llama-cloud 0.1.7a1__py3-none-any.whl → 0.1.8__py3-none-any.whl

llama_cloud/resources/llama_extract/client.py

@@ -14,7 +14,9 @@ from ...types.extract_config import ExtractConfig
 from ...types.extract_job import ExtractJob
 from ...types.extract_job_create import ExtractJobCreate
 from ...types.extract_resultset import ExtractResultset
+from ...types.extract_run import ExtractRun
 from ...types.http_validation_error import HttpValidationError
+from ...types.llama_extract_settings import LlamaExtractSettings
 from .types.extract_agent_create_data_schema_value import ExtractAgentCreateDataSchemaValue
 from .types.extract_agent_update_data_schema_value import ExtractAgentUpdateDataSchemaValue
 
@@ -122,6 +124,45 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    def get_extraction_agent_by_name(
+        self, *, name: str, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
+    ) -> ExtractAgent:
+        """
+        Parameters:
+            - name: str.
+
+            - project_id: typing.Optional[str].
+
+            - organization_id: typing.Optional[str].
+        ---
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.llama_extract.get_extraction_agent_by_name(
+            name="string",
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", "api/v1/extractionv2/extraction_agents/by_name"
+            ),
+            params=remove_none_from_dict({"name": name, "project_id": project_id, "organization_id": organization_id}),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ExtractAgent, _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_extraction_agent(
         self,
         extraction_agent_id: str,
@@ -399,6 +440,67 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    def run_job_with_parsed_file_test(
+        self,
+        *,
+        project_id: typing.Optional[str] = None,
+        organization_id: typing.Optional[str] = None,
+        job_create: ExtractJobCreate,
+        extract_settings: typing.Optional[LlamaExtractSettings] = OMIT,
+    ) -> typing.Optional[ExtractResultset]:
+        """
+        Parameters:
+            - project_id: typing.Optional[str].
+
+            - organization_id: typing.Optional[str].
+
+            - job_create: ExtractJobCreate.
+
+            - extract_settings: typing.Optional[LlamaExtractSettings].
+        ---
+        from llama_cloud import (
+            ExtractConfig,
+            ExtractJobCreate,
+            ExtractMode,
+            LlamaExtractSettings,
+        )
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.llama_extract.run_job_with_parsed_file_test(
+            job_create=ExtractJobCreate(
+                extraction_agent_id="string",
+                file_id="string",
+                config_override=ExtractConfig(
+                    extraction_mode=ExtractMode.PER_DOC,
+                ),
+            ),
+            extract_settings=LlamaExtractSettings(),
+        )
+        """
+        _request: typing.Dict[str, typing.Any] = {"job_create": job_create}
+        if extract_settings is not OMIT:
+            _request["extract_settings"] = extract_settings
+        _response = self._client_wrapper.httpx_client.request(
+            "POST",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extractionv2/jobs/parsed/test"),
+            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
+            json=jsonable_encoder(_request),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(typing.Optional[ExtractResultset], _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 run_job_with_parsed_file(
         self,
         *,
@@ -448,6 +550,67 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    def run_job_test_user(
+        self,
+        *,
+        project_id: typing.Optional[str] = None,
+        organization_id: typing.Optional[str] = None,
+        job_create: ExtractJobCreate,
+        extract_settings: typing.Optional[LlamaExtractSettings] = OMIT,
+    ) -> ExtractJob:
+        """
+        Parameters:
+            - project_id: typing.Optional[str].
+
+            - organization_id: typing.Optional[str].
+
+            - job_create: ExtractJobCreate.
+
+            - extract_settings: typing.Optional[LlamaExtractSettings].
+        ---
+        from llama_cloud import (
+            ExtractConfig,
+            ExtractJobCreate,
+            ExtractMode,
+            LlamaExtractSettings,
+        )
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.llama_extract.run_job_test_user(
+            job_create=ExtractJobCreate(
+                extraction_agent_id="string",
+                file_id="string",
+                config_override=ExtractConfig(
+                    extraction_mode=ExtractMode.PER_DOC,
+                ),
+            ),
+            extract_settings=LlamaExtractSettings(),
+        )
+        """
+        _request: typing.Dict[str, typing.Any] = {"job_create": job_create}
+        if extract_settings is not OMIT:
+            _request["extract_settings"] = extract_settings
+        _response = self._client_wrapper.httpx_client.request(
+            "POST",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extractionv2/jobs/test"),
+            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
+            json=jsonable_encoder(_request),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ExtractJob, _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 run_jobs_in_batch(
         self,
         *,
@@ -533,6 +696,43 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    def get_extract_run_api_v_1_extractionv_2_runs_run_id_get(
+        self, run_id: str, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
+    ) -> ExtractRun:
+        """
+        Parameters:
+            - run_id: str.
+
+            - project_id: typing.Optional[str].
+
+            - organization_id: typing.Optional[str].
+        ---
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.llama_extract.get_extract_run_api_v_1_extractionv_2_runs_run_id_get(
+            run_id="string",
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extractionv2/runs/{run_id}"),
+            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ExtractRun, _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)
+
 
 class AsyncLlamaExtractClient:
     def __init__(self, *, client_wrapper: AsyncClientWrapper):
@@ -626,6 +826,45 @@ class AsyncLlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    async def get_extraction_agent_by_name(
+        self, *, name: str, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
+    ) -> ExtractAgent:
+        """
+        Parameters:
+            - name: str.
+
+            - project_id: typing.Optional[str].
+
+            - organization_id: typing.Optional[str].
+        ---
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.llama_extract.get_extraction_agent_by_name(
+            name="string",
+        )
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", "api/v1/extractionv2/extraction_agents/by_name"
+            ),
+            params=remove_none_from_dict({"name": name, "project_id": project_id, "organization_id": organization_id}),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ExtractAgent, _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_extraction_agent(
         self,
         extraction_agent_id: str,
@@ -903,6 +1142,67 @@ class AsyncLlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    async def run_job_with_parsed_file_test(
+        self,
+        *,
+        project_id: typing.Optional[str] = None,
+        organization_id: typing.Optional[str] = None,
+        job_create: ExtractJobCreate,
+        extract_settings: typing.Optional[LlamaExtractSettings] = OMIT,
+    ) -> typing.Optional[ExtractResultset]:
+        """
+        Parameters:
+            - project_id: typing.Optional[str].
+
+            - organization_id: typing.Optional[str].
+
+            - job_create: ExtractJobCreate.
+
+            - extract_settings: typing.Optional[LlamaExtractSettings].
+        ---
+        from llama_cloud import (
+            ExtractConfig,
+            ExtractJobCreate,
+            ExtractMode,
+            LlamaExtractSettings,
+        )
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.llama_extract.run_job_with_parsed_file_test(
+            job_create=ExtractJobCreate(
+                extraction_agent_id="string",
+                file_id="string",
+                config_override=ExtractConfig(
+                    extraction_mode=ExtractMode.PER_DOC,
+                ),
+            ),
+            extract_settings=LlamaExtractSettings(),
+        )
+        """
+        _request: typing.Dict[str, typing.Any] = {"job_create": job_create}
+        if extract_settings is not OMIT:
+            _request["extract_settings"] = extract_settings
+        _response = await self._client_wrapper.httpx_client.request(
+            "POST",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extractionv2/jobs/parsed/test"),
+            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
+            json=jsonable_encoder(_request),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(typing.Optional[ExtractResultset], _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 run_job_with_parsed_file(
         self,
         *,
@@ -952,6 +1252,67 @@ class AsyncLlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    async def run_job_test_user(
+        self,
+        *,
+        project_id: typing.Optional[str] = None,
+        organization_id: typing.Optional[str] = None,
+        job_create: ExtractJobCreate,
+        extract_settings: typing.Optional[LlamaExtractSettings] = OMIT,
+    ) -> ExtractJob:
+        """
+        Parameters:
+            - project_id: typing.Optional[str].
+
+            - organization_id: typing.Optional[str].
+
+            - job_create: ExtractJobCreate.
+
+            - extract_settings: typing.Optional[LlamaExtractSettings].
+        ---
+        from llama_cloud import (
+            ExtractConfig,
+            ExtractJobCreate,
+            ExtractMode,
+            LlamaExtractSettings,
+        )
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.llama_extract.run_job_test_user(
+            job_create=ExtractJobCreate(
+                extraction_agent_id="string",
+                file_id="string",
+                config_override=ExtractConfig(
+                    extraction_mode=ExtractMode.PER_DOC,
+                ),
+            ),
+            extract_settings=LlamaExtractSettings(),
+        )
+        """
+        _request: typing.Dict[str, typing.Any] = {"job_create": job_create}
+        if extract_settings is not OMIT:
+            _request["extract_settings"] = extract_settings
+        _response = await self._client_wrapper.httpx_client.request(
+            "POST",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extractionv2/jobs/test"),
+            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
+            json=jsonable_encoder(_request),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ExtractJob, _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 run_jobs_in_batch(
         self,
         *,
@@ -1036,3 +1397,40 @@ class AsyncLlamaExtractClient:
         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_extract_run_api_v_1_extractionv_2_runs_run_id_get(
+        self, run_id: str, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
+    ) -> ExtractRun:
+        """
+        Parameters:
+            - run_id: str.
+
+            - project_id: typing.Optional[str].
+
+            - organization_id: typing.Optional[str].
+        ---
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.llama_extract.get_extract_run_api_v_1_extractionv_2_runs_run_id_get(
+            run_id="string",
+        )
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extractionv2/runs/{run_id}"),
+            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ExtractRun, _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)

llama_cloud/resources/parsing/client.py

@@ -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,
@@ -128,6 +130,7 @@ 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,
@@ -199,6 +202,10 @@ class ParsingClient:
 
             - bbox_top: float.
 
+            - complemental_formatting_instruction: str.
+
+            - content_guideline_instruction: str.
+
             - continuous_mode: bool.
 
             - disable_ocr: bool.
@@ -215,6 +222,8 @@ class ParsingClient:
 
             - fast_mode: bool.
 
+            - formatting_instruction: str.
+
             - guess_xlsx_sheet_name: bool.
 
             - html_make_all_elements_visible: bool.
@@ -294,6 +303,8 @@ 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,
@@ -302,6 +313,7 @@ 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,
@@ -904,6 +916,8 @@ 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,
@@ -912,6 +926,7 @@ 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,
@@ -983,6 +998,10 @@ class AsyncParsingClient:
 
             - bbox_top: float.
 
+            - complemental_formatting_instruction: str.
+
+            - content_guideline_instruction: str.
+
             - continuous_mode: bool.
 
             - disable_ocr: bool.
@@ -999,6 +1018,8 @@ class AsyncParsingClient:
 
             - fast_mode: bool.
 
+            - formatting_instruction: str.
+
             - guess_xlsx_sheet_name: bool.
 
             - html_make_all_elements_visible: bool.
@@ -1078,6 +1099,8 @@ 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,
@@ -1086,6 +1109,7 @@ 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,

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
@@ -116,6 +117,9 @@ 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 .extract_run import ExtractRun
+from .extract_run_data_schema_value import ExtractRunDataSchemaValue
+from .extract_state import ExtractState
 from .extraction_job import ExtractionJob
 from .extraction_result import ExtractionResult
 from .extraction_result_data_value import ExtractionResultDataValue
@@ -140,6 +144,7 @@ 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 +179,7 @@ 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 +356,7 @@ __all__ = [
     "CompositeRetrievalMode",
     "CompositeRetrievalResult",
     "CompositeRetrievedTextNode",
+    "CompositeRetrievedTextNodeWithScore",
     "ConfigurableDataSinkNames",
     "ConfigurableDataSourceNames",
     "ConfigurableTransformationDefinition",
@@ -409,6 +416,9 @@ __all__ = [
     "ExtractResultsetDataItemValue",
     "ExtractResultsetDataZeroValue",
     "ExtractResultsetExtractionMetadataValue",
+    "ExtractRun",
+    "ExtractRunDataSchemaValue",
+    "ExtractState",
     "ExtractionJob",
     "ExtractionResult",
     "ExtractionResultDataValue",
@@ -433,6 +443,7 @@ __all__ = [
     "JobNames",
     "JobRecord",
     "JobRecordWithUsageMetrics",
+    "LlamaExtractSettings",
     "LlamaIndexCoreBaseLlmsTypesChatMessage",
     "LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem",
     "LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Image",
@@ -465,6 +476,7 @@ __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(