llama-cloud 0.1.22__py3-none-any.whl → 0.1.24__py3-none-any.whl

llama_cloud/resources/pipelines/client.py

@@ -17,6 +17,7 @@ from ...types.eval_execution_params import EvalExecutionParams
 from ...types.file_count_by_status_response import FileCountByStatusResponse
 from ...types.http_validation_error import HttpValidationError
 from ...types.input_message import InputMessage
+from ...types.json_type import JsonType
 from ...types.llama_parse_parameters import LlamaParseParameters
 from ...types.managed_ingestion_status_response import ManagedIngestionStatusResponse
 from ...types.metadata_filters import MetadataFilters
@@ -36,7 +37,6 @@ from ...types.preset_retrieval_params import PresetRetrievalParams
 from ...types.retrieval_mode import RetrievalMode
 from ...types.retrieve_results import RetrieveResults
 from ...types.text_node import TextNode
-from .types.pipeline_file_update_custom_metadata_value import PipelineFileUpdateCustomMetadataValue
 from .types.pipeline_update_embedding_config import PipelineUpdateEmbeddingConfig
 from .types.pipeline_update_transform_config import PipelineUpdateTransformConfig
 
@@ -63,6 +63,7 @@ class PipelinesClient:
         project_name: typing.Optional[str] = None,
         pipeline_name: typing.Optional[str] = None,
         pipeline_type: typing.Optional[PipelineType] = None,
+        organization_id: typing.Optional[str] = None,
     ) -> typing.List[Pipeline]:
         """
         Search for pipelines by various parameters.
@@ -75,6 +76,8 @@ class PipelinesClient:
             - pipeline_name: typing.Optional[str].
 
             - pipeline_type: typing.Optional[PipelineType].
+
+            - organization_id: typing.Optional[str].
         ---
         from llama_cloud import PipelineType
         from llama_cloud.client import LlamaCloud
@@ -95,6 +98,7 @@ class PipelinesClient:
                     "project_name": project_name,
                     "pipeline_name": pipeline_name,
                     "pipeline_type": pipeline_type,
+                    "organization_id": organization_id,
                 }
             ),
             headers=self._client_wrapper.get_headers(),
@@ -658,9 +662,7 @@ class PipelinesClient:
         file_id: str,
         pipeline_id: str,
         *,
-        custom_metadata: typing.Optional[
-            typing.Dict[str, typing.Optional[PipelineFileUpdateCustomMetadataValue]]
-        ] = OMIT,
+        custom_metadata: typing.Optional[typing.Dict[str, typing.Optional[JsonType]]] = OMIT,
     ) -> PipelineFile:
         """
         Update a file for a pipeline.
@@ -670,7 +672,7 @@ class PipelinesClient:
 
             - pipeline_id: str.
 
-            - custom_metadata: typing.Optional[typing.Dict[str, typing.Optional[PipelineFileUpdateCustomMetadataValue]]].
+            - custom_metadata: typing.Optional[typing.Dict[str, typing.Optional[JsonType]]].
         ---
         from llama_cloud.client import LlamaCloud
 
@@ -1037,9 +1039,12 @@ class PipelinesClient:
         rerank_top_n: typing.Optional[int] = OMIT,
         alpha: typing.Optional[float] = OMIT,
         search_filters: typing.Optional[MetadataFilters] = OMIT,
+        search_filters_inference_schema: typing.Optional[typing.Dict[str, typing.Optional[JsonType]]] = OMIT,
         files_top_k: typing.Optional[int] = OMIT,
         retrieval_mode: typing.Optional[RetrievalMode] = OMIT,
         retrieve_image_nodes: typing.Optional[bool] = OMIT,
+        retrieve_page_screenshot_nodes: typing.Optional[bool] = OMIT,
+        retrieve_page_figure_nodes: typing.Optional[bool] = OMIT,
         query: str,
         class_name: typing.Optional[str] = OMIT,
     ) -> RetrieveResults:
@@ -1067,12 +1072,18 @@ class PipelinesClient:
 
             - search_filters: typing.Optional[MetadataFilters].
 
+            - search_filters_inference_schema: typing.Optional[typing.Dict[str, typing.Optional[JsonType]]].
+
             - files_top_k: typing.Optional[int].
 
             - retrieval_mode: typing.Optional[RetrievalMode]. The retrieval mode for the query.
 
             - retrieve_image_nodes: typing.Optional[bool]. Whether to retrieve image nodes.
 
+            - retrieve_page_screenshot_nodes: typing.Optional[bool]. Whether to retrieve page screenshot nodes.
+
+            - retrieve_page_figure_nodes: typing.Optional[bool]. Whether to retrieve page figure nodes.
+
             - query: str. The query to retrieve against.
 
             - class_name: typing.Optional[str].
@@ -1108,12 +1119,18 @@ class PipelinesClient:
             _request["alpha"] = alpha
         if search_filters is not OMIT:
             _request["search_filters"] = search_filters
+        if search_filters_inference_schema is not OMIT:
+            _request["search_filters_inference_schema"] = search_filters_inference_schema
         if files_top_k is not OMIT:
             _request["files_top_k"] = files_top_k
         if retrieval_mode is not OMIT:
             _request["retrieval_mode"] = retrieval_mode
         if retrieve_image_nodes is not OMIT:
             _request["retrieve_image_nodes"] = retrieve_image_nodes
+        if retrieve_page_screenshot_nodes is not OMIT:
+            _request["retrieve_page_screenshot_nodes"] = retrieve_page_screenshot_nodes
+        if retrieve_page_figure_nodes is not OMIT:
+            _request["retrieve_page_figure_nodes"] = retrieve_page_figure_nodes
         if class_name is not OMIT:
             _request["class_name"] = class_name
         _response = self._client_wrapper.httpx_client.request(
@@ -1681,6 +1698,7 @@ class AsyncPipelinesClient:
         project_name: typing.Optional[str] = None,
         pipeline_name: typing.Optional[str] = None,
         pipeline_type: typing.Optional[PipelineType] = None,
+        organization_id: typing.Optional[str] = None,
     ) -> typing.List[Pipeline]:
         """
         Search for pipelines by various parameters.
@@ -1693,6 +1711,8 @@ class AsyncPipelinesClient:
             - pipeline_name: typing.Optional[str].
 
             - pipeline_type: typing.Optional[PipelineType].
+
+            - organization_id: typing.Optional[str].
         ---
         from llama_cloud import PipelineType
         from llama_cloud.client import AsyncLlamaCloud
@@ -1713,6 +1733,7 @@ class AsyncPipelinesClient:
                     "project_name": project_name,
                     "pipeline_name": pipeline_name,
                     "pipeline_type": pipeline_type,
+                    "organization_id": organization_id,
                 }
             ),
             headers=self._client_wrapper.get_headers(),
@@ -2276,9 +2297,7 @@ class AsyncPipelinesClient:
         file_id: str,
         pipeline_id: str,
         *,
-        custom_metadata: typing.Optional[
-            typing.Dict[str, typing.Optional[PipelineFileUpdateCustomMetadataValue]]
-        ] = OMIT,
+        custom_metadata: typing.Optional[typing.Dict[str, typing.Optional[JsonType]]] = OMIT,
     ) -> PipelineFile:
         """
         Update a file for a pipeline.
@@ -2288,7 +2307,7 @@ class AsyncPipelinesClient:
 
             - pipeline_id: str.
 
-            - custom_metadata: typing.Optional[typing.Dict[str, typing.Optional[PipelineFileUpdateCustomMetadataValue]]].
+            - custom_metadata: typing.Optional[typing.Dict[str, typing.Optional[JsonType]]].
         ---
         from llama_cloud.client import AsyncLlamaCloud
 
@@ -2657,9 +2676,12 @@ class AsyncPipelinesClient:
         rerank_top_n: typing.Optional[int] = OMIT,
         alpha: typing.Optional[float] = OMIT,
         search_filters: typing.Optional[MetadataFilters] = OMIT,
+        search_filters_inference_schema: typing.Optional[typing.Dict[str, typing.Optional[JsonType]]] = OMIT,
         files_top_k: typing.Optional[int] = OMIT,
         retrieval_mode: typing.Optional[RetrievalMode] = OMIT,
         retrieve_image_nodes: typing.Optional[bool] = OMIT,
+        retrieve_page_screenshot_nodes: typing.Optional[bool] = OMIT,
+        retrieve_page_figure_nodes: typing.Optional[bool] = OMIT,
         query: str,
         class_name: typing.Optional[str] = OMIT,
     ) -> RetrieveResults:
@@ -2687,12 +2709,18 @@ class AsyncPipelinesClient:
 
             - search_filters: typing.Optional[MetadataFilters].
 
+            - search_filters_inference_schema: typing.Optional[typing.Dict[str, typing.Optional[JsonType]]].
+
             - files_top_k: typing.Optional[int].
 
             - retrieval_mode: typing.Optional[RetrievalMode]. The retrieval mode for the query.
 
             - retrieve_image_nodes: typing.Optional[bool]. Whether to retrieve image nodes.
 
+            - retrieve_page_screenshot_nodes: typing.Optional[bool]. Whether to retrieve page screenshot nodes.
+
+            - retrieve_page_figure_nodes: typing.Optional[bool]. Whether to retrieve page figure nodes.
+
             - query: str. The query to retrieve against.
 
             - class_name: typing.Optional[str].
@@ -2728,12 +2756,18 @@ class AsyncPipelinesClient:
             _request["alpha"] = alpha
         if search_filters is not OMIT:
             _request["search_filters"] = search_filters
+        if search_filters_inference_schema is not OMIT:
+            _request["search_filters_inference_schema"] = search_filters_inference_schema
         if files_top_k is not OMIT:
             _request["files_top_k"] = files_top_k
         if retrieval_mode is not OMIT:
             _request["retrieval_mode"] = retrieval_mode
         if retrieve_image_nodes is not OMIT:
             _request["retrieve_image_nodes"] = retrieve_image_nodes
+        if retrieve_page_screenshot_nodes is not OMIT:
+            _request["retrieve_page_screenshot_nodes"] = retrieve_page_screenshot_nodes
+        if retrieve_page_figure_nodes is not OMIT:
+            _request["retrieve_page_figure_nodes"] = retrieve_page_figure_nodes
         if class_name is not OMIT:
             _request["class_name"] = class_name
         _response = await self._client_wrapper.httpx_client.request(

llama_cloud/resources/pipelines/types/__init__.py

@@ -1,6 +1,5 @@
 # This file was auto-generated by Fern from our API Definition.
 
-from .pipeline_file_update_custom_metadata_value import PipelineFileUpdateCustomMetadataValue
 from .pipeline_update_embedding_config import (
     PipelineUpdateEmbeddingConfig,
     PipelineUpdateEmbeddingConfig_AzureEmbedding,
@@ -14,7 +13,6 @@ from .pipeline_update_embedding_config import (
 from .pipeline_update_transform_config import PipelineUpdateTransformConfig
 
 __all__ = [
-    "PipelineFileUpdateCustomMetadataValue",
     "PipelineUpdateEmbeddingConfig",
     "PipelineUpdateEmbeddingConfig_AzureEmbedding",
     "PipelineUpdateEmbeddingConfig_BedrockEmbedding",

llama_cloud/types/__init__.py

@@ -72,8 +72,6 @@ from .data_source import DataSource
 from .data_source_component import DataSourceComponent
 from .data_source_create import DataSourceCreate
 from .data_source_create_component import DataSourceCreateComponent
-from .data_source_create_custom_metadata_value import DataSourceCreateCustomMetadataValue
-from .data_source_custom_metadata_value import DataSourceCustomMetadataValue
 from .data_source_update_dispatcher_config import DataSourceUpdateDispatcherConfig
 from .delete_params import DeleteParams
 from .document_block import DocumentBlock
@@ -106,35 +104,24 @@ from .embedding_model_config_update_embedding_config import (
 )
 from .eval_execution_params import EvalExecutionParams
 from .extract_agent import ExtractAgent
-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 import ExtractJobCreateDataSchemaOverride
-from .extract_job_create_data_schema_override_zero_value import ExtractJobCreateDataSchemaOverrideZeroValue
 from .extract_mode import ExtractMode
 from .extract_models import ExtractModels
 from .extract_resultset import ExtractResultset
 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 import ExtractRunData
-from .extract_run_data_item_value import ExtractRunDataItemValue
-from .extract_run_data_schema_value import ExtractRunDataSchemaValue
-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 .extract_target import ExtractTarget
 from .fail_page_mode import FailPageMode
 from .file import File
 from .file_count_by_status_response import FileCountByStatusResponse
+from .file_id_presigned_url import FileIdPresignedUrl
 from .file_parse_public import FileParsePublic
-from .file_permission_info_value import FilePermissionInfoValue
-from .file_resource_info_value import FileResourceInfoValue
 from .filter_condition import FilterCondition
 from .filter_operator import FilterOperator
 from .free_credits_usage import FreeCreditsUsage
@@ -163,6 +150,7 @@ from .job_record_parameters import (
     JobRecordParameters_PipelineManagedIngestion,
 )
 from .job_record_with_usage_metrics import JobRecordWithUsageMetrics
+from .json_type import JsonType
 from .l_lama_parse_transform_config import LLamaParseTransformConfig
 from .legacy_parse_job_config import LegacyParseJobConfig
 from .llama_extract_settings import LlamaExtractSettings
@@ -176,9 +164,6 @@ from .llama_index_core_base_llms_types_chat_message_blocks_item import (
 )
 from .llama_parse_parameters import LlamaParseParameters
 from .llama_parse_supported_file_extensions import LlamaParseSupportedFileExtensions
-from .llm_config_result import LlmConfigResult
-from .llm_config_result_llm_type import LlmConfigResultLlmType
-from .llm_configs_response import LlmConfigsResponse
 from .llm_model_data import LlmModelData
 from .llm_parameters import LlmParameters
 from .load_files_job_config import LoadFilesJobConfig
@@ -199,6 +184,7 @@ from .open_ai_embedding_config import OpenAiEmbeddingConfig
 from .organization import Organization
 from .organization_create import OrganizationCreate
 from .page_figure_metadata import PageFigureMetadata
+from .page_figure_node_with_score import PageFigureNodeWithScore
 from .page_screenshot_metadata import PageScreenshotMetadata
 from .page_screenshot_node_with_score import PageScreenshotNodeWithScore
 from .page_segmentation_config import PageSegmentationConfig
@@ -239,7 +225,6 @@ from .pipeline_create_transform_config import PipelineCreateTransformConfig
 from .pipeline_data_source import PipelineDataSource
 from .pipeline_data_source_component import PipelineDataSourceComponent
 from .pipeline_data_source_create import PipelineDataSourceCreate
-from .pipeline_data_source_custom_metadata_value import PipelineDataSourceCustomMetadataValue
 from .pipeline_data_source_status import PipelineDataSourceStatus
 from .pipeline_deployment import PipelineDeployment
 from .pipeline_embedding_config import (
@@ -253,12 +238,7 @@ from .pipeline_embedding_config import (
     PipelineEmbeddingConfig_VertexaiEmbedding,
 )
 from .pipeline_file import PipelineFile
-from .pipeline_file_config_hash_value import PipelineFileConfigHashValue
 from .pipeline_file_create import PipelineFileCreate
-from .pipeline_file_create_custom_metadata_value import PipelineFileCreateCustomMetadataValue
-from .pipeline_file_custom_metadata_value import PipelineFileCustomMetadataValue
-from .pipeline_file_permission_info_value import PipelineFilePermissionInfoValue
-from .pipeline_file_resource_info_value import PipelineFileResourceInfoValue
 from .pipeline_file_status import PipelineFileStatus
 from .pipeline_file_update_dispatcher_config import PipelineFileUpdateDispatcherConfig
 from .pipeline_file_updater_config import PipelineFileUpdaterConfig
@@ -410,8 +390,6 @@ __all__ = [
     "DataSourceComponent",
     "DataSourceCreate",
     "DataSourceCreateComponent",
-    "DataSourceCreateCustomMetadataValue",
-    "DataSourceCustomMetadataValue",
     "DataSourceUpdateDispatcherConfig",
     "DeleteParams",
     "DocumentBlock",
@@ -440,35 +418,24 @@ __all__ = [
     "EmbeddingModelConfigUpdateEmbeddingConfig_VertexaiEmbedding",
     "EvalExecutionParams",
     "ExtractAgent",
-    "ExtractAgentDataSchemaValue",
     "ExtractConfig",
     "ExtractJob",
     "ExtractJobCreate",
     "ExtractJobCreateDataSchemaOverride",
-    "ExtractJobCreateDataSchemaOverrideZeroValue",
     "ExtractMode",
     "ExtractModels",
     "ExtractResultset",
     "ExtractResultsetData",
-    "ExtractResultsetDataItemValue",
-    "ExtractResultsetDataZeroValue",
-    "ExtractResultsetExtractionMetadataValue",
     "ExtractRun",
     "ExtractRunData",
-    "ExtractRunDataItemValue",
-    "ExtractRunDataSchemaValue",
-    "ExtractRunDataZeroValue",
-    "ExtractRunExtractionMetadataValue",
     "ExtractSchemaValidateResponse",
-    "ExtractSchemaValidateResponseDataSchemaValue",
     "ExtractState",
     "ExtractTarget",
     "FailPageMode",
     "File",
     "FileCountByStatusResponse",
+    "FileIdPresignedUrl",
     "FileParsePublic",
-    "FilePermissionInfoValue",
-    "FileResourceInfoValue",
     "FilterCondition",
     "FilterOperator",
     "FreeCreditsUsage",
@@ -495,6 +462,7 @@ __all__ = [
     "JobRecordParameters_PipelineFileUpdater",
     "JobRecordParameters_PipelineManagedIngestion",
     "JobRecordWithUsageMetrics",
+    "JsonType",
     "LLamaParseTransformConfig",
     "LegacyParseJobConfig",
     "LlamaExtractSettings",
@@ -506,9 +474,6 @@ __all__ = [
     "LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Text",
     "LlamaParseParameters",
     "LlamaParseSupportedFileExtensions",
-    "LlmConfigResult",
-    "LlmConfigResultLlmType",
-    "LlmConfigsResponse",
     "LlmModelData",
     "LlmParameters",
     "LoadFilesJobConfig",
@@ -529,6 +494,7 @@ __all__ = [
     "Organization",
     "OrganizationCreate",
     "PageFigureMetadata",
+    "PageFigureNodeWithScore",
     "PageScreenshotMetadata",
     "PageScreenshotNodeWithScore",
     "PageSegmentationConfig",
@@ -567,7 +533,6 @@ __all__ = [
     "PipelineDataSource",
     "PipelineDataSourceComponent",
     "PipelineDataSourceCreate",
-    "PipelineDataSourceCustomMetadataValue",
     "PipelineDataSourceStatus",
     "PipelineDeployment",
     "PipelineEmbeddingConfig",
@@ -579,12 +544,7 @@ __all__ = [
     "PipelineEmbeddingConfig_OpenaiEmbedding",
     "PipelineEmbeddingConfig_VertexaiEmbedding",
     "PipelineFile",
-    "PipelineFileConfigHashValue",
     "PipelineFileCreate",
-    "PipelineFileCreateCustomMetadataValue",
-    "PipelineFileCustomMetadataValue",
-    "PipelineFilePermissionInfoValue",
-    "PipelineFileResourceInfoValue",
     "PipelineFileStatus",
     "PipelineFileUpdateDispatcherConfig",
     "PipelineFileUpdaterConfig",

llama_cloud/types/composite_retrieval_result.py

@@ -5,6 +5,7 @@ import typing
 
 from ..core.datetime_utils import serialize_datetime
 from .composite_retrieved_text_node_with_score import CompositeRetrievedTextNodeWithScore
+from .page_figure_node_with_score import PageFigureNodeWithScore
 from .page_screenshot_node_with_score import PageScreenshotNodeWithScore
 
 try:
@@ -21,7 +22,10 @@ class CompositeRetrievalResult(pydantic.BaseModel):
         description="The retrieved nodes from the composite retrieval."
     )
     image_nodes: typing.Optional[typing.List[PageScreenshotNodeWithScore]] = pydantic.Field(
-        description="The image nodes retrieved by the pipeline for the given query."
+        description="The image nodes retrieved by the pipeline for the given query. Deprecated - will soon be replaced with 'page_screenshot_nodes'."
+    )
+    page_figure_nodes: typing.Optional[typing.List[PageFigureNodeWithScore]] = pydantic.Field(
+        description="The page figure nodes retrieved by the pipeline for the given query."
     )
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/data_source.py

@@ -6,7 +6,7 @@ import typing
 from ..core.datetime_utils import serialize_datetime
 from .configurable_data_source_names import ConfigurableDataSourceNames
 from .data_source_component import DataSourceComponent
-from .data_source_custom_metadata_value import DataSourceCustomMetadataValue
+from .json_type import JsonType
 
 try:
     import pydantic
@@ -27,7 +27,7 @@ class DataSource(pydantic.BaseModel):
     updated_at: typing.Optional[dt.datetime]
     name: str = pydantic.Field(description="The name of the data source.")
     source_type: ConfigurableDataSourceNames
-    custom_metadata: typing.Optional[typing.Dict[str, typing.Optional[DataSourceCustomMetadataValue]]]
+    custom_metadata: typing.Optional[typing.Dict[str, typing.Optional[JsonType]]]
     component: DataSourceComponent = pydantic.Field(description="Component that implements the data source")
     version_metadata: typing.Optional[typing.Dict[str, typing.Any]]
     project_id: str

llama_cloud/types/data_source_create.py

@@ -6,7 +6,7 @@ import typing
 from ..core.datetime_utils import serialize_datetime
 from .configurable_data_source_names import ConfigurableDataSourceNames
 from .data_source_create_component import DataSourceCreateComponent
-from .data_source_create_custom_metadata_value import DataSourceCreateCustomMetadataValue
+from .json_type import JsonType
 
 try:
     import pydantic
@@ -24,7 +24,7 @@ class DataSourceCreate(pydantic.BaseModel):
 
     name: str = pydantic.Field(description="The name of the data source.")
     source_type: ConfigurableDataSourceNames
-    custom_metadata: typing.Optional[typing.Dict[str, typing.Optional[DataSourceCreateCustomMetadataValue]]]
+    custom_metadata: typing.Optional[typing.Dict[str, typing.Optional[JsonType]]]
     component: DataSourceCreateComponent = pydantic.Field(description="Component that implements the data source")
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/extract_agent.py

@@ -4,8 +4,8 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
-from .extract_agent_data_schema_value import ExtractAgentDataSchemaValue
 from .extract_config import ExtractConfig
+from .json_type import JsonType
 
 try:
     import pydantic
@@ -24,9 +24,7 @@ class ExtractAgent(pydantic.BaseModel):
     id: str = pydantic.Field(description="The id of the extraction agent.")
     name: str = pydantic.Field(description="The name of the extraction agent.")
     project_id: str = pydantic.Field(description="The ID of the project that the extraction agent belongs to.")
-    data_schema: typing.Dict[str, typing.Optional[ExtractAgentDataSchemaValue]] = pydantic.Field(
-        description="The schema of the data."
-    )
+    data_schema: typing.Dict[str, typing.Optional[JsonType]] = pydantic.Field(description="The schema of the data.")
     config: ExtractConfig = pydantic.Field(description="The configuration parameters for the extraction agent.")
     created_at: typing.Optional[dt.datetime]
     updated_at: typing.Optional[dt.datetime]

llama_cloud/types/extract_job_create_data_schema_override.py

@@ -2,8 +2,6 @@
 
 import typing
 
-from .extract_job_create_data_schema_override_zero_value import ExtractJobCreateDataSchemaOverrideZeroValue
+from .json_type import JsonType
 
-ExtractJobCreateDataSchemaOverride = typing.Union[
-    typing.Dict[str, typing.Optional[ExtractJobCreateDataSchemaOverrideZeroValue]], str
-]
+ExtractJobCreateDataSchemaOverride = typing.Union[typing.Dict[str, typing.Optional[JsonType]], str]

llama_cloud/types/extract_models.py

@@ -7,27 +7,39 @@ T_Result = typing.TypeVar("T_Result")
 
 
 class ExtractModels(str, enum.Enum):
-    GPT_4_O = "gpt-4o"
-    GPT_4_O_MINI = "gpt-4o-mini"
     GPT_41 = "gpt-4.1"
     GPT_41_MINI = "gpt-4.1-mini"
+    GEMINI_20_FLASH = "gemini-2.0-flash"
     O_3_MINI = "o3-mini"
+    GEMINI_25_FLASH = "gemini-2.5-flash"
+    GEMINI_25_PRO = "gemini-2.5-pro"
+    GPT_4_O = "gpt-4o"
+    GPT_4_O_MINI = "gpt-4o-mini"
 
     def visit(
         self,
-        gpt_4_o: typing.Callable[[], T_Result],
-        gpt_4_o_mini: typing.Callable[[], T_Result],
         gpt_41: typing.Callable[[], T_Result],
         gpt_41_mini: typing.Callable[[], T_Result],
+        gemini_20_flash: typing.Callable[[], T_Result],
         o_3_mini: typing.Callable[[], T_Result],
+        gemini_25_flash: typing.Callable[[], T_Result],
+        gemini_25_pro: typing.Callable[[], T_Result],
+        gpt_4_o: typing.Callable[[], T_Result],
+        gpt_4_o_mini: typing.Callable[[], T_Result],
     ) -> T_Result:
-        if self is ExtractModels.GPT_4_O:
-            return gpt_4_o()
-        if self is ExtractModels.GPT_4_O_MINI:
-            return gpt_4_o_mini()
         if self is ExtractModels.GPT_41:
             return gpt_41()
         if self is ExtractModels.GPT_41_MINI:
             return gpt_41_mini()
+        if self is ExtractModels.GEMINI_20_FLASH:
+            return gemini_20_flash()
         if self is ExtractModels.O_3_MINI:
             return o_3_mini()
+        if self is ExtractModels.GEMINI_25_FLASH:
+            return gemini_25_flash()
+        if self is ExtractModels.GEMINI_25_PRO:
+            return gemini_25_pro()
+        if self is ExtractModels.GPT_4_O:
+            return gpt_4_o()
+        if self is ExtractModels.GPT_4_O_MINI:
+            return gpt_4_o_mini()

llama_cloud/types/extract_resultset.py

@@ -5,7 +5,7 @@ import typing
 
 from ..core.datetime_utils import serialize_datetime
 from .extract_resultset_data import ExtractResultsetData
-from .extract_resultset_extraction_metadata_value import ExtractResultsetExtractionMetadataValue
+from .json_type import JsonType
 
 try:
     import pydantic
@@ -24,7 +24,7 @@ class ExtractResultset(pydantic.BaseModel):
     run_id: str = pydantic.Field(description="The id of the extraction run")
     extraction_agent_id: str = pydantic.Field(description="The id of the extraction agent")
     data: typing.Optional[ExtractResultsetData] = pydantic.Field(description="The data extracted from the file")
-    extraction_metadata: typing.Dict[str, typing.Optional[ExtractResultsetExtractionMetadataValue]] = pydantic.Field(
+    extraction_metadata: typing.Dict[str, typing.Optional[JsonType]] = pydantic.Field(
         description="The metadata extracted from the file"
     )
 

llama_cloud/types/extract_resultset_data.py

@@ -2,10 +2,8 @@
 
 import typing
 
-from .extract_resultset_data_item_value import ExtractResultsetDataItemValue
-from .extract_resultset_data_zero_value import ExtractResultsetDataZeroValue
+from .json_type import JsonType
 
 ExtractResultsetData = typing.Union[
-    typing.Dict[str, typing.Optional[ExtractResultsetDataZeroValue]],
-    typing.List[typing.Dict[str, typing.Optional[ExtractResultsetDataItemValue]]],
+    typing.Dict[str, typing.Optional[JsonType]], typing.List[typing.Dict[str, typing.Optional[JsonType]]]
 ]

llama_cloud/types/extract_run.py

@@ -6,10 +6,9 @@ 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_extraction_metadata_value import ExtractRunExtractionMetadataValue
 from .extract_state import ExtractState
 from .file import File
+from .json_type import JsonType
 
 try:
     import pydantic
@@ -29,7 +28,7 @@ class ExtractRun(pydantic.BaseModel):
     created_at: typing.Optional[dt.datetime]
     updated_at: typing.Optional[dt.datetime]
     extraction_agent_id: str = pydantic.Field(description="The id of the extraction agent")
-    data_schema: typing.Dict[str, typing.Optional[ExtractRunDataSchemaValue]] = pydantic.Field(
+    data_schema: typing.Dict[str, typing.Optional[JsonType]] = pydantic.Field(
         description="The schema used for extraction"
     )
     config: ExtractConfig = pydantic.Field(description="The config used for extraction")
@@ -38,7 +37,7 @@ class ExtractRun(pydantic.BaseModel):
     error: typing.Optional[str]
     job_id: typing.Optional[str]
     data: typing.Optional[ExtractRunData] = pydantic.Field(description="The data extracted from the file")
-    extraction_metadata: typing.Optional[typing.Dict[str, typing.Optional[ExtractRunExtractionMetadataValue]]]
+    extraction_metadata: typing.Optional[typing.Dict[str, typing.Optional[JsonType]]]
     from_ui: bool = pydantic.Field(description="Whether this extraction run was triggered from the UI")
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/extract_run_data.py

@@ -2,10 +2,8 @@
 
 import typing
 
-from .extract_run_data_item_value import ExtractRunDataItemValue
-from .extract_run_data_zero_value import ExtractRunDataZeroValue
+from .json_type import JsonType
 
 ExtractRunData = typing.Union[
-    typing.Dict[str, typing.Optional[ExtractRunDataZeroValue]],
-    typing.List[typing.Dict[str, typing.Optional[ExtractRunDataItemValue]]],
+    typing.Dict[str, typing.Optional[JsonType]], typing.List[typing.Dict[str, typing.Optional[JsonType]]]
 ]

llama_cloud/types/extract_schema_validate_response.py

@@ -4,7 +4,7 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
-from .extract_schema_validate_response_data_schema_value import ExtractSchemaValidateResponseDataSchemaValue
+from .json_type import JsonType
 
 try:
     import pydantic
@@ -16,7 +16,7 @@ except ImportError:
 
 
 class ExtractSchemaValidateResponse(pydantic.BaseModel):
-    data_schema: typing.Dict[str, typing.Optional[ExtractSchemaValidateResponseDataSchemaValue]]
+    data_schema: typing.Dict[str, typing.Optional[JsonType]]
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/file.py

@@ -4,8 +4,7 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
-from .file_permission_info_value import FilePermissionInfoValue
-from .file_resource_info_value import FileResourceInfoValue
+from .json_type import JsonType
 
 try:
     import pydantic
@@ -30,8 +29,8 @@ class File(pydantic.BaseModel):
     file_type: typing.Optional[str]
     project_id: str = pydantic.Field(description="The ID of the project that the file belongs to")
     last_modified_at: typing.Optional[dt.datetime]
-    resource_info: typing.Optional[typing.Dict[str, typing.Optional[FileResourceInfoValue]]]
-    permission_info: typing.Optional[typing.Dict[str, typing.Optional[FilePermissionInfoValue]]]
+    resource_info: typing.Optional[typing.Dict[str, typing.Optional[JsonType]]]
+    permission_info: typing.Optional[typing.Dict[str, typing.Optional[JsonType]]]
     data_source_id: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str: