema_name: str,
+        take_screenshot: bool,
         target_pages: str,
         use_vendor_multimodal_model: bool,
-        vendor_multimodal_model_name: str,
         vendor_multimodal_api_key: str,
-        page_prefix: str,
-        page_suffix: str,
+        vendor_multimodal_model_name: str,
         webhook_url: str,
-        take_screenshot: bool,
-        is_formatting_instruction: bool,
-        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,
+        bounding_box: str,
+        gpt_4_o_mode: bool,
+        gpt_4_o_api_key: str,
     ) -> ParsingJob:
         """
         Upload a file to s3 and create a job. return a job id
@@ -154,132 +169,175 @@ class ParsingClient:
 
             - organization_id: typing.Optional[str].
 
-            - language: typing.List[ParserLanguages].
+            - file: typing.Optional[str].
 
-            - parsing_instruction: str.
+            - annotate_links: bool.
 
-            - skip_diagonal_text: bool.
+            - auto_mode: bool.
 
-            - invalidate_cache: bool.
+            - auto_mode_trigger_on_image_in_page: bool.
 
-            - do_not_cache: bool.
+            - auto_mode_trigger_on_table_in_page: bool.
 
-            - gpt_4_o_mode: bool.
+            - auto_mode_trigger_on_text_in_page: str.
 
-            - fast_mode: bool.
+            - auto_mode_trigger_on_regexp_in_page: str.
 
-            - premium_mode: bool.
+            - azure_openai_api_version: str.
+
+            - azure_openai_deployment_name: str.
+
+            - azure_openai_endpoint: str.
+
+            - azure_openai_key: str.
+
+            - bbox_bottom: float.
+
+            - bbox_left: float.
+
+            - bbox_right: float.
+
+            - bbox_top: float.
 
             - continuous_mode: bool.
 
-            - gpt_4_o_api_key: str.
+            - disable_ocr: bool.
+
+            - disable_reconstruction: bool.
+
+            - disable_image_extraction: bool.
+
+            - do_not_cache: bool.
 
             - do_not_unroll_columns: bool.
 
+            - extract_charts: bool.
+
+            - fast_mode: bool.
+
             - guess_xlsx_sheet_name: bool.
 
-            - page_separator: str.
+            - html_make_all_elements_visible: bool.
 
-            - bounding_box: str.
+            - html_remove_fixed_elements: bool.
 
-            - target_pages: str.
+            - html_remove_navigation_elements: bool.
 
-            - use_vendor_multimodal_model: bool.
+            - http_proxy: str.
 
-            - vendor_multimodal_model_name: str.
+            - input_s_3_path: str.
 
-            - vendor_multimodal_api_key: str.
+            - input_url: str.
 
-            - page_prefix: str.
+            - invalidate_cache: bool.
 
-            - page_suffix: str.
+            - is_formatting_instruction: bool.
 
-            - webhook_url: str.
+            - language: typing.List[ParserLanguages].
 
-            - take_screenshot: bool.
+            - extract_layout: bool.
 
-            - is_formatting_instruction: bool.
+            - max_pages: typing.Optional[int].
 
-            - disable_ocr: bool.
+            - output_pdf_of_document: bool.
 
-            - annotate_links: bool.
+            - output_s_3_path_prefix: str.
 
-            - disable_reconstruction: bool.
+            - page_prefix: str.
 
-            - disable_image_extraction: bool.
+            - page_separator: str.
 
-            - input_s_3_path: str.
+            - page_suffix: str.
 
-            - output_s_3_path_prefix: str.
+            - parsing_instruction: str.
 
-            - azure_openai_deployment_name: str.
+            - premium_mode: bool.
 
-            - azure_openai_endpoint: str.
+            - skip_diagonal_text: bool.
 
-            - azure_openai_api_version: str.
+            - structured_output: bool.
 
-            - azure_openai_key: str.
+            - structured_output_json_schema: str.
 
-            - auto_mode: bool.
+            - structured_output_json_schema_name: str.
 
-            - auto_mode_trigger_on_regexp_in_page: str.
+            - take_screenshot: bool.
 
-            - auto_mode_trigger_on_text_in_page: str.
+            - target_pages: str.
 
-            - auto_mode_trigger_on_table_in_page: bool.
+            - use_vendor_multimodal_model: bool.
 
-            - auto_mode_trigger_on_image_in_page: bool.
+            - vendor_multimodal_api_key: str.
 
-            - file: typing.Optional[str].
+            - vendor_multimodal_model_name: str.
 
-            - input_url: str.
+            - webhook_url: str.
 
-            - http_proxy: str.
+            - bounding_box: str.
+
+            - gpt_4_o_mode: bool.
+
+            - gpt_4_o_api_key: str.
         """
         _request: typing.Dict[str, typing.Any] = {
-            "language": language,
-            "parsing_instruction": parsing_instruction,
-            "skip_diagonal_text": skip_diagonal_text,
-            "invalidate_cache": invalidate_cache,
-            "do_not_cache": do_not_cache,
-            "gpt4o_mode": gpt_4_o_mode,
-            "fast_mode": fast_mode,
-            "premium_mode": premium_mode,
+            "annotate_links": annotate_links,
+            "auto_mode": auto_mode,
+            "auto_mode_trigger_on_image_in_page": auto_mode_trigger_on_image_in_page,
+            "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,
+            "azure_openai_api_version": azure_openai_api_version,
+            "azure_openai_deployment_name": azure_openai_deployment_name,
+            "azure_openai_endpoint": azure_openai_endpoint,
+            "azure_openai_key": azure_openai_key,
+            "bbox_bottom": bbox_bottom,
+            "bbox_left": bbox_left,
+            "bbox_right": bbox_right,
+            "bbox_top": bbox_top,
             "continuous_mode": continuous_mode,
-            "gpt4o_api_key": gpt_4_o_api_key,
+            "disable_ocr": disable_ocr,
+            "disable_reconstruction": disable_reconstruction,
+            "disable_image_extraction": disable_image_extraction,
+            "do_not_cache": do_not_cache,
             "do_not_unroll_columns": do_not_unroll_columns,
+            "extract_charts": extract_charts,
+            "fast_mode": fast_mode,
             "guess_xlsx_sheet_name": guess_xlsx_sheet_name,
+            "html_make_all_elements_visible": html_make_all_elements_visible,
+            "html_remove_fixed_elements": html_remove_fixed_elements,
+            "html_remove_navigation_elements": html_remove_navigation_elements,
+            "http_proxy": http_proxy,
+            "input_s3_path": input_s_3_path,
+            "input_url": input_url,
+            "invalidate_cache": invalidate_cache,
+            "is_formatting_instruction": is_formatting_instruction,
+            "language": language,
+            "extract_layout": extract_layout,
+            "output_pdf_of_document": output_pdf_of_document,
+            "output_s3_path_prefix": output_s_3_path_prefix,
+            "page_prefix": page_prefix,
             "page_separator": page_separator,
-            "bounding_box": bounding_box,
+            "page_suffix": page_suffix,
+            "parsing_instruction": parsing_instruction,
+            "premium_mode": premium_mode,
+            "skip_diagonal_text": skip_diagonal_text,
+            "structured_output": structured_output,
+            "structured_output_json_schema": structured_output_json_schema,
+            "structured_output_json_schema_name": structured_output_json_schema_name,
+            "take_screenshot": take_screenshot,
             "target_pages": target_pages,
             "use_vendor_multimodal_model": use_vendor_multimodal_model,
-            "vendor_multimodal_model_name": vendor_multimodal_model_name,
             "vendor_multimodal_api_key": vendor_multimodal_api_key,
-            "page_prefix": page_prefix,
-            "page_suffix": page_suffix,
+            "vendor_multimodal_model_name": vendor_multimodal_model_name,
             "webhook_url": webhook_url,
-            "take_screenshot": take_screenshot,
-            "is_formatting_instruction": is_formatting_instruction,
-            "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,
+            "bounding_box": bounding_box,
+            "gpt4o_mode": gpt_4_o_mode,
+            "gpt4o_api_key": gpt_4_o_api_key,
         }
         if file is not OMIT:
             _request["file"] = file
+        if max_pages is not OMIT:
+            _request["max_pages"] = max_pages
         _response = self._client_wrapper.httpx_client.request(
             "POST",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/parsing/upload"),
@@ -442,7 +500,7 @@ class ParsingClient:
         _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/text"
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/raw/pdf"
             ),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
@@ -457,7 +515,7 @@ 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:
+    def get_job_structured_result(self, job_id: str) -> ParsingJobStructuredResult:
         """
         Get a job by id
 
@@ -469,20 +527,20 @@ class ParsingClient:
         client = LlamaCloud(
             token="YOUR_TOKEN",
         )
-        client.parsing.get_job_raw_xlsx_result(
+        client.parsing.get_job_structured_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"
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/structured"
             ),
             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
+            return pydantic.parse_obj_as(ParsingJobStructuredResult, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -491,7 +549,7 @@ 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_result(self, job_id: str) -> ParsingJobMarkdownResult:
+    def get_job_raw_structured_result(self, job_id: str) -> typing.Any:
         """
         Get a job by id
 
@@ -503,20 +561,20 @@ class ParsingClient:
         client = LlamaCloud(
             token="YOUR_TOKEN",
         )
-        client.parsing.get_job_result(
+        client.parsing.get_job_raw_structured_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/markdown"
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/raw/structured"
             ),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(ParsingJobMarkdownResult, _response.json())  # type: ignore
+            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:
@@ -525,7 +583,7 @@ 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_md_result(self, job_id: str) -> typing.Any:
+    def get_job_raw_xlsx_result(self, job_id: str) -> typing.Any:
         """
         Get a job by id
 
@@ -537,14 +595,14 @@ class ParsingClient:
         client = LlamaCloud(
             token="YOUR_TOKEN",
         )
-        client.parsing.get_job_raw_md_result(
+        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/markdown"
+                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,
@@ -559,7 +617,7 @@ 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_json_result(self, job_id: str) -> ParsingJobJsonResult:
+    def get_job_result(self, job_id: str) -> ParsingJobMarkdownResult:
         """
         Get a job by id
 
@@ -571,18 +629,20 @@ class ParsingClient:
         client = LlamaCloud(
             token="YOUR_TOKEN",
         )
-        client.parsing.get_job_json_result(
+        client.parsing.get_job_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/json"),
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/markdown"
+            ),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(ParsingJobJsonResult, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(ParsingJobMarkdownResult, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -591,7 +651,7 @@ 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_json_raw_result(self, job_id: str) -> typing.Any:
+    def get_job_raw_md_result(self, job_id: str) -> typing.Any:
         """
         Get a job by id
 
@@ -603,14 +663,14 @@ class ParsingClient:
         client = LlamaCloud(
             token="YOUR_TOKEN",
         )
-        client.parsing.get_job_json_raw_result(
+        client.parsing.get_job_raw_md_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/json"
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/raw/markdown"
             ),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
@@ -625,11 +685,77 @@ class ParsingClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    def get_parsing_history_result(self) -> typing.List[ParsingHistoryItem]:
+    def get_job_json_result(self, job_id: str) -> ParsingJobJsonResult:
         """
-        Get parsing history for user
+        Get a job by id
 
-        ---
+        Parameters:
+            - job_id: str.
+        ---
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.parsing.get_job_json_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/json"),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ParsingJobJsonResult, _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_json_raw_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_json_raw_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/json"
+            ),
+            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_history_result(self) -> typing.List[ParsingHistoryItem]:
+        """
+        Get parsing history for user
+
+        ---
         from llama_cloud.client import LlamaCloud
 
         client = LlamaCloud(
@@ -763,47 +889,61 @@ class AsyncParsingClient:
         *,
         project_id: typing.Optional[str] = None,
         organization_id: typing.Optional[str] = None,
-        language: typing.List[ParserLanguages],
-        parsing_instruction: str,
-        skip_diagonal_text: bool,
-        invalidate_cache: bool,
-        do_not_cache: bool,
-        gpt_4_o_mode: bool,
-        fast_mode: bool,
-        premium_mode: bool,
+        file: typing.Optional[str] = OMIT,
+        annotate_links: bool,
+        auto_mode: bool,
+        auto_mode_trigger_on_image_in_page: bool,
+        auto_mode_trigger_on_table_in_page: bool,
+        auto_mode_trigger_on_text_in_page: str,
+        auto_mode_trigger_on_regexp_in_page: str,
+        azure_openai_api_version: str,
+        azure_openai_deployment_name: str,
+        azure_openai_endpoint: str,
+        azure_openai_key: str,
+        bbox_bottom: float,
+        bbox_left: float,
+        bbox_right: float,
+        bbox_top: float,
         continuous_mode: bool,
-        gpt_4_o_api_key: str,
+        disable_ocr: bool,
+        disable_reconstruction: bool,
+        disable_image_extraction: bool,
+        do_not_cache: bool,
         do_not_unroll_columns: bool,
+        extract_charts: bool,
+        fast_mode: bool,
         guess_xlsx_sheet_name: bool,
+        html_make_all_elements_visible: bool,
+        html_remove_fixed_elements: bool,
+        html_remove_navigation_elements: bool,
+        http_proxy: str,
+        input_s_3_path: str,
+        input_url: str,
+        invalidate_cache: bool,
+        is_formatting_instruction: bool,
+        language: typing.List[ParserLanguages],
+        extract_layout: bool,
+        max_pages: typing.Optional[int] = OMIT,
+        output_pdf_of_document: bool,
+        output_s_3_path_prefix: str,
+        page_prefix: str,
         page_separator: str,
-        bounding_box: str,
+        page_suffix: str,
+        parsing_instruction: str,
+        premium_mode: bool,
+        skip_diagonal_text: bool,
+        structured_output: bool,
+        structured_output_json_schema: str,
+        structured_output_json_schema_name: str,
+        take_screenshot: bool,
         target_pages: str,
         use_vendor_multimodal_model: bool,
-        vendor_multimodal_model_name: str,
         vendor_multimodal_api_key: str,
-        page_prefix: str,
-        page_suffix: str,
+        vendor_multimodal_model_name: str,
         webhook_url: str,
-        take_screenshot: bool,
-        is_formatting_instruction: bool,
-        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,
+        bounding_box: str,
+        gpt_4_o_mode: bool,
+        gpt_4_o_api_key: str,
     ) -> ParsingJob:
         """
         Upload a file to s3 and create a job. return a job id
@@ -813,132 +953,175 @@ class AsyncParsingClient:
 
             - organization_id: typing.Optional[str].
 
-            - language: typing.List[ParserLanguages].
+            - file: typing.Optional[str].
 
-            - parsing_instruction: str.
+            - annotate_links: bool.
 
-            - skip_diagonal_text: bool.
+            - auto_mode: bool.
 
-            - invalidate_cache: bool.
+            - auto_mode_trigger_on_image_in_page: bool.
 
-            - do_not_cache: bool.
+            - auto_mode_trigger_on_table_in_page: bool.
 
-            - gpt_4_o_mode: bool.
+            - auto_mode_trigger_on_text_in_page: str.
 
-            - fast_mode: bool.
+            - auto_mode_trigger_on_regexp_in_page: str.
 
-            - premium_mode: bool.
+            - azure_openai_api_version: str.
+
+            - azure_openai_deployment_name: str.
+
+            - azure_openai_endpoint: str.
+
+            - azure_openai_key: str.
+
+            - bbox_bottom: float.
+
+            - bbox_left: float.
+
+            - bbox_right: float.
+
+            - bbox_top: float.
 
             - continuous_mode: bool.
 
-            - gpt_4_o_api_key: str.
+            - disable_ocr: bool.
+
+            - disable_reconstruction: bool.
+
+            - disable_image_extraction: bool.
+
+            - do_not_cache: bool.
 
             - do_not_unroll_columns: bool.
 
+            - extract_charts: bool.
+
+            - fast_mode: bool.
+
             - guess_xlsx_sheet_name: bool.
 
-            - page_separator: str.
+            - html_make_all_elements_visible: bool.
 
-            - bounding_box: str.
+            - html_remove_fixed_elements: bool.
 
-            - target_pages: str.
+            - html_remove_navigation_elements: bool.
 
-            - use_vendor_multimodal_model: bool.
+            - http_proxy: str.
 
-            - vendor_multimodal_model_name: str.
+            - input_s_3_path: str.
 
-            - vendor_multimodal_api_key: str.
+            - input_url: str.
 
-            - page_prefix: str.
+            - invalidate_cache: bool.
 
-            - page_suffix: str.
+            - is_formatting_instruction: bool.
 
-            - webhook_url: str.
+            - language: typing.List[ParserLanguages].
 
-            - take_screenshot: bool.
+            - extract_layout: bool.
 
-            - is_formatting_instruction: bool.
+            - max_pages: typing.Optional[int].
 
-            - disable_ocr: bool.
+            - output_pdf_of_document: bool.
 
-            - annotate_links: bool.
+            - output_s_3_path_prefix: str.
 
-            - disable_reconstruction: bool.
+            - page_prefix: str.
 
-            - disable_image_extraction: bool.
+            - page_separator: str.
 
-            - input_s_3_path: str.
+            - page_suffix: str.
 
-            - output_s_3_path_prefix: str.
+            - parsing_instruction: str.
 
-            - azure_openai_deployment_name: str.
+            - premium_mode: bool.
 
-            - azure_openai_endpoint: str.
+            - skip_diagonal_text: bool.
 
-            - azure_openai_api_version: str.
+            - structured_output: bool.
 
-            - azure_openai_key: str.
+            - structured_output_json_schema: str.
 
-            - auto_mode: bool.
+            - structured_output_json_schema_name: str.
 
-            - auto_mode_trigger_on_regexp_in_page: str.
+            - take_screenshot: bool.
 
-            - auto_mode_trigger_on_text_in_page: str.
+            - target_pages: str.
 
-            - auto_mode_trigger_on_table_in_page: bool.
+            - use_vendor_multimodal_model: bool.
 
-            - auto_mode_trigger_on_image_in_page: bool.
+            - vendor_multimodal_api_key: str.
 
-            - file: typing.Optional[str].
+            - vendor_multimodal_model_name: str.
 
-            - input_url: str.
+            - webhook_url: str.
 
-            - http_proxy: str.
+            - bounding_box: str.
+
+            - gpt_4_o_mode: bool.
+
+            - gpt_4_o_api_key: str.
         """
         _request: typing.Dict[str, typing.Any] = {
-            "language": language,
-            "parsing_instruction": parsing_instruction,
-            "skip_diagonal_text": skip_diagonal_text,
-            "invalidate_cache": invalidate_cache,
-            "do_not_cache": do_not_cache,
-            "gpt4o_mode": gpt_4_o_mode,
-            "fast_mode": fast_mode,
-            "premium_mode": premium_mode,
+            "annotate_links": annotate_links,
+            "auto_mode": auto_mode,
+            "auto_mode_trigger_on_image_in_page": auto_mode_trigger_on_image_in_page,
+            "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,
+            "azure_openai_api_version": azure_openai_api_version,
+            "azure_openai_deployment_name": azure_openai_deployment_name,
+            "azure_openai_endpoint": azure_openai_endpoint,
+            "azure_openai_key": azure_openai_key,
+            "bbox_bottom": bbox_bottom,
+            "bbox_left": bbox_left,
+            "bbox_right": bbox_right,
+            "bbox_top": bbox_top,
             "continuous_mode": continuous_mode,
-            "gpt4o_api_key": gpt_4_o_api_key,
+            "disable_ocr": disable_ocr,
+            "disable_reconstruction": disable_reconstruction,
+            "disable_image_extraction": disable_image_extraction,
+            "do_not_cache": do_not_cache,
             "do_not_unroll_columns": do_not_unroll_columns,
+            "extract_charts": extract_charts,
+            "fast_mode": fast_mode,
             "guess_xlsx_sheet_name": guess_xlsx_sheet_name,
+            "html_make_all_elements_visible": html_make_all_elements_visible,
+            "html_remove_fixed_elements": html_remove_fixed_elements,
+            "html_remove_navigation_elements": html_remove_navigation_elements,
+            "http_proxy": http_proxy,
+            "input_s3_path": input_s_3_path,
+            "input_url": input_url,
+            "invalidate_cache": invalidate_cache,
+            "is_formatting_instruction": is_formatting_instruction,
+            "language": language,
+            "extract_layout": extract_layout,
+            "output_pdf_of_document": output_pdf_of_document,
+            "output_s3_path_prefix": output_s_3_path_prefix,
+            "page_prefix": page_prefix,
             "page_separator": page_separator,
-            "bounding_box": bounding_box,
+            "page_suffix": page_suffix,
+            "parsing_instruction": parsing_instruction,
+            "premium_mode": premium_mode,
+            "skip_diagonal_text": skip_diagonal_text,
+            "structured_output": structured_output,
+            "structured_output_json_schema": structured_output_json_schema,
+            "structured_output_json_schema_name": structured_output_json_schema_name,
+            "take_screenshot": take_screenshot,
             "target_pages": target_pages,
             "use_vendor_multimodal_model": use_vendor_multimodal_model,
-            "vendor_multimodal_model_name": vendor_multimodal_model_name,
             "vendor_multimodal_api_key": vendor_multimodal_api_key,
-            "page_prefix": page_prefix,
-            "page_suffix": page_suffix,
+            "vendor_multimodal_model_name": vendor_multimodal_model_name,
             "webhook_url": webhook_url,
-            "take_screenshot": take_screenshot,
-            "is_formatting_instruction": is_formatting_instruction,
-            "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,
+            "bounding_box": bounding_box,
+            "gpt4o_mode": gpt_4_o_mode,
+            "gpt4o_api_key": gpt_4_o_api_key,
         }
         if file is not OMIT:
             _request["file"] = file
+        if max_pages is not OMIT:
+            _request["max_pages"] = max_pages
         _response = await self._client_wrapper.httpx_client.request(
             "POST",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/parsing/upload"),
@@ -1101,7 +1284,75 @@ class AsyncParsingClient:
         _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/text"
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/raw/pdf"
+            ),
+            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_structured_result(self, job_id: str) -> ParsingJobStructuredResult:
+        """
+        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_structured_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/structured"
+            ),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ParsingJobStructuredResult, _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_raw_structured_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_structured_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/structured"
             ),
             headers=self._client_wrapper.get_headers(),
             timeout=60,