llama-cloud 0.1.7a1__py3-none-any.whl → 0.1.9__py3-none-any.whl

llama_cloud/resources/parsing/client.py

@@ -103,8 +103,8 @@ class ParsingClient:
     def upload_file(
         self,
         *,
-        project_id: typing.Optional[str] = None,
         organization_id: typing.Optional[str] = None,
+        project_id: typing.Optional[str] = None,
         file: typing.Optional[str] = OMIT,
         annotate_links: bool,
         auto_mode: bool,
@@ -120,6 +120,8 @@ class ParsingClient:
         bbox_left: float,
         bbox_right: float,
         bbox_top: float,
+        complemental_formatting_instruction: str,
+        content_guideline_instruction: str,
         continuous_mode: bool,
         disable_ocr: bool,
         disable_reconstruction: bool,
@@ -128,12 +130,14 @@ class ParsingClient:
         do_not_unroll_columns: bool,
         extract_charts: bool,
         fast_mode: bool,
+        formatting_instruction: str,
         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_s_3_region: str,
         input_url: str,
         invalidate_cache: bool,
         is_formatting_instruction: bool,
@@ -142,12 +146,14 @@ class ParsingClient:
         max_pages: typing.Optional[int] = OMIT,
         output_pdf_of_document: bool,
         output_s_3_path_prefix: str,
+        output_s_3_region: str,
         page_prefix: str,
         page_separator: str,
         page_suffix: str,
         parsing_instruction: str,
         premium_mode: bool,
         skip_diagonal_text: bool,
+        spreadsheet_extract_sub_tables: bool,
         structured_output: bool,
         structured_output_json_schema: str,
         structured_output_json_schema_name: str,
@@ -165,10 +171,10 @@ class ParsingClient:
         Upload a file to s3 and create a job. return a job id
 
         Parameters:
-            - project_id: typing.Optional[str].
-
             - organization_id: typing.Optional[str].
 
+            - project_id: typing.Optional[str].
+
             - file: typing.Optional[str].
 
             - annotate_links: bool.
@@ -199,6 +205,10 @@ class ParsingClient:
 
             - bbox_top: float.
 
+            - complemental_formatting_instruction: str.
+
+            - content_guideline_instruction: str.
+
             - continuous_mode: bool.
 
             - disable_ocr: bool.
@@ -215,6 +225,8 @@ class ParsingClient:
 
             - fast_mode: bool.
 
+            - formatting_instruction: str.
+
             - guess_xlsx_sheet_name: bool.
 
             - html_make_all_elements_visible: bool.
@@ -227,6 +239,8 @@ class ParsingClient:
 
             - input_s_3_path: str.
 
+            - input_s_3_region: str.
+
             - input_url: str.
 
             - invalidate_cache: bool.
@@ -243,6 +257,8 @@ class ParsingClient:
 
             - output_s_3_path_prefix: str.
 
+            - output_s_3_region: str.
+
             - page_prefix: str.
 
             - page_separator: str.
@@ -255,6 +271,8 @@ class ParsingClient:
 
             - skip_diagonal_text: bool.
 
+            - spreadsheet_extract_sub_tables: bool.
+
             - structured_output: bool.
 
             - structured_output_json_schema: str.
@@ -294,6 +312,8 @@ class ParsingClient:
             "bbox_left": bbox_left,
             "bbox_right": bbox_right,
             "bbox_top": bbox_top,
+            "complemental_formatting_instruction": complemental_formatting_instruction,
+            "content_guideline_instruction": content_guideline_instruction,
             "continuous_mode": continuous_mode,
             "disable_ocr": disable_ocr,
             "disable_reconstruction": disable_reconstruction,
@@ -302,12 +322,14 @@ class ParsingClient:
             "do_not_unroll_columns": do_not_unroll_columns,
             "extract_charts": extract_charts,
             "fast_mode": fast_mode,
+            "formatting_instruction": formatting_instruction,
             "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_s3_region": input_s_3_region,
             "input_url": input_url,
             "invalidate_cache": invalidate_cache,
             "is_formatting_instruction": is_formatting_instruction,
@@ -315,12 +337,14 @@ class ParsingClient:
             "extract_layout": extract_layout,
             "output_pdf_of_document": output_pdf_of_document,
             "output_s3_path_prefix": output_s_3_path_prefix,
+            "output_s3_region": output_s_3_region,
             "page_prefix": page_prefix,
             "page_separator": page_separator,
             "page_suffix": page_suffix,
             "parsing_instruction": parsing_instruction,
             "premium_mode": premium_mode,
             "skip_diagonal_text": skip_diagonal_text,
+            "spreadsheet_extract_sub_tables": spreadsheet_extract_sub_tables,
             "structured_output": structured_output,
             "structured_output_json_schema": structured_output_json_schema,
             "structured_output_json_schema_name": structured_output_json_schema_name,
@@ -341,7 +365,7 @@ class ParsingClient:
         _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}),
+            params=remove_none_from_dict({"organization_id": organization_id, "project_id": project_id}),
             json=jsonable_encoder(_request),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
@@ -356,11 +380,13 @@ class ParsingClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    def usage(self) -> ParsingUsage:
+    def usage(self, *, organization_id: typing.Optional[str] = None) -> ParsingUsage:
         """
         DEPRECATED: use either /organizations/{organization_id}/usage or /projects/{project_id}/usage instead
         Get parsing usage for user
 
+        Parameters:
+            - organization_id: typing.Optional[str].
         ---
         from llama_cloud.client import LlamaCloud
 
@@ -372,6 +398,7 @@ class ParsingClient:
         _response = self._client_wrapper.httpx_client.request(
             "GET",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/parsing/usage"),
+            params=remove_none_from_dict({"organization_id": organization_id}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
@@ -449,12 +476,14 @@ 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_text_result(self, job_id: str) -> ParsingJobTextResult:
+    def get_job_text_result(self, job_id: str, *, organization_id: typing.Optional[str] = None) -> ParsingJobTextResult:
         """
         Get a job by id
 
         Parameters:
             - job_id: str.
+
+            - organization_id: typing.Optional[str].
         ---
         from llama_cloud.client import LlamaCloud
 
@@ -468,6 +497,7 @@ 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/text"),
+            params=remove_none_from_dict({"organization_id": organization_id}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
@@ -515,12 +545,16 @@ 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_structured_result(self, job_id: str) -> ParsingJobStructuredResult:
+    def get_job_structured_result(
+        self, job_id: str, *, organization_id: typing.Optional[str] = None
+    ) -> ParsingJobStructuredResult:
         """
         Get a job by id
 
         Parameters:
             - job_id: str.
+
+            - organization_id: typing.Optional[str].
         ---
         from llama_cloud.client import LlamaCloud
 
@@ -536,6 +570,7 @@ class ParsingClient:
             urllib.parse.urljoin(
                 f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/structured"
             ),
+            params=remove_none_from_dict({"organization_id": organization_id}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
@@ -617,12 +652,14 @@ 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_result(self, job_id: str, *, organization_id: typing.Optional[str] = None) -> ParsingJobMarkdownResult:
         """
         Get a job by id
 
         Parameters:
             - job_id: str.
+
+            - organization_id: typing.Optional[str].
         ---
         from llama_cloud.client import LlamaCloud
 
@@ -638,6 +675,7 @@ class ParsingClient:
             urllib.parse.urljoin(
                 f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/markdown"
             ),
+            params=remove_none_from_dict({"organization_id": organization_id}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
@@ -685,12 +723,14 @@ 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_json_result(self, job_id: str, *, organization_id: typing.Optional[str] = None) -> ParsingJobJsonResult:
         """
         Get a job by id
 
         Parameters:
             - job_id: str.
+
+            - organization_id: typing.Optional[str].
         ---
         from llama_cloud.client import LlamaCloud
 
@@ -704,6 +744,7 @@ 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/json"),
+            params=remove_none_from_dict({"organization_id": organization_id}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
@@ -887,8 +928,8 @@ class AsyncParsingClient:
     async def upload_file(
         self,
         *,
-        project_id: typing.Optional[str] = None,
         organization_id: typing.Optional[str] = None,
+        project_id: typing.Optional[str] = None,
         file: typing.Optional[str] = OMIT,
         annotate_links: bool,
         auto_mode: bool,
@@ -904,6 +945,8 @@ class AsyncParsingClient:
         bbox_left: float,
         bbox_right: float,
         bbox_top: float,
+        complemental_formatting_instruction: str,
+        content_guideline_instruction: str,
         continuous_mode: bool,
         disable_ocr: bool,
         disable_reconstruction: bool,
@@ -912,12 +955,14 @@ class AsyncParsingClient:
         do_not_unroll_columns: bool,
         extract_charts: bool,
         fast_mode: bool,
+        formatting_instruction: str,
         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_s_3_region: str,
         input_url: str,
         invalidate_cache: bool,
         is_formatting_instruction: bool,
@@ -926,12 +971,14 @@ class AsyncParsingClient:
         max_pages: typing.Optional[int] = OMIT,
         output_pdf_of_document: bool,
         output_s_3_path_prefix: str,
+        output_s_3_region: str,
         page_prefix: str,
         page_separator: str,
         page_suffix: str,
         parsing_instruction: str,
         premium_mode: bool,
         skip_diagonal_text: bool,
+        spreadsheet_extract_sub_tables: bool,
         structured_output: bool,
         structured_output_json_schema: str,
         structured_output_json_schema_name: str,
@@ -949,10 +996,10 @@ class AsyncParsingClient:
         Upload a file to s3 and create a job. return a job id
 
         Parameters:
-            - project_id: typing.Optional[str].
-
             - organization_id: typing.Optional[str].
 
+            - project_id: typing.Optional[str].
+
             - file: typing.Optional[str].
 
             - annotate_links: bool.
@@ -983,6 +1030,10 @@ class AsyncParsingClient:
 
             - bbox_top: float.
 
+            - complemental_formatting_instruction: str.
+
+            - content_guideline_instruction: str.
+
             - continuous_mode: bool.
 
             - disable_ocr: bool.
@@ -999,6 +1050,8 @@ class AsyncParsingClient:
 
             - fast_mode: bool.
 
+            - formatting_instruction: str.
+
             - guess_xlsx_sheet_name: bool.
 
             - html_make_all_elements_visible: bool.
@@ -1011,6 +1064,8 @@ class AsyncParsingClient:
 
             - input_s_3_path: str.
 
+            - input_s_3_region: str.
+
             - input_url: str.
 
             - invalidate_cache: bool.
@@ -1027,6 +1082,8 @@ class AsyncParsingClient:
 
             - output_s_3_path_prefix: str.
 
+            - output_s_3_region: str.
+
             - page_prefix: str.
 
             - page_separator: str.
@@ -1039,6 +1096,8 @@ class AsyncParsingClient:
 
             - skip_diagonal_text: bool.
 
+            - spreadsheet_extract_sub_tables: bool.
+
             - structured_output: bool.
 
             - structured_output_json_schema: str.
@@ -1078,6 +1137,8 @@ class AsyncParsingClient:
             "bbox_left": bbox_left,
             "bbox_right": bbox_right,
             "bbox_top": bbox_top,
+            "complemental_formatting_instruction": complemental_formatting_instruction,
+            "content_guideline_instruction": content_guideline_instruction,
             "continuous_mode": continuous_mode,
             "disable_ocr": disable_ocr,
             "disable_reconstruction": disable_reconstruction,
@@ -1086,12 +1147,14 @@ class AsyncParsingClient:
             "do_not_unroll_columns": do_not_unroll_columns,
             "extract_charts": extract_charts,
             "fast_mode": fast_mode,
+            "formatting_instruction": formatting_instruction,
             "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_s3_region": input_s_3_region,
             "input_url": input_url,
             "invalidate_cache": invalidate_cache,
             "is_formatting_instruction": is_formatting_instruction,
@@ -1099,12 +1162,14 @@ class AsyncParsingClient:
             "extract_layout": extract_layout,
             "output_pdf_of_document": output_pdf_of_document,
             "output_s3_path_prefix": output_s_3_path_prefix,
+            "output_s3_region": output_s_3_region,
             "page_prefix": page_prefix,
             "page_separator": page_separator,
             "page_suffix": page_suffix,
             "parsing_instruction": parsing_instruction,
             "premium_mode": premium_mode,
             "skip_diagonal_text": skip_diagonal_text,
+            "spreadsheet_extract_sub_tables": spreadsheet_extract_sub_tables,
             "structured_output": structured_output,
             "structured_output_json_schema": structured_output_json_schema,
             "structured_output_json_schema_name": structured_output_json_schema_name,
@@ -1125,7 +1190,7 @@ class AsyncParsingClient:
         _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}),
+            params=remove_none_from_dict({"organization_id": organization_id, "project_id": project_id}),
             json=jsonable_encoder(_request),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
@@ -1140,11 +1205,13 @@ class AsyncParsingClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    async def usage(self) -> ParsingUsage:
+    async def usage(self, *, organization_id: typing.Optional[str] = None) -> ParsingUsage:
         """
         DEPRECATED: use either /organizations/{organization_id}/usage or /projects/{project_id}/usage instead
         Get parsing usage for user
 
+        Parameters:
+            - organization_id: typing.Optional[str].
         ---
         from llama_cloud.client import AsyncLlamaCloud
 
@@ -1156,6 +1223,7 @@ class AsyncParsingClient:
         _response = await self._client_wrapper.httpx_client.request(
             "GET",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/parsing/usage"),
+            params=remove_none_from_dict({"organization_id": organization_id}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
@@ -1233,12 +1301,16 @@ 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_text_result(self, job_id: str) -> ParsingJobTextResult:
+    async def get_job_text_result(
+        self, job_id: str, *, organization_id: typing.Optional[str] = None
+    ) -> ParsingJobTextResult:
         """
         Get a job by id
 
         Parameters:
             - job_id: str.
+
+            - organization_id: typing.Optional[str].
         ---
         from llama_cloud.client import AsyncLlamaCloud
 
@@ -1252,6 +1324,7 @@ 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/text"),
+            params=remove_none_from_dict({"organization_id": organization_id}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
@@ -1299,12 +1372,16 @@ 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_structured_result(self, job_id: str) -> ParsingJobStructuredResult:
+    async def get_job_structured_result(
+        self, job_id: str, *, organization_id: typing.Optional[str] = None
+    ) -> ParsingJobStructuredResult:
         """
         Get a job by id
 
         Parameters:
             - job_id: str.
+
+            - organization_id: typing.Optional[str].
         ---
         from llama_cloud.client import AsyncLlamaCloud
 
@@ -1320,6 +1397,7 @@ class AsyncParsingClient:
             urllib.parse.urljoin(
                 f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/structured"
             ),
+            params=remove_none_from_dict({"organization_id": organization_id}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
@@ -1401,12 +1479,16 @@ 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_result(self, job_id: str) -> ParsingJobMarkdownResult:
+    async def get_job_result(
+        self, job_id: str, *, organization_id: typing.Optional[str] = None
+    ) -> ParsingJobMarkdownResult:
         """
         Get a job by id
 
         Parameters:
             - job_id: str.
+
+            - organization_id: typing.Optional[str].
         ---
         from llama_cloud.client import AsyncLlamaCloud
 
@@ -1422,6 +1504,7 @@ class AsyncParsingClient:
             urllib.parse.urljoin(
                 f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/markdown"
             ),
+            params=remove_none_from_dict({"organization_id": organization_id}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
@@ -1469,12 +1552,16 @@ 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_json_result(self, job_id: str) -> ParsingJobJsonResult:
+    async def get_job_json_result(
+        self, job_id: str, *, organization_id: typing.Optional[str] = None
+    ) -> ParsingJobJsonResult:
         """
         Get a job by id
 
         Parameters:
             - job_id: str.
+
+            - organization_id: typing.Optional[str].
         ---
         from llama_cloud.client import AsyncLlamaCloud
 
@@ -1488,6 +1575,7 @@ 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/json"),
+            params=remove_none_from_dict({"organization_id": organization_id}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )

llama_cloud/resources/reports/client.py

@@ -581,7 +581,7 @@ class ReportsClient:
         self, report_id: str, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
     ) -> typing.Any:
         """
-        Restart a report.
+        Restart a report from scratch.
 
         Parameters:
             - report_id: str.
@@ -601,7 +601,7 @@ class ReportsClient:
         """
         _response = self._client_wrapper.httpx_client.request(
             "POST",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/reports/{report_id}/retry"),
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/reports/{report_id}/restart"),
             params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
@@ -1162,7 +1162,7 @@ class AsyncReportsClient:
         self, report_id: str, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
     ) -> typing.Any:
         """
-        Restart a report.
+        Restart a report from scratch.
 
         Parameters:
             - report_id: str.
@@ -1182,7 +1182,7 @@ class AsyncReportsClient:
         """
         _response = await self._client_wrapper.httpx_client.request(
             "POST",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/reports/{report_id}/retry"),
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/reports/{report_id}/restart"),
             params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,

llama_cloud/types/__init__.py

@@ -53,6 +53,7 @@ from .cohere_embedding_config import CohereEmbeddingConfig
 from .composite_retrieval_mode import CompositeRetrievalMode
 from .composite_retrieval_result import CompositeRetrievalResult
 from .composite_retrieved_text_node import CompositeRetrievedTextNode
+from .composite_retrieved_text_node_with_score import CompositeRetrievedTextNodeWithScore
 from .configurable_data_sink_names import ConfigurableDataSinkNames
 from .configurable_data_source_names import ConfigurableDataSourceNames
 from .configurable_transformation_definition import ConfigurableTransformationDefinition
@@ -116,11 +117,11 @@ from .extract_resultset_data import ExtractResultsetData
 from .extract_resultset_data_item_value import ExtractResultsetDataItemValue
 from .extract_resultset_data_zero_value import ExtractResultsetDataZeroValue
 from .extract_resultset_extraction_metadata_value import ExtractResultsetExtractionMetadataValue
-from .extraction_job import ExtractionJob
-from .extraction_result import ExtractionResult
-from .extraction_result_data_value import ExtractionResultDataValue
-from .extraction_schema import ExtractionSchema
-from .extraction_schema_data_schema_value import ExtractionSchemaDataSchemaValue
+from .extract_run import ExtractRun
+from .extract_run_data_schema_value import ExtractRunDataSchemaValue
+from .extract_run_data_value import ExtractRunDataValue
+from .extract_run_extraction_metadata_value import ExtractRunExtractionMetadataValue
+from .extract_state import ExtractState
 from .file import File
 from .file_permission_info_value import FilePermissionInfoValue
 from .file_resource_info_value import FileResourceInfoValue
@@ -140,6 +141,7 @@ from .job_name_mapping import JobNameMapping
 from .job_names import JobNames
 from .job_record import JobRecord
 from .job_record_with_usage_metrics import JobRecordWithUsageMetrics
+from .llama_extract_settings import LlamaExtractSettings
 from .llama_index_core_base_llms_types_chat_message import LlamaIndexCoreBaseLlmsTypesChatMessage
 from .llama_index_core_base_llms_types_chat_message_blocks_item import (
     LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem,
@@ -174,6 +176,7 @@ from .open_ai_embedding import OpenAiEmbedding
 from .open_ai_embedding_config import OpenAiEmbeddingConfig
 from .organization import Organization
 from .organization_create import OrganizationCreate
+from .page_figure_metadata import PageFigureMetadata
 from .page_screenshot_metadata import PageScreenshotMetadata
 from .page_screenshot_node_with_score import PageScreenshotNodeWithScore
 from .page_segmentation_config import PageSegmentationConfig
@@ -350,6 +353,7 @@ __all__ = [
     "CompositeRetrievalMode",
     "CompositeRetrievalResult",
     "CompositeRetrievedTextNode",
+    "CompositeRetrievedTextNodeWithScore",
     "ConfigurableDataSinkNames",
     "ConfigurableDataSourceNames",
     "ConfigurableTransformationDefinition",
@@ -409,11 +413,11 @@ __all__ = [
     "ExtractResultsetDataItemValue",
     "ExtractResultsetDataZeroValue",
     "ExtractResultsetExtractionMetadataValue",
-    "ExtractionJob",
-    "ExtractionResult",
-    "ExtractionResultDataValue",
-    "ExtractionSchema",
-    "ExtractionSchemaDataSchemaValue",
+    "ExtractRun",
+    "ExtractRunDataSchemaValue",
+    "ExtractRunDataValue",
+    "ExtractRunExtractionMetadataValue",
+    "ExtractState",
     "File",
     "FilePermissionInfoValue",
     "FileResourceInfoValue",
@@ -433,6 +437,7 @@ __all__ = [
     "JobNames",
     "JobRecord",
     "JobRecordWithUsageMetrics",
+    "LlamaExtractSettings",
     "LlamaIndexCoreBaseLlmsTypesChatMessage",
     "LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem",
     "LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Image",
@@ -465,6 +470,7 @@ __all__ = [
     "OpenAiEmbeddingConfig",
     "Organization",
     "OrganizationCreate",
+    "PageFigureMetadata",
     "PageScreenshotMetadata",
     "PageScreenshotNodeWithScore",
     "PageSegmentationConfig",

llama_cloud/types/composite_retrieval_result.py

@@ -4,7 +4,7 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
-from .composite_retrieved_text_node import CompositeRetrievedTextNode
+from .composite_retrieved_text_node_with_score import CompositeRetrievedTextNodeWithScore
 from .page_screenshot_node_with_score import PageScreenshotNodeWithScore
 
 try:
@@ -17,7 +17,7 @@ except ImportError:
 
 
 class CompositeRetrievalResult(pydantic.BaseModel):
-    nodes: typing.Optional[typing.List[CompositeRetrievedTextNode]] = pydantic.Field(
+    nodes: typing.Optional[typing.List[CompositeRetrievedTextNodeWithScore]] = pydantic.Field(
         description="The retrieved nodes from the composite retrieval."
     )
     image_nodes: typing.Optional[typing.List[PageScreenshotNodeWithScore]] = pydantic.Field(