llama-cloud 0.1.9__py3-none-any.whl → 0.1.10__py3-none-any.whl

llama_cloud/resources/llama_extract/types/__init__.py

@@ -1,6 +1,17 @@
 # This file was auto-generated by Fern from our API Definition.
 
-from .extract_agent_create_data_schema_value import ExtractAgentCreateDataSchemaValue
-from .extract_agent_update_data_schema_value import ExtractAgentUpdateDataSchemaValue
+from .extract_agent_create_data_schema import ExtractAgentCreateDataSchema
+from .extract_agent_create_data_schema_zero_value import ExtractAgentCreateDataSchemaZeroValue
+from .extract_agent_update_data_schema import ExtractAgentUpdateDataSchema
+from .extract_agent_update_data_schema_zero_value import ExtractAgentUpdateDataSchemaZeroValue
+from .extract_schema_validate_request_data_schema import ExtractSchemaValidateRequestDataSchema
+from .extract_schema_validate_request_data_schema_zero_value import ExtractSchemaValidateRequestDataSchemaZeroValue
 
-__all__ = ["ExtractAgentCreateDataSchemaValue", "ExtractAgentUpdateDataSchemaValue"]
+__all__ = [
+    "ExtractAgentCreateDataSchema",
+    "ExtractAgentCreateDataSchemaZeroValue",
+    "ExtractAgentUpdateDataSchema",
+    "ExtractAgentUpdateDataSchemaZeroValue",
+    "ExtractSchemaValidateRequestDataSchema",
+    "ExtractSchemaValidateRequestDataSchemaZeroValue",
+]

llama_cloud/resources/llama_extract/types/extract_agent_create_data_schema.py

@@ -0,0 +1,9 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+from .extract_agent_create_data_schema_zero_value import ExtractAgentCreateDataSchemaZeroValue
+
+ExtractAgentCreateDataSchema = typing.Union[
+    typing.Dict[str, typing.Optional[ExtractAgentCreateDataSchemaZeroValue]], str
+]

llama_cloud/resources/llama_extract/types/{extract_agent_create_data_schema_value.py → extract_agent_create_data_schema_zero_value.py}

@@ -2,6 +2,6 @@
 
 import typing
 
-ExtractAgentCreateDataSchemaValue = typing.Union[
+ExtractAgentCreateDataSchemaZeroValue = typing.Union[
     typing.Dict[str, typing.Any], typing.List[typing.Any], str, int, float, bool
 ]

llama_cloud/resources/llama_extract/types/extract_agent_update_data_schema.py

@@ -0,0 +1,9 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+from .extract_agent_update_data_schema_zero_value import ExtractAgentUpdateDataSchemaZeroValue
+
+ExtractAgentUpdateDataSchema = typing.Union[
+    typing.Dict[str, typing.Optional[ExtractAgentUpdateDataSchemaZeroValue]], str
+]

llama_cloud/resources/llama_extract/types/{extract_agent_update_data_schema_value.py → extract_agent_update_data_schema_zero_value.py}

@@ -2,6 +2,6 @@
 
 import typing
 
-ExtractAgentUpdateDataSchemaValue = typing.Union[
+ExtractAgentUpdateDataSchemaZeroValue = typing.Union[
     typing.Dict[str, typing.Any], typing.List[typing.Any], str, int, float, bool
 ]

llama_cloud/resources/llama_extract/types/extract_schema_validate_request_data_schema.py

@@ -0,0 +1,9 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+from .extract_schema_validate_request_data_schema_zero_value import ExtractSchemaValidateRequestDataSchemaZeroValue
+
+ExtractSchemaValidateRequestDataSchema = typing.Union[
+    typing.Dict[str, typing.Optional[ExtractSchemaValidateRequestDataSchemaZeroValue]], str
+]

llama_cloud/resources/llama_extract/types/extract_schema_validate_request_data_schema_zero_value.py

@@ -0,0 +1,7 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+ExtractSchemaValidateRequestDataSchemaZeroValue = typing.Union[
+    typing.Dict[str, typing.Any], typing.List[typing.Any], str, int, float, bool
+]

llama_cloud/resources/organizations/client.py

@@ -229,14 +229,14 @@ class OrganizationsClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    def update_organization(self, organization_id: str, *, name: typing.Optional[str] = OMIT) -> Organization:
+    def update_organization(self, organization_id: str, *, name: str) -> Organization:
         """
         Update an existing organization.
 
         Parameters:
             - organization_id: str.
 
-            - name: typing.Optional[str].
+            - name: str. A name for the organization.
         ---
         from llama_cloud.client import LlamaCloud
 
@@ -245,15 +245,13 @@ class OrganizationsClient:
         )
         client.organizations.update_organization(
             organization_id="string",
+            name="string",
         )
         """
-        _request: typing.Dict[str, typing.Any] = {}
-        if name is not OMIT:
-            _request["name"] = name
         _response = self._client_wrapper.httpx_client.request(
             "PUT",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/organizations/{organization_id}"),
-            json=jsonable_encoder(_request),
+            json=jsonable_encoder({"name": name}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
@@ -922,14 +920,14 @@ class AsyncOrganizationsClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    async def update_organization(self, organization_id: str, *, name: typing.Optional[str] = OMIT) -> Organization:
+    async def update_organization(self, organization_id: str, *, name: str) -> Organization:
         """
         Update an existing organization.
 
         Parameters:
             - organization_id: str.
 
-            - name: typing.Optional[str].
+            - name: str. A name for the organization.
         ---
         from llama_cloud.client import AsyncLlamaCloud
 
@@ -938,15 +936,13 @@ class AsyncOrganizationsClient:
         )
         await client.organizations.update_organization(
             organization_id="string",
+            name="string",
         )
         """
-        _request: typing.Dict[str, typing.Any] = {}
-        if name is not OMIT:
-            _request["name"] = name
         _response = await self._client_wrapper.httpx_client.request(
             "PUT",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/organizations/{organization_id}"),
-            json=jsonable_encoder(_request),
+            json=jsonable_encoder({"name": name}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )

llama_cloud/resources/parsing/client.py

@@ -166,6 +166,14 @@ class ParsingClient:
         bounding_box: str,
         gpt_4_o_mode: bool,
         gpt_4_o_api_key: str,
+        job_timeout_in_seconds: float,
+        job_timeout_extra_time_per_page_in_seconds: float,
+        strict_mode_image_extraction: bool,
+        strict_mode_image_ocr: bool,
+        strict_mode_reconstruction: bool,
+        strict_mode_buggy_font: bool,
+        ignore_document_elements_for_layout_detection: bool,
+        output_tables_as_html: bool,
     ) -> ParsingJob:
         """
         Upload a file to s3 and create a job. return a job id
@@ -296,6 +304,22 @@ class ParsingClient:
             - gpt_4_o_mode: bool.
 
             - gpt_4_o_api_key: str.
+
+            - job_timeout_in_seconds: float.
+
+            - job_timeout_extra_time_per_page_in_seconds: float.
+
+            - strict_mode_image_extraction: bool.
+
+            - strict_mode_image_ocr: bool.
+
+            - strict_mode_reconstruction: bool.
+
+            - strict_mode_buggy_font: bool.
+
+            - ignore_document_elements_for_layout_detection: bool.
+
+            - output_tables_as_html: bool.
         """
         _request: typing.Dict[str, typing.Any] = {
             "annotate_links": annotate_links,
@@ -357,6 +381,14 @@ class ParsingClient:
             "bounding_box": bounding_box,
             "gpt4o_mode": gpt_4_o_mode,
             "gpt4o_api_key": gpt_4_o_api_key,
+            "job_timeout_in_seconds": job_timeout_in_seconds,
+            "job_timeout_extra_time_per_page_in_seconds": job_timeout_extra_time_per_page_in_seconds,
+            "strict_mode_image_extraction": strict_mode_image_extraction,
+            "strict_mode_image_ocr": strict_mode_image_ocr,
+            "strict_mode_reconstruction": strict_mode_reconstruction,
+            "strict_mode_buggy_font": strict_mode_buggy_font,
+            "ignore_document_elements_for_layout_detection": ignore_document_elements_for_layout_detection,
+            "output_tables_as_HTML": output_tables_as_html,
         }
         if file is not OMIT:
             _request["file"] = file
@@ -991,6 +1023,14 @@ class AsyncParsingClient:
         bounding_box: str,
         gpt_4_o_mode: bool,
         gpt_4_o_api_key: str,
+        job_timeout_in_seconds: float,
+        job_timeout_extra_time_per_page_in_seconds: float,
+        strict_mode_image_extraction: bool,
+        strict_mode_image_ocr: bool,
+        strict_mode_reconstruction: bool,
+        strict_mode_buggy_font: bool,
+        ignore_document_elements_for_layout_detection: bool,
+        output_tables_as_html: bool,
     ) -> ParsingJob:
         """
         Upload a file to s3 and create a job. return a job id
@@ -1121,6 +1161,22 @@ class AsyncParsingClient:
             - gpt_4_o_mode: bool.
 
             - gpt_4_o_api_key: str.
+
+            - job_timeout_in_seconds: float.
+
+            - job_timeout_extra_time_per_page_in_seconds: float.
+
+            - strict_mode_image_extraction: bool.
+
+            - strict_mode_image_ocr: bool.
+
+            - strict_mode_reconstruction: bool.
+
+            - strict_mode_buggy_font: bool.
+
+            - ignore_document_elements_for_layout_detection: bool.
+
+            - output_tables_as_html: bool.
         """
         _request: typing.Dict[str, typing.Any] = {
             "annotate_links": annotate_links,
@@ -1182,6 +1238,14 @@ class AsyncParsingClient:
             "bounding_box": bounding_box,
             "gpt4o_mode": gpt_4_o_mode,
             "gpt4o_api_key": gpt_4_o_api_key,
+            "job_timeout_in_seconds": job_timeout_in_seconds,
+            "job_timeout_extra_time_per_page_in_seconds": job_timeout_extra_time_per_page_in_seconds,
+            "strict_mode_image_extraction": strict_mode_image_extraction,
+            "strict_mode_image_ocr": strict_mode_image_ocr,
+            "strict_mode_reconstruction": strict_mode_reconstruction,
+            "strict_mode_buggy_font": strict_mode_buggy_font,
+            "ignore_document_elements_for_layout_detection": ignore_document_elements_for_layout_detection,
+            "output_tables_as_HTML": output_tables_as_html,
         }
         if file is not OMIT:
             _request["file"] = file

llama_cloud/resources/reports/client.py

@@ -47,9 +47,10 @@ class ReportsClient:
         organization_id: typing.Optional[str] = None,
         name: str,
         template_text: str,
-        template_instructions: str,
+        template_instructions: typing.Optional[str] = OMIT,
+        existing_retriever_id: typing.Optional[str] = OMIT,
         files: typing.List[str],
-        template_file: typing.IO,
+        template_file: typing.Optional[str] = OMIT,
     ) -> ReportCreateResponse:
         """
         Create a new report.
@@ -63,25 +64,26 @@ class ReportsClient:
 
             - template_text: str.
 
-            - template_instructions: str.
+            - template_instructions: typing.Optional[str].
+
+            - existing_retriever_id: typing.Optional[str].
 
             - files: typing.List[str].
 
-            - template_file: typing.IO.
+            - template_file: typing.Optional[str].
         """
+        _request: typing.Dict[str, typing.Any] = {"name": name, "template_text": template_text, "files": files}
+        if template_instructions is not OMIT:
+            _request["template_instructions"] = template_instructions
+        if existing_retriever_id is not OMIT:
+            _request["existing_retriever_id"] = existing_retriever_id
+        if template_file is not OMIT:
+            _request["template_file"] = template_file
         _response = self._client_wrapper.httpx_client.request(
             "POST",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/reports"),
             params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
-            data=jsonable_encoder(
-                {
-                    "name": name,
-                    "template_text": template_text,
-                    "template_instructions": template_instructions,
-                    "files": files,
-                }
-            ),
-            files={"template_file": template_file},
+            json=jsonable_encoder(_request),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
@@ -628,9 +630,10 @@ class AsyncReportsClient:
         organization_id: typing.Optional[str] = None,
         name: str,
         template_text: str,
-        template_instructions: str,
+        template_instructions: typing.Optional[str] = OMIT,
+        existing_retriever_id: typing.Optional[str] = OMIT,
         files: typing.List[str],
-        template_file: typing.IO,
+        template_file: typing.Optional[str] = OMIT,
     ) -> ReportCreateResponse:
         """
         Create a new report.
@@ -644,25 +647,26 @@ class AsyncReportsClient:
 
             - template_text: str.
 
-            - template_instructions: str.
+            - template_instructions: typing.Optional[str].
+
+            - existing_retriever_id: typing.Optional[str].
 
             - files: typing.List[str].
 
-            - template_file: typing.IO.
+            - template_file: typing.Optional[str].
         """
+        _request: typing.Dict[str, typing.Any] = {"name": name, "template_text": template_text, "files": files}
+        if template_instructions is not OMIT:
+            _request["template_instructions"] = template_instructions
+        if existing_retriever_id is not OMIT:
+            _request["existing_retriever_id"] = existing_retriever_id
+        if template_file is not OMIT:
+            _request["template_file"] = template_file
         _response = await self._client_wrapper.httpx_client.request(
             "POST",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/reports"),
             params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
-            data=jsonable_encoder(
-                {
-                    "name": name,
-                    "template_text": template_text,
-                    "template_instructions": template_instructions,
-                    "files": files,
-                }
-            ),
-            files={"template_file": template_file},
+            json=jsonable_encoder(_request),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )

llama_cloud/resources/retrievers/client.py

@@ -33,12 +33,18 @@ class RetrieversClient:
         self._client_wrapper = client_wrapper
 
     def list_retrievers(
-        self, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
+        self,
+        *,
+        name: typing.Optional[str] = None,
+        project_id: typing.Optional[str] = None,
+        organization_id: typing.Optional[str] = None,
     ) -> typing.List[Retriever]:
         """
         List Retrievers for a project.
 
         Parameters:
+            - name: typing.Optional[str].
+
             - project_id: typing.Optional[str].
 
             - organization_id: typing.Optional[str].
@@ -53,7 +59,7 @@ class RetrieversClient:
         _response = self._client_wrapper.httpx_client.request(
             "GET",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/retrievers"),
-            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
+            params=remove_none_from_dict({"name": name, "project_id": project_id, "organization_id": organization_id}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
@@ -346,12 +352,18 @@ class AsyncRetrieversClient:
         self._client_wrapper = client_wrapper
 
     async def list_retrievers(
-        self, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
+        self,
+        *,
+        name: typing.Optional[str] = None,
+        project_id: typing.Optional[str] = None,
+        organization_id: typing.Optional[str] = None,
     ) -> typing.List[Retriever]:
         """
         List Retrievers for a project.
 
         Parameters:
+            - name: typing.Optional[str].
+
             - project_id: typing.Optional[str].
 
             - organization_id: typing.Optional[str].
@@ -366,7 +378,7 @@ class AsyncRetrieversClient:
         _response = await self._client_wrapper.httpx_client.request(
             "GET",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/retrievers"),
-            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
+            params=remove_none_from_dict({"name": name, "project_id": project_id, "organization_id": organization_id}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )

llama_cloud/types/__init__.py

@@ -110,7 +110,8 @@ from .extract_agent_data_schema_value import ExtractAgentDataSchemaValue
 from .extract_config import ExtractConfig
 from .extract_job import ExtractJob
 from .extract_job_create import ExtractJobCreate
-from .extract_job_create_data_schema_override_value import ExtractJobCreateDataSchemaOverrideValue
+from .extract_job_create_data_schema_override import ExtractJobCreateDataSchemaOverride
+from .extract_job_create_data_schema_override_zero_value import ExtractJobCreateDataSchemaOverrideZeroValue
 from .extract_mode import ExtractMode
 from .extract_resultset import ExtractResultset
 from .extract_resultset_data import ExtractResultsetData
@@ -118,9 +119,13 @@ 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 import ExtractRunData
+from .extract_run_data_item_value import ExtractRunDataItemValue
 from .extract_run_data_schema_value import ExtractRunDataSchemaValue
-from .extract_run_data_value import ExtractRunDataValue
+from .extract_run_data_zero_value import ExtractRunDataZeroValue
 from .extract_run_extraction_metadata_value import ExtractRunExtractionMetadataValue
+from .extract_schema_validate_response import ExtractSchemaValidateResponse
+from .extract_schema_validate_response_data_schema_value import ExtractSchemaValidateResponseDataSchemaValue
 from .extract_state import ExtractState
 from .file import File
 from .file_permission_info_value import FilePermissionInfoValue
@@ -240,6 +245,7 @@ from .pipeline_type import PipelineType
 from .plan import Plan
 from .playground_session import PlaygroundSession
 from .pooling import Pooling
+from .preset_composite_retrieval_params import PresetCompositeRetrievalParams
 from .preset_retrieval_params import PresetRetrievalParams
 from .presigned_url import PresignedUrl
 from .progress_event import ProgressEvent
@@ -263,6 +269,7 @@ from .report_event_item_event_data import (
     ReportEventItemEventData_ReportStateUpdate,
 )
 from .report_event_type import ReportEventType
+from .report_file_info import ReportFileInfo
 from .report_metadata import ReportMetadata
 from .report_plan import ReportPlan
 from .report_plan_block import ReportPlanBlock
@@ -406,7 +413,8 @@ __all__ = [
     "ExtractConfig",
     "ExtractJob",
     "ExtractJobCreate",
-    "ExtractJobCreateDataSchemaOverrideValue",
+    "ExtractJobCreateDataSchemaOverride",
+    "ExtractJobCreateDataSchemaOverrideZeroValue",
     "ExtractMode",
     "ExtractResultset",
     "ExtractResultsetData",
@@ -414,9 +422,13 @@ __all__ = [
     "ExtractResultsetDataZeroValue",
     "ExtractResultsetExtractionMetadataValue",
     "ExtractRun",
+    "ExtractRunData",
+    "ExtractRunDataItemValue",
     "ExtractRunDataSchemaValue",
-    "ExtractRunDataValue",
+    "ExtractRunDataZeroValue",
     "ExtractRunExtractionMetadataValue",
+    "ExtractSchemaValidateResponse",
+    "ExtractSchemaValidateResponseDataSchemaValue",
     "ExtractState",
     "File",
     "FilePermissionInfoValue",
@@ -528,6 +540,7 @@ __all__ = [
     "Plan",
     "PlaygroundSession",
     "Pooling",
+    "PresetCompositeRetrievalParams",
     "PresetRetrievalParams",
     "PresignedUrl",
     "ProgressEvent",
@@ -549,6 +562,7 @@ __all__ = [
     "ReportEventItemEventData_ReportBlockUpdate",
     "ReportEventItemEventData_ReportStateUpdate",
     "ReportEventType",
+    "ReportFileInfo",
     "ReportMetadata",
     "ReportPlan",
     "ReportPlanBlock",

llama_cloud/types/chat_app.py

@@ -5,7 +5,7 @@ import typing
 
 from ..core.datetime_utils import serialize_datetime
 from .llm_parameters import LlmParameters
-from .preset_retrieval_params import PresetRetrievalParams
+from .preset_composite_retrieval_params import PresetCompositeRetrievalParams
 
 try:
     import pydantic
@@ -21,14 +21,16 @@ class ChatApp(pydantic.BaseModel):
     Schema for a chat app
     """
 
-    id: str
-    name: str
-    pipeline_id: str
-    project_id: str
-    llm_config: LlmParameters
-    retrieval_config: PresetRetrievalParams
-    created_at: dt.datetime
-    updated_at: dt.datetime
+    id: str = pydantic.Field(description="Unique identifier")
+    created_at: typing.Optional[dt.datetime]
+    updated_at: typing.Optional[dt.datetime]
+    name: str = pydantic.Field(description="Name of the chat app")
+    retriever_id: str = pydantic.Field(description="ID of the retriever to use for the chat app")
+    llm_config: LlmParameters = pydantic.Field(description="Configuration for the LLM model to use for the chat app")
+    retrieval_config: PresetCompositeRetrievalParams = pydantic.Field(
+        description="Configuration for the retrieval model to use for the chat app"
+    )
+    project_id: str = pydantic.Field(description="ID of the project the chat app belongs to")
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/chat_app_response.py

@@ -5,7 +5,7 @@ import typing
 
 from ..core.datetime_utils import serialize_datetime
 from .llm_parameters import LlmParameters
-from .preset_retrieval_params import PresetRetrievalParams
+from .preset_composite_retrieval_params import PresetCompositeRetrievalParams
 
 try:
     import pydantic
@@ -17,15 +17,17 @@ except ImportError:
 
 
 class ChatAppResponse(pydantic.BaseModel):
-    id: str
-    name: str
-    pipeline_id: str
-    project_id: str
-    llm_config: LlmParameters
-    retrieval_config: PresetRetrievalParams
-    created_at: dt.datetime
-    updated_at: dt.datetime
-    pipeline_name: str
+    id: str = pydantic.Field(description="Unique identifier")
+    created_at: typing.Optional[dt.datetime]
+    updated_at: typing.Optional[dt.datetime]
+    name: str = pydantic.Field(description="Name of the chat app")
+    retriever_id: str = pydantic.Field(description="ID of the retriever to use for the chat app")
+    llm_config: LlmParameters = pydantic.Field(description="Configuration for the LLM model to use for the chat app")
+    retrieval_config: PresetCompositeRetrievalParams = pydantic.Field(
+        description="Configuration for the retrieval model to use for the chat app"
+    )
+    project_id: str = pydantic.Field(description="ID of the project the chat app belongs to")
+    retriever_name: str
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/cloud_mongo_db_atlas_vector_search.py

@@ -35,6 +35,7 @@ class CloudMongoDbAtlasVectorSearch(pydantic.BaseModel):
     collection_name: str
     vector_index_name: typing.Optional[str]
     fulltext_index_name: typing.Optional[str]
+    embedding_dimension: typing.Optional[int]
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/extract_job_create.py

@@ -5,7 +5,7 @@ import typing
 
 from ..core.datetime_utils import serialize_datetime
 from .extract_config import ExtractConfig
-from .extract_job_create_data_schema_override_value import ExtractJobCreateDataSchemaOverrideValue
+from .extract_job_create_data_schema_override import ExtractJobCreateDataSchemaOverride
 
 try:
     import pydantic
@@ -23,7 +23,9 @@ class ExtractJobCreate(pydantic.BaseModel):
 
     extraction_agent_id: str = pydantic.Field(description="The id of the extraction agent")
     file_id: str = pydantic.Field(description="The id of the file")
-    data_schema_override: typing.Optional[typing.Dict[str, typing.Optional[ExtractJobCreateDataSchemaOverrideValue]]]
+    data_schema_override: typing.Optional[ExtractJobCreateDataSchemaOverride] = pydantic.Field(
+        description="The data schema to override the extraction agent's data schema with"
+    )
     config_override: typing.Optional[ExtractConfig]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/extract_job_create_data_schema_override.py

@@ -0,0 +1,9 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+from .extract_job_create_data_schema_override_zero_value import ExtractJobCreateDataSchemaOverrideZeroValue
+
+ExtractJobCreateDataSchemaOverride = typing.Union[
+    typing.Dict[str, typing.Optional[ExtractJobCreateDataSchemaOverrideZeroValue]], str
+]

llama_cloud/types/{extract_job_create_data_schema_override_value.py → extract_job_create_data_schema_override_zero_value.py}

@@ -2,6 +2,6 @@
 
 import typing
 
-ExtractJobCreateDataSchemaOverrideValue = typing.Union[
+ExtractJobCreateDataSchemaOverrideZeroValue = typing.Union[
     typing.Dict[str, typing.Any], typing.List[typing.Any], str, int, float, bool
 ]

llama_cloud/types/extract_run.py

@@ -5,8 +5,8 @@ import typing
 
 from ..core.datetime_utils import serialize_datetime
 from .extract_config import ExtractConfig
+from .extract_run_data import ExtractRunData
 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
@@ -37,7 +37,7 @@ class ExtractRun(pydantic.BaseModel):
     status: ExtractState = pydantic.Field(description="The status of the extraction run")
     error: typing.Optional[str]
     job_id: typing.Optional[str]
-    data: typing.Optional[typing.Dict[str, typing.Optional[ExtractRunDataValue]]]
+    data: typing.Optional[ExtractRunData] = pydantic.Field(description="The data extracted from the file")
     extraction_metadata: typing.Optional[typing.Dict[str, typing.Optional[ExtractRunExtractionMetadataValue]]]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/extract_run_data.py

@@ -0,0 +1,11 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+from .extract_run_data_item_value import ExtractRunDataItemValue
+from .extract_run_data_zero_value import ExtractRunDataZeroValue
+
+ExtractRunData = typing.Union[
+    typing.Dict[str, typing.Optional[ExtractRunDataZeroValue]],
+    typing.List[typing.Dict[str, typing.Optional[ExtractRunDataItemValue]]],
+]

llama_cloud/types/extract_run_data_item_value.py

@@ -0,0 +1,5 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+ExtractRunDataItemValue = typing.Union[typing.Dict[str, typing.Any], typing.List[typing.Any], str, int, float, bool]

llama_cloud/types/extract_run_data_zero_value.py

@@ -0,0 +1,5 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+ExtractRunDataZeroValue = typing.Union[typing.Dict[str, typing.Any], typing.List[typing.Any], str, int, float, bool]