llama-cloud 0.1.5__py3-none-any.whl → 0.1.6__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
@@ -36,7 +37,7 @@ class ParsingClient:
     def __init__(self, *, client_wrapper: SyncClientWrapper):
         self._client_wrapper = client_wrapper
 
-    def get_job_image_result(self, job_id: str, name: str) -> None:
+    def get_job_image_result(self, job_id: str, name: str) -> typing.Iterator[bytes]:
         """
         Get a job by id
 
@@ -44,34 +45,29 @@ class ParsingClient:
             - job_id: str.
 
             - name: str.
-        ---
-        from llama_cloud.client import LlamaCloud
-
-        client = LlamaCloud(
-            token="YOUR_TOKEN",
-        )
-        client.parsing.get_job_image_result(
-            job_id="string",
-            name="string",
-        )
         """
-        _response = self._client_wrapper.httpx_client.request(
+        with self._client_wrapper.httpx_client.stream(
             "GET",
             urllib.parse.urljoin(
                 f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/image/{name}"
             ),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
-        )
-        if 200 <= _response.status_code < 300:
-            return
-        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)
+        ) as _response:
+            if 200 <= _response.status_code < 300:
+                for _chunk in _response.iter_bytes():
+                    yield _chunk
+                return
+            _response.read()
+            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_supported_file_extensions(self) -> typing.List[LlamaParseSupportedFileExtensions]:
         """
@@ -104,47 +100,58 @@ 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,
-        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,
-        use_vendor_multimodal_model: bool,
-        vendor_multimodal_model_name: str,
-        vendor_multimodal_api_key: str,
-        page_prefix: str,
-        page_suffix: 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,
+        language: typing.Optional[typing.List[ParserLanguages]] = None,
+        parsing_instruction: typing.Optional[str] = None,
+        skip_diagonal_text: typing.Optional[bool] = None,
+        invalidate_cache: typing.Optional[bool] = None,
+        output_pdf_of_document: typing.Optional[bool] = None,
+        do_not_cache: typing.Optional[bool] = None,
+        gpt_4_o_mode: typing.Optional[bool] = None,
+        fast_mode: typing.Optional[bool] = None,
+        premium_mode: typing.Optional[bool] = None,
+        continuous_mode: typing.Optional[bool] = None,
+        gpt_4_o_api_key: typing.Optional[str] = None,
+        do_not_unroll_columns: typing.Optional[bool] = None,
+        html_make_all_elements_visible: typing.Optional[bool] = None,
+        html_remove_fixed_elements: typing.Optional[bool] = None,
+        guess_xlsx_sheet_name: typing.Optional[bool] = None,
+        page_separator: typing.Optional[str] = None,
+        bounding_box: typing.Optional[str] = None,
+        bbox_top: typing.Optional[float] = None,
+        bbox_right: typing.Optional[float] = None,
+        bbox_bottom: typing.Optional[float] = None,
+        bbox_left: typing.Optional[float] = None,
+        target_pages: typing.Optional[str] = None,
+        use_vendor_multimodal_model: typing.Optional[bool] = None,
+        vendor_multimodal_model_name: typing.Optional[str] = None,
+        vendor_multimodal_api_key: typing.Optional[str] = None,
+        page_prefix: typing.Optional[str] = None,
+        page_suffix: typing.Optional[str] = None,
+        webhook_url: typing.Optional[str] = None,
+        take_screenshot: typing.Optional[bool] = None,
+        is_formatting_instruction: typing.Optional[bool] = None,
+        disable_ocr: typing.Optional[bool] = None,
+        annotate_links: typing.Optional[bool] = None,
+        disable_reconstruction: typing.Optional[bool] = None,
+        disable_image_extraction: typing.Optional[bool] = None,
+        input_s_3_path: typing.Optional[str] = None,
+        output_s_3_path_prefix: typing.Optional[str] = None,
+        azure_openai_deployment_name: typing.Optional[str] = None,
+        azure_openai_endpoint: typing.Optional[str] = None,
+        azure_openai_api_version: typing.Optional[str] = None,
+        azure_openai_key: typing.Optional[str] = None,
+        auto_mode: typing.Optional[bool] = None,
+        auto_mode_trigger_on_regexp_in_page: typing.Optional[str] = None,
+        auto_mode_trigger_on_text_in_page: typing.Optional[str] = None,
+        auto_mode_trigger_on_table_in_page: typing.Optional[bool] = None,
+        auto_mode_trigger_on_image_in_page: typing.Optional[bool] = None,
+        file: typing.Optional[str] = None,
+        input_url: typing.Optional[str] = None,
+        http_proxy: typing.Optional[str] = None,
+        structured_output: typing.Optional[bool] = None,
+        structured_output_json_schema: typing.Optional[str] = None,
+        structured_output_json_schema_name: typing.Optional[str] = None,
+        max_pages: typing.Optional[int] = None,
     ) -> ParsingJob:
         """
         Upload a file to s3 and create a job. return a job id
@@ -154,137 +161,178 @@ class ParsingClient:
 
             - organization_id: typing.Optional[str].
 
-            - language: typing.List[ParserLanguages].
+            - language: typing.Optional[typing.List[ParserLanguages]].
+
+            - parsing_instruction: typing.Optional[str].
+
+            - skip_diagonal_text: typing.Optional[bool].
+
+            - invalidate_cache: typing.Optional[bool].
+
+            - output_pdf_of_document: typing.Optional[bool].
+
+            - do_not_cache: typing.Optional[bool].
+
+            - gpt_4_o_mode: typing.Optional[bool].
+
+            - fast_mode: typing.Optional[bool].
 
-            - parsing_instruction: str.
+            - premium_mode: typing.Optional[bool].
 
-            - skip_diagonal_text: bool.
+            - continuous_mode: typing.Optional[bool].
 
-            - invalidate_cache: bool.
+            - gpt_4_o_api_key: typing.Optional[str].
 
-            - do_not_cache: bool.
+            - do_not_unroll_columns: typing.Optional[bool].
 
-            - gpt_4_o_mode: bool.
+            - html_make_all_elements_visible: typing.Optional[bool].
 
-            - fast_mode: bool.
+            - html_remove_fixed_elements: typing.Optional[bool].
 
-            - premium_mode: bool.
+            - guess_xlsx_sheet_name: typing.Optional[bool].
 
-            - continuous_mode: bool.
+            - page_separator: typing.Optional[str].
 
-            - gpt_4_o_api_key: str.
+            - bounding_box: typing.Optional[str].
 
-            - do_not_unroll_columns: bool.
+            - bbox_top: typing.Optional[float].
 
-            - guess_xlsx_sheet_name: bool.
+            - bbox_right: typing.Optional[float].
 
-            - page_separator: str.
+            - bbox_bottom: typing.Optional[float].
 
-            - bounding_box: str.
+            - bbox_left: typing.Optional[float].
 
-            - target_pages: str.
+            - target_pages: typing.Optional[str].
 
-            - use_vendor_multimodal_model: bool.
+            - use_vendor_multimodal_model: typing.Optional[bool].
 
-            - vendor_multimodal_model_name: str.
+            - vendor_multimodal_model_name: typing.Optional[str].
 
-            - vendor_multimodal_api_key: str.
+            - vendor_multimodal_api_key: typing.Optional[str].
 
-            - page_prefix: str.
+            - page_prefix: typing.Optional[str].
 
-            - page_suffix: str.
+            - page_suffix: typing.Optional[str].
 
-            - webhook_url: str.
+            - webhook_url: typing.Optional[str].
 
-            - take_screenshot: bool.
+            - take_screenshot: typing.Optional[bool].
 
-            - is_formatting_instruction: bool.
+            - is_formatting_instruction: typing.Optional[bool].
 
-            - disable_ocr: bool.
+            - disable_ocr: typing.Optional[bool].
 
-            - annotate_links: bool.
+            - annotate_links: typing.Optional[bool].
 
-            - disable_reconstruction: bool.
+            - disable_reconstruction: typing.Optional[bool].
 
-            - disable_image_extraction: bool.
+            - disable_image_extraction: typing.Optional[bool].
 
-            - input_s_3_path: str.
+            - input_s_3_path: typing.Optional[str].
 
-            - output_s_3_path_prefix: str.
+            - output_s_3_path_prefix: typing.Optional[str].
 
-            - azure_openai_deployment_name: str.
+            - azure_openai_deployment_name: typing.Optional[str].
 
-            - azure_openai_endpoint: str.
+            - azure_openai_endpoint: typing.Optional[str].
 
-            - azure_openai_api_version: str.
+            - azure_openai_api_version: typing.Optional[str].
 
-            - azure_openai_key: str.
+            - azure_openai_key: typing.Optional[str].
 
-            - auto_mode: bool.
+            - auto_mode: typing.Optional[bool].
 
-            - auto_mode_trigger_on_regexp_in_page: str.
+            - auto_mode_trigger_on_regexp_in_page: typing.Optional[str].
 
-            - auto_mode_trigger_on_text_in_page: str.
+            - auto_mode_trigger_on_text_in_page: typing.Optional[str].
 
-            - auto_mode_trigger_on_table_in_page: bool.
+            - auto_mode_trigger_on_table_in_page: typing.Optional[bool].
 
-            - auto_mode_trigger_on_image_in_page: bool.
+            - auto_mode_trigger_on_image_in_page: typing.Optional[bool].
 
             - file: typing.Optional[str].
 
-            - input_url: str.
-
-            - http_proxy: 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,
-            "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,
-            "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,
-            "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,
-        }
-        if file is not OMIT:
-            _request["file"] = file
+            - input_url: typing.Optional[str].
+
+            - http_proxy: typing.Optional[str].
+
+            - structured_output: typing.Optional[bool].
+
+            - structured_output_json_schema: typing.Optional[str].
+
+            - structured_output_json_schema_name: typing.Optional[str].
+
+            - max_pages: typing.Optional[int].
+        ---
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.parsing.upload_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),
+            data=jsonable_encoder(
+                {
+                    "language": language,
+                    "parsing_instruction": parsing_instruction,
+                    "skip_diagonal_text": skip_diagonal_text,
+                    "invalidate_cache": invalidate_cache,
+                    "output_pdf_of_document": output_pdf_of_document,
+                    "do_not_cache": do_not_cache,
+                    "gpt4o_mode": gpt_4_o_mode,
+                    "fast_mode": fast_mode,
+                    "premium_mode": premium_mode,
+                    "continuous_mode": continuous_mode,
+                    "gpt4o_api_key": gpt_4_o_api_key,
+                    "do_not_unroll_columns": do_not_unroll_columns,
+                    "html_make_all_elements_visible": html_make_all_elements_visible,
+                    "html_remove_fixed_elements": html_remove_fixed_elements,
+                    "guess_xlsx_sheet_name": guess_xlsx_sheet_name,
+                    "page_separator": page_separator,
+                    "bounding_box": bounding_box,
+                    "bbox_top": bbox_top,
+                    "bbox_right": bbox_right,
+                    "bbox_bottom": bbox_bottom,
+                    "bbox_left": bbox_left,
+                    "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,
+                    "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,
+                    "file": file,
+                    "input_url": input_url,
+                    "http_proxy": http_proxy,
+                    "structured_output": structured_output,
+                    "structured_output_json_schema": structured_output_json_schema,
+                    "structured_output_json_schema_name": structured_output_json_schema_name,
+                    "max_pages": max_pages,
+                }
+            ),
+            files={},
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
@@ -340,7 +388,7 @@ class ParsingClient:
             token="YOUR_TOKEN",
         )
         client.parsing.get_job(
-            job_id="string",
+            job_id="job_id",
         )
         """
         _response = self._client_wrapper.httpx_client.request(
@@ -372,7 +420,7 @@ class ParsingClient:
             token="YOUR_TOKEN",
         )
         client.parsing.get_parsing_job_details(
-            job_id="string",
+            job_id="job_id",
         )
         """
         _response = self._client_wrapper.httpx_client.request(
@@ -404,7 +452,7 @@ class ParsingClient:
             token="YOUR_TOKEN",
         )
         client.parsing.get_job_text_result(
-            job_id="string",
+            job_id="job_id",
         )
         """
         _response = self._client_wrapper.httpx_client.request(
@@ -436,13 +484,81 @@ class ParsingClient:
             token="YOUR_TOKEN",
         )
         client.parsing.get_job_raw_text_result(
-            job_id="string",
+            job_id="job_id",
+        )
+        """
+        _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/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)
+
+    def get_job_structured_result(self, job_id: str) -> ParsingJobStructuredResult:
+        """
+        Get a job by id
+
+        Parameters:
+            - job_id: str.
+        ---
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.parsing.get_job_structured_result(
+            job_id="job_id",
+        )
+        """
+        _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/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)
+
+    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 LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.parsing.get_job_raw_structured_result(
+            job_id="job_id",
         )
         """
         _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/structured"
             ),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
@@ -470,7 +586,7 @@ class ParsingClient:
             token="YOUR_TOKEN",
         )
         client.parsing.get_job_raw_xlsx_result(
-            job_id="string",
+            job_id="job_id",
         )
         """
         _response = self._client_wrapper.httpx_client.request(
@@ -504,7 +620,7 @@ class ParsingClient:
             token="YOUR_TOKEN",
         )
         client.parsing.get_job_result(
-            job_id="string",
+            job_id="job_id",
         )
         """
         _response = self._client_wrapper.httpx_client.request(
@@ -538,7 +654,7 @@ class ParsingClient:
             token="YOUR_TOKEN",
         )
         client.parsing.get_job_raw_md_result(
-            job_id="string",
+            job_id="job_id",
         )
         """
         _response = self._client_wrapper.httpx_client.request(
@@ -572,7 +688,7 @@ class ParsingClient:
             token="YOUR_TOKEN",
         )
         client.parsing.get_job_json_result(
-            job_id="string",
+            job_id="job_id",
         )
         """
         _response = self._client_wrapper.httpx_client.request(
@@ -604,7 +720,7 @@ class ParsingClient:
             token="YOUR_TOKEN",
         )
         client.parsing.get_job_json_raw_result(
-            job_id="string",
+            job_id="job_id",
         )
         """
         _response = self._client_wrapper.httpx_client.request(
@@ -668,8 +784,8 @@ class ParsingClient:
             token="YOUR_TOKEN",
         )
         client.parsing.generate_presigned_url(
-            job_id="string",
-            filename="string",
+            job_id="job_id",
+            filename="filename",
         )
         """
         _response = self._client_wrapper.httpx_client.request(
@@ -695,7 +811,7 @@ class AsyncParsingClient:
     def __init__(self, *, client_wrapper: AsyncClientWrapper):
         self._client_wrapper = client_wrapper
 
-    async def get_job_image_result(self, job_id: str, name: str) -> None:
+    async def get_job_image_result(self, job_id: str, name: str) -> typing.AsyncIterator[bytes]:
         """
         Get a job by id
 
@@ -703,34 +819,29 @@ class AsyncParsingClient:
             - job_id: str.
 
             - name: str.
-        ---
-        from llama_cloud.client import AsyncLlamaCloud
-
-        client = AsyncLlamaCloud(
-            token="YOUR_TOKEN",
-        )
-        await client.parsing.get_job_image_result(
-            job_id="string",
-            name="string",
-        )
         """
-        _response = await self._client_wrapper.httpx_client.request(
+        async with self._client_wrapper.httpx_client.stream(
             "GET",
             urllib.parse.urljoin(
                 f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/image/{name}"
             ),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
-        )
-        if 200 <= _response.status_code < 300:
-            return
-        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)
+        ) as _response:
+            if 200 <= _response.status_code < 300:
+                async for _chunk in _response.aiter_bytes():
+                    yield _chunk
+                return
+            await _response.aread()
+            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_supported_file_extensions(self) -> typing.List[LlamaParseSupportedFileExtensions]:
         """
@@ -763,47 +874,58 @@ 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,
-        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,
-        use_vendor_multimodal_model: bool,
-        vendor_multimodal_model_name: str,
-        vendor_multimodal_api_key: str,
-        page_prefix: str,
-        page_suffix: 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,
+        language: typing.Optional[typing.List[ParserLanguages]] = None,
+        parsing_instruction: typing.Optional[str] = None,
+        skip_diagonal_text: typing.Optional[bool] = None,
+        invalidate_cache: typing.Optional[bool] = None,
+        output_pdf_of_document: typing.Optional[bool] = None,
+        do_not_cache: typing.Optional[bool] = None,
+        gpt_4_o_mode: typing.Optional[bool] = None,
+        fast_mode: typing.Optional[bool] = None,
+        premium_mode: typing.Optional[bool] = None,
+        continuous_mode: typing.Optional[bool] = None,
+        gpt_4_o_api_key: typing.Optional[str] = None,
+        do_not_unroll_columns: typing.Optional[bool] = None,
+        html_make_all_elements_visible: typing.Optional[bool] = None,
+        html_remove_fixed_elements: typing.Optional[bool] = None,
+        guess_xlsx_sheet_name: typing.Optional[bool] = None,
+        page_separator: typing.Optional[str] = None,
+        bounding_box: typing.Optional[str] = None,
+        bbox_top: typing.Optional[float] = None,
+        bbox_right: typing.Optional[float] = None,
+        bbox_bottom: typing.Optional[float] = None,
+        bbox_left: typing.Optional[float] = None,
+        target_pages: typing.Optional[str] = None,
+        use_vendor_multimodal_model: typing.Optional[bool] = None,
+        vendor_multimodal_model_name: typing.Optional[str] = None,
+        vendor_multimodal_api_key: typing.Optional[str] = None,
+        page_prefix: typing.Optional[str] = None,
+        page_suffix: typing.Optional[str] = None,
+        webhook_url: typing.Optional[str] = None,
+        take_screenshot: typing.Optional[bool] = None,
+        is_formatting_instruction: typing.Optional[bool] = None,
+        disable_ocr: typing.Optional[bool] = None,
+        annotate_links: typing.Optional[bool] = None,
+        disable_reconstruction: typing.Optional[bool] = None,
+        disable_image_extraction: typing.Optional[bool] = None,
+        input_s_3_path: typing.Optional[str] = None,
+        output_s_3_path_prefix: typing.Optional[str] = None,
+        azure_openai_deployment_name: typing.Optional[str] = None,
+        azure_openai_endpoint: typing.Optional[str] = None,
+        azure_openai_api_version: typing.Optional[str] = None,
+        azure_openai_key: typing.Optional[str] = None,
+        auto_mode: typing.Optional[bool] = None,
+        auto_mode_trigger_on_regexp_in_page: typing.Optional[str] = None,
+        auto_mode_trigger_on_text_in_page: typing.Optional[str] = None,
+        auto_mode_trigger_on_table_in_page: typing.Optional[bool] = None,
+        auto_mode_trigger_on_image_in_page: typing.Optional[bool] = None,
+        file: typing.Optional[str] = None,
+        input_url: typing.Optional[str] = None,
+        http_proxy: typing.Optional[str] = None,
+        structured_output: typing.Optional[bool] = None,
+        structured_output_json_schema: typing.Optional[str] = None,
+        structured_output_json_schema_name: typing.Optional[str] = None,
+        max_pages: typing.Optional[int] = None,
     ) -> ParsingJob:
         """
         Upload a file to s3 and create a job. return a job id
@@ -813,137 +935,178 @@ class AsyncParsingClient:
 
             - organization_id: typing.Optional[str].
 
-            - language: typing.List[ParserLanguages].
+            - language: typing.Optional[typing.List[ParserLanguages]].
+
+            - parsing_instruction: typing.Optional[str].
+
+            - skip_diagonal_text: typing.Optional[bool].
+
+            - invalidate_cache: typing.Optional[bool].
+
+            - output_pdf_of_document: typing.Optional[bool].
+
+            - do_not_cache: typing.Optional[bool].
+
+            - gpt_4_o_mode: typing.Optional[bool].
+
+            - fast_mode: typing.Optional[bool].
 
-            - parsing_instruction: str.
+            - premium_mode: typing.Optional[bool].
 
-            - skip_diagonal_text: bool.
+            - continuous_mode: typing.Optional[bool].
 
-            - invalidate_cache: bool.
+            - gpt_4_o_api_key: typing.Optional[str].
 
-            - do_not_cache: bool.
+            - do_not_unroll_columns: typing.Optional[bool].
 
-            - gpt_4_o_mode: bool.
+            - html_make_all_elements_visible: typing.Optional[bool].
 
-            - fast_mode: bool.
+            - html_remove_fixed_elements: typing.Optional[bool].
 
-            - premium_mode: bool.
+            - guess_xlsx_sheet_name: typing.Optional[bool].
 
-            - continuous_mode: bool.
+            - page_separator: typing.Optional[str].
 
-            - gpt_4_o_api_key: str.
+            - bounding_box: typing.Optional[str].
 
-            - do_not_unroll_columns: bool.
+            - bbox_top: typing.Optional[float].
 
-            - guess_xlsx_sheet_name: bool.
+            - bbox_right: typing.Optional[float].
 
-            - page_separator: str.
+            - bbox_bottom: typing.Optional[float].
 
-            - bounding_box: str.
+            - bbox_left: typing.Optional[float].
 
-            - target_pages: str.
+            - target_pages: typing.Optional[str].
 
-            - use_vendor_multimodal_model: bool.
+            - use_vendor_multimodal_model: typing.Optional[bool].
 
-            - vendor_multimodal_model_name: str.
+            - vendor_multimodal_model_name: typing.Optional[str].
 
-            - vendor_multimodal_api_key: str.
+            - vendor_multimodal_api_key: typing.Optional[str].
 
-            - page_prefix: str.
+            - page_prefix: typing.Optional[str].
 
-            - page_suffix: str.
+            - page_suffix: typing.Optional[str].
 
-            - webhook_url: str.
+            - webhook_url: typing.Optional[str].
 
-            - take_screenshot: bool.
+            - take_screenshot: typing.Optional[bool].
 
-            - is_formatting_instruction: bool.
+            - is_formatting_instruction: typing.Optional[bool].
 
-            - disable_ocr: bool.
+            - disable_ocr: typing.Optional[bool].
 
-            - annotate_links: bool.
+            - annotate_links: typing.Optional[bool].
 
-            - disable_reconstruction: bool.
+            - disable_reconstruction: typing.Optional[bool].
 
-            - disable_image_extraction: bool.
+            - disable_image_extraction: typing.Optional[bool].
 
-            - input_s_3_path: str.
+            - input_s_3_path: typing.Optional[str].
 
-            - output_s_3_path_prefix: str.
+            - output_s_3_path_prefix: typing.Optional[str].
 
-            - azure_openai_deployment_name: str.
+            - azure_openai_deployment_name: typing.Optional[str].
 
-            - azure_openai_endpoint: str.
+            - azure_openai_endpoint: typing.Optional[str].
 
-            - azure_openai_api_version: str.
+            - azure_openai_api_version: typing.Optional[str].
 
-            - azure_openai_key: str.
+            - azure_openai_key: typing.Optional[str].
 
-            - auto_mode: bool.
+            - auto_mode: typing.Optional[bool].
 
-            - auto_mode_trigger_on_regexp_in_page: str.
+            - auto_mode_trigger_on_regexp_in_page: typing.Optional[str].
 
-            - auto_mode_trigger_on_text_in_page: str.
+            - auto_mode_trigger_on_text_in_page: typing.Optional[str].
 
-            - auto_mode_trigger_on_table_in_page: bool.
+            - auto_mode_trigger_on_table_in_page: typing.Optional[bool].
 
-            - auto_mode_trigger_on_image_in_page: bool.
+            - auto_mode_trigger_on_image_in_page: typing.Optional[bool].
 
             - file: typing.Optional[str].
 
-            - input_url: str.
-
-            - http_proxy: 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,
-            "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,
-            "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,
-            "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,
-        }
-        if file is not OMIT:
-            _request["file"] = file
+            - input_url: typing.Optional[str].
+
+            - http_proxy: typing.Optional[str].
+
+            - structured_output: typing.Optional[bool].
+
+            - structured_output_json_schema: typing.Optional[str].
+
+            - structured_output_json_schema_name: typing.Optional[str].
+
+            - max_pages: typing.Optional[int].
+        ---
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.parsing.upload_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),
+            data=jsonable_encoder(
+                {
+                    "language": language,
+                    "parsing_instruction": parsing_instruction,
+                    "skip_diagonal_text": skip_diagonal_text,
+                    "invalidate_cache": invalidate_cache,
+                    "output_pdf_of_document": output_pdf_of_document,
+                    "do_not_cache": do_not_cache,
+                    "gpt4o_mode": gpt_4_o_mode,
+                    "fast_mode": fast_mode,
+                    "premium_mode": premium_mode,
+                    "continuous_mode": continuous_mode,
+                    "gpt4o_api_key": gpt_4_o_api_key,
+                    "do_not_unroll_columns": do_not_unroll_columns,
+                    "html_make_all_elements_visible": html_make_all_elements_visible,
+                    "html_remove_fixed_elements": html_remove_fixed_elements,
+                    "guess_xlsx_sheet_name": guess_xlsx_sheet_name,
+                    "page_separator": page_separator,
+                    "bounding_box": bounding_box,
+                    "bbox_top": bbox_top,
+                    "bbox_right": bbox_right,
+                    "bbox_bottom": bbox_bottom,
+                    "bbox_left": bbox_left,
+                    "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,
+                    "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,
+                    "file": file,
+                    "input_url": input_url,
+                    "http_proxy": http_proxy,
+                    "structured_output": structured_output,
+                    "structured_output_json_schema": structured_output_json_schema,
+                    "structured_output_json_schema_name": structured_output_json_schema_name,
+                    "max_pages": max_pages,
+                }
+            ),
+            files={},
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
@@ -999,7 +1162,7 @@ class AsyncParsingClient:
             token="YOUR_TOKEN",
         )
         await client.parsing.get_job(
-            job_id="string",
+            job_id="job_id",
         )
         """
         _response = await self._client_wrapper.httpx_client.request(
@@ -1031,7 +1194,7 @@ class AsyncParsingClient:
             token="YOUR_TOKEN",
         )
         await client.parsing.get_parsing_job_details(
-            job_id="string",
+            job_id="job_id",
         )
         """
         _response = await self._client_wrapper.httpx_client.request(
@@ -1063,7 +1226,7 @@ class AsyncParsingClient:
             token="YOUR_TOKEN",
         )
         await client.parsing.get_job_text_result(
-            job_id="string",
+            job_id="job_id",
         )
         """
         _response = await self._client_wrapper.httpx_client.request(
@@ -1095,13 +1258,81 @@ class AsyncParsingClient:
             token="YOUR_TOKEN",
         )
         await client.parsing.get_job_raw_text_result(
-            job_id="string",
+            job_id="job_id",
+        )
+        """
+        _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/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="job_id",
+        )
+        """
+        _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="job_id",
         )
         """
         _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/structured"
             ),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
@@ -1129,7 +1360,7 @@ class AsyncParsingClient:
             token="YOUR_TOKEN",
         )
         await client.parsing.get_job_raw_xlsx_result(
-            job_id="string",
+            job_id="job_id",
         )
         """
         _response = await self._client_wrapper.httpx_client.request(
@@ -1163,7 +1394,7 @@ class AsyncParsingClient:
             token="YOUR_TOKEN",
         )
         await client.parsing.get_job_result(
-            job_id="string",
+            job_id="job_id",
         )
         """
         _response = await self._client_wrapper.httpx_client.request(
@@ -1197,7 +1428,7 @@ class AsyncParsingClient:
             token="YOUR_TOKEN",
         )
         await client.parsing.get_job_raw_md_result(
-            job_id="string",
+            job_id="job_id",
         )
         """
         _response = await self._client_wrapper.httpx_client.request(
@@ -1231,7 +1462,7 @@ class AsyncParsingClient:
             token="YOUR_TOKEN",
         )
         await client.parsing.get_job_json_result(
-            job_id="string",
+            job_id="job_id",
         )
         """
         _response = await self._client_wrapper.httpx_client.request(
@@ -1263,7 +1494,7 @@ class AsyncParsingClient:
             token="YOUR_TOKEN",
         )
         await client.parsing.get_job_json_raw_result(
-            job_id="string",
+            job_id="job_id",
         )
         """
         _response = await self._client_wrapper.httpx_client.request(
@@ -1327,8 +1558,8 @@ class AsyncParsingClient:
             token="YOUR_TOKEN",
         )
         await client.parsing.generate_presigned_url(
-            job_id="string",
-            filename="string",
+            job_id="job_id",
+            filename="filename",
         )
         """
         _response = await self._client_wrapper.httpx_client.request(