llama-cloud 0.1.19__py3-none-any.whl → 0.1.21__py3-none-any.whl

llama_cloud/__init__.py

@@ -21,7 +21,6 @@ from .types import (
     BasePlanMetronomePlanType,
     BasePlanName,
     BasePlanPlanFrequency,
-    BasePromptTemplate,
     Batch,
     BatchItem,
     BatchPaginatedList,
@@ -31,7 +30,6 @@ from .types import (
     BillingPeriod,
     BoxAuthMechanism,
     CharacterChunkingConfig,
-    CharacterSplitter,
     ChatApp,
     ChatAppResponse,
     ChatData,
@@ -54,7 +52,6 @@ from .types import (
     CloudS3DataSource,
     CloudSharepointDataSource,
     CloudSlackDataSource,
-    CodeSplitter,
     CohereEmbedding,
     CohereEmbeddingConfig,
     CompositeRetrievalMode,
@@ -65,8 +62,6 @@ from .types import (
     ConfigurableDataSourceNames,
     ConfigurableTransformationDefinition,
     ConfigurableTransformationNames,
-    ConfiguredTransformationItem,
-    ConfiguredTransformationItemComponent,
     CreditType,
     DataSink,
     DataSinkComponent,
@@ -80,6 +75,9 @@ from .types import (
     DataSourceCreateCustomMetadataValue,
     DataSourceCustomMetadataValue,
     DataSourceDefinition,
+    DataSourceUpdateDispatcherConfig,
+    DeleteParams,
+    DocumentIngestionJobParams,
     EditSuggestion,
     EditSuggestionBlocksItem,
     ElementSegmentationConfig,
@@ -146,7 +144,19 @@ from .types import (
     JobNameMapping,
     JobNames,
     JobRecord,
+    JobRecordParameters,
+    JobRecordParameters_DataSourceUpdateDispatcher,
+    JobRecordParameters_DocumentIngestion,
+    JobRecordParameters_LegacyParse,
+    JobRecordParameters_LlamaParseTransform,
+    JobRecordParameters_LoadFiles,
+    JobRecordParameters_Parse,
+    JobRecordParameters_PipelineFileUpdateDispatcher,
+    JobRecordParameters_PipelineFileUpdater,
+    JobRecordParameters_PipelineManagedIngestion,
     JobRecordWithUsageMetrics,
+    LLamaParseTransformConfig,
+    LegacyParseJobConfig,
     LlamaExtractSettings,
     LlamaIndexCoreBaseLlmsTypesChatMessage,
     LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem,
@@ -155,20 +165,17 @@ from .types import (
     LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Text,
     LlamaParseParameters,
     LlamaParseSupportedFileExtensions,
-    Llm,
     LlmModelData,
     LlmParameters,
+    LoadFilesJobConfig,
     ManagedIngestionStatus,
     ManagedIngestionStatusResponse,
-    MarkdownElementNodeParser,
-    MarkdownNodeParser,
     MessageAnnotation,
     MessageRole,
     MetadataFilter,
     MetadataFilterValue,
     MetadataFilters,
     MetadataFiltersFiltersItem,
-    NodeParser,
     NodeRelationship,
     NoneChunkingConfig,
     NoneSegmentationConfig,
@@ -181,12 +188,12 @@ from .types import (
     PageScreenshotMetadata,
     PageScreenshotNodeWithScore,
     PageSegmentationConfig,
-    PageSplitterNodeParser,
     PaginatedExtractRunsResponse,
     PaginatedJobsHistoryWithMetrics,
     PaginatedListCloudDocumentsResponse,
     PaginatedListPipelineFilesResponse,
     PaginatedReportResponse,
+    ParseJobConfig,
     ParsePlanLevel,
     ParserLanguages,
     ParsingHistoryItem,
@@ -235,6 +242,11 @@ from .types import (
     PipelineFilePermissionInfoValue,
     PipelineFileResourceInfoValue,
     PipelineFileStatus,
+    PipelineFileUpdateDispatcherConfig,
+    PipelineFileUpdaterConfig,
+    PipelineManagedIngestionJobParams,
+    PipelineMetadataConfig,
+    PipelineStatus,
     PipelineTransformConfig,
     PipelineTransformConfig_Advanced,
     PipelineTransformConfig_Auto,
@@ -250,7 +262,6 @@ from .types import (
     Project,
     ProjectCreate,
     PromptConf,
-    PydanticProgramMode,
     ReRankConfig,
     ReRankerType,
     RecurringCreditGrant,
@@ -283,7 +294,6 @@ from .types import (
     SchemaRelaxMode,
     SemanticChunkingConfig,
     SentenceChunkingConfig,
-    SentenceSplitter,
     StatusEnum,
     StructMode,
     StructParseConf,
@@ -294,7 +304,6 @@ from .types import (
     TextNodeRelationshipsValue,
     TextNodeWithScore,
     TokenChunkingConfig,
-    TokenTextSplitter,
     TransformationCategoryNames,
     UsageAndPlan,
     UsageMetricResponse,
@@ -386,7 +395,6 @@ __all__ = [
     "BasePlanMetronomePlanType",
     "BasePlanName",
     "BasePlanPlanFrequency",
-    "BasePromptTemplate",
     "Batch",
     "BatchItem",
     "BatchPaginatedList",
@@ -396,7 +404,6 @@ __all__ = [
     "BillingPeriod",
     "BoxAuthMechanism",
     "CharacterChunkingConfig",
-    "CharacterSplitter",
     "ChatApp",
     "ChatAppResponse",
     "ChatData",
@@ -419,7 +426,6 @@ __all__ = [
     "CloudS3DataSource",
     "CloudSharepointDataSource",
     "CloudSlackDataSource",
-    "CodeSplitter",
     "CohereEmbedding",
     "CohereEmbeddingConfig",
     "CompositeRetrievalMode",
@@ -430,8 +436,6 @@ __all__ = [
     "ConfigurableDataSourceNames",
     "ConfigurableTransformationDefinition",
     "ConfigurableTransformationNames",
-    "ConfiguredTransformationItem",
-    "ConfiguredTransformationItemComponent",
     "CreditType",
     "DataSink",
     "DataSinkComponent",
@@ -448,6 +452,9 @@ __all__ = [
     "DataSourceDefinition",
     "DataSourceUpdateComponent",
     "DataSourceUpdateCustomMetadataValue",
+    "DataSourceUpdateDispatcherConfig",
+    "DeleteParams",
+    "DocumentIngestionJobParams",
     "EditSuggestion",
     "EditSuggestionBlocksItem",
     "ElementSegmentationConfig",
@@ -533,7 +540,19 @@ __all__ = [
     "JobNameMapping",
     "JobNames",
     "JobRecord",
+    "JobRecordParameters",
+    "JobRecordParameters_DataSourceUpdateDispatcher",
+    "JobRecordParameters_DocumentIngestion",
+    "JobRecordParameters_LegacyParse",
+    "JobRecordParameters_LlamaParseTransform",
+    "JobRecordParameters_LoadFiles",
+    "JobRecordParameters_Parse",
+    "JobRecordParameters_PipelineFileUpdateDispatcher",
+    "JobRecordParameters_PipelineFileUpdater",
+    "JobRecordParameters_PipelineManagedIngestion",
     "JobRecordWithUsageMetrics",
+    "LLamaParseTransformConfig",
+    "LegacyParseJobConfig",
     "LlamaCloudEnvironment",
     "LlamaExtractSettings",
     "LlamaIndexCoreBaseLlmsTypesChatMessage",
@@ -543,20 +562,17 @@ __all__ = [
     "LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Text",
     "LlamaParseParameters",
     "LlamaParseSupportedFileExtensions",
-    "Llm",
     "LlmModelData",
     "LlmParameters",
+    "LoadFilesJobConfig",
     "ManagedIngestionStatus",
     "ManagedIngestionStatusResponse",
-    "MarkdownElementNodeParser",
-    "MarkdownNodeParser",
     "MessageAnnotation",
     "MessageRole",
     "MetadataFilter",
     "MetadataFilterValue",
     "MetadataFilters",
     "MetadataFiltersFiltersItem",
-    "NodeParser",
     "NodeRelationship",
     "NoneChunkingConfig",
     "NoneSegmentationConfig",
@@ -569,12 +585,12 @@ __all__ = [
     "PageScreenshotMetadata",
     "PageScreenshotNodeWithScore",
     "PageSegmentationConfig",
-    "PageSplitterNodeParser",
     "PaginatedExtractRunsResponse",
     "PaginatedJobsHistoryWithMetrics",
     "PaginatedListCloudDocumentsResponse",
     "PaginatedListPipelineFilesResponse",
     "PaginatedReportResponse",
+    "ParseJobConfig",
     "ParsePlanLevel",
     "ParserLanguages",
     "ParsingHistoryItem",
@@ -624,6 +640,11 @@ __all__ = [
     "PipelineFileResourceInfoValue",
     "PipelineFileStatus",
     "PipelineFileUpdateCustomMetadataValue",
+    "PipelineFileUpdateDispatcherConfig",
+    "PipelineFileUpdaterConfig",
+    "PipelineManagedIngestionJobParams",
+    "PipelineMetadataConfig",
+    "PipelineStatus",
     "PipelineTransformConfig",
     "PipelineTransformConfig_Advanced",
     "PipelineTransformConfig_Auto",
@@ -648,7 +669,6 @@ __all__ = [
     "Project",
     "ProjectCreate",
     "PromptConf",
-    "PydanticProgramMode",
     "ReRankConfig",
     "ReRankerType",
     "RecurringCreditGrant",
@@ -681,7 +701,6 @@ __all__ = [
     "SchemaRelaxMode",
     "SemanticChunkingConfig",
     "SentenceChunkingConfig",
-    "SentenceSplitter",
     "StatusEnum",
     "StructMode",
     "StructParseConf",
@@ -692,7 +711,6 @@ __all__ = [
     "TextNodeRelationshipsValue",
     "TextNodeWithScore",
     "TokenChunkingConfig",
-    "TokenTextSplitter",
     "TransformationCategoryNames",
     "UnprocessableEntityError",
     "UpdateReportPlanApiV1ReportsReportIdPlanPatchRequestAction",

llama_cloud/resources/files/client.py

@@ -213,7 +213,7 @@ class FilesClient:
 
             - organization_id: typing.Optional[str].
 
-            - name: str.
+            - name: str. Name that will be used for created file. If possible, always include the file extension in the name.
 
             - external_file_id: typing.Optional[str].
 
@@ -318,7 +318,14 @@ class FilesClient:
         resource_info: typing.Optional[typing.Dict[str, typing.Optional[FileCreateFromUrlResourceInfoValue]]] = OMIT,
     ) -> File:
         """
-        Upload a file to S3 from a URL.
+        Upload a file to the project from a URL.
+
+        If name is ommitted in the request payload, the file name will be
+        extracted from the response Content-Disposition header if available
+        or otherwise it will be derived from the URL path.
+
+        If providing the name in the request payload, always suffix the
+        file extension in the name if available.
 
         Parameters:
             - project_id: typing.Optional[str].
@@ -833,7 +840,7 @@ class AsyncFilesClient:
 
             - organization_id: typing.Optional[str].
 
-            - name: str.
+            - name: str. Name that will be used for created file. If possible, always include the file extension in the name.
 
             - external_file_id: typing.Optional[str].
 
@@ -938,7 +945,14 @@ class AsyncFilesClient:
         resource_info: typing.Optional[typing.Dict[str, typing.Optional[FileCreateFromUrlResourceInfoValue]]] = OMIT,
     ) -> File:
         """
-        Upload a file to S3 from a URL.
+        Upload a file to the project from a URL.
+
+        If name is ommitted in the request payload, the file name will be
+        extracted from the response Content-Disposition header if available
+        or otherwise it will be derived from the URL path.
+
+        If providing the name in the request payload, always suffix the
+        file extension in the name if available.
 
         Parameters:
             - project_id: typing.Optional[str].

llama_cloud/resources/parsing/client.py

@@ -204,6 +204,7 @@ class ParsingClient:
         auto_mode_trigger_on_table_in_page: bool,
         auto_mode_trigger_on_text_in_page: str,
         auto_mode_trigger_on_regexp_in_page: str,
+        auto_mode_configuration_json: str,
         azure_openai_api_version: str,
         azure_openai_deployment_name: str,
         azure_openai_endpoint: str,
@@ -303,6 +304,8 @@ class ParsingClient:
 
             - auto_mode_trigger_on_regexp_in_page: str.
 
+            - auto_mode_configuration_json: str.
+
             - azure_openai_api_version: str.
 
             - azure_openai_deployment_name: str.
@@ -463,6 +466,7 @@ class ParsingClient:
             "auto_mode_trigger_on_table_in_page": auto_mode_trigger_on_table_in_page,
             "auto_mode_trigger_on_text_in_page": auto_mode_trigger_on_text_in_page,
             "auto_mode_trigger_on_regexp_in_page": auto_mode_trigger_on_regexp_in_page,
+            "auto_mode_configuration_json": auto_mode_configuration_json,
             "azure_openai_api_version": azure_openai_api_version,
             "azure_openai_deployment_name": azure_openai_deployment_name,
             "azure_openai_endpoint": azure_openai_endpoint,
@@ -1211,6 +1215,7 @@ class AsyncParsingClient:
         auto_mode_trigger_on_table_in_page: bool,
         auto_mode_trigger_on_text_in_page: str,
         auto_mode_trigger_on_regexp_in_page: str,
+        auto_mode_configuration_json: str,
         azure_openai_api_version: str,
         azure_openai_deployment_name: str,
         azure_openai_endpoint: str,
@@ -1310,6 +1315,8 @@ class AsyncParsingClient:
 
             - auto_mode_trigger_on_regexp_in_page: str.
 
+            - auto_mode_configuration_json: str.
+
             - azure_openai_api_version: str.
 
             - azure_openai_deployment_name: str.
@@ -1470,6 +1477,7 @@ class AsyncParsingClient:
             "auto_mode_trigger_on_table_in_page": auto_mode_trigger_on_table_in_page,
             "auto_mode_trigger_on_text_in_page": auto_mode_trigger_on_text_in_page,
             "auto_mode_trigger_on_regexp_in_page": auto_mode_trigger_on_regexp_in_page,
+            "auto_mode_configuration_json": auto_mode_configuration_json,
             "azure_openai_api_version": azure_openai_api_version,
             "azure_openai_deployment_name": azure_openai_deployment_name,
             "azure_openai_endpoint": azure_openai_endpoint,

llama_cloud/resources/pipelines/client.py

@@ -12,7 +12,6 @@ from ...errors.unprocessable_entity_error import UnprocessableEntityError
 from ...types.chat_data import ChatData
 from ...types.cloud_document import CloudDocument
 from ...types.cloud_document_create import CloudDocumentCreate
-from ...types.configured_transformation_item import ConfiguredTransformationItem
 from ...types.data_sink_create import DataSinkCreate
 from ...types.eval_execution_params import EvalExecutionParams
 from ...types.file_count_by_status_response import FileCountByStatusResponse
@@ -30,6 +29,7 @@ from ...types.pipeline_data_source_create import PipelineDataSourceCreate
 from ...types.pipeline_deployment import PipelineDeployment
 from ...types.pipeline_file import PipelineFile
 from ...types.pipeline_file_create import PipelineFileCreate
+from ...types.pipeline_metadata_config import PipelineMetadataConfig
 from ...types.pipeline_type import PipelineType
 from ...types.playground_session import PlaygroundSession
 from ...types.preset_retrieval_params import PresetRetrievalParams
@@ -210,7 +210,6 @@ class PipelinesClient:
         *,
         embedding_config: typing.Optional[PipelineUpdateEmbeddingConfig] = OMIT,
         transform_config: typing.Optional[PipelineUpdateTransformConfig] = OMIT,
-        configured_transformations: typing.Optional[typing.List[ConfiguredTransformationItem]] = OMIT,
         data_sink_id: typing.Optional[str] = OMIT,
         embedding_model_config_id: typing.Optional[str] = OMIT,
         data_sink: typing.Optional[DataSinkCreate] = OMIT,
@@ -218,6 +217,7 @@ class PipelinesClient:
         eval_parameters: typing.Optional[EvalExecutionParams] = OMIT,
         llama_parse_parameters: typing.Optional[LlamaParseParameters] = OMIT,
         status: typing.Optional[str] = OMIT,
+        metadata_config: typing.Optional[PipelineMetadataConfig] = OMIT,
         name: typing.Optional[str] = OMIT,
         managed_pipeline_id: typing.Optional[str] = OMIT,
     ) -> Pipeline:
@@ -231,8 +231,6 @@ class PipelinesClient:
 
             - transform_config: typing.Optional[PipelineUpdateTransformConfig]. Configuration for the transformation.
 
-            - configured_transformations: typing.Optional[typing.List[ConfiguredTransformationItem]].
-
             - data_sink_id: typing.Optional[str].
 
             - embedding_model_config_id: typing.Optional[str].
@@ -247,6 +245,8 @@ class PipelinesClient:
 
             - status: typing.Optional[str].
 
+            - metadata_config: typing.Optional[PipelineMetadataConfig].
+
             - name: typing.Optional[str].
 
             - managed_pipeline_id: typing.Optional[str].
@@ -256,8 +256,6 @@ class PipelinesClient:
             _request["embedding_config"] = embedding_config
         if transform_config is not OMIT:
             _request["transform_config"] = transform_config
-        if configured_transformations is not OMIT:
-            _request["configured_transformations"] = configured_transformations
         if data_sink_id is not OMIT:
             _request["data_sink_id"] = data_sink_id
         if embedding_model_config_id is not OMIT:
@@ -272,6 +270,8 @@ class PipelinesClient:
             _request["llama_parse_parameters"] = llama_parse_parameters
         if status is not OMIT:
             _request["status"] = status
+        if metadata_config is not OMIT:
+            _request["metadata_config"] = metadata_config
         if name is not OMIT:
             _request["name"] = name
         if managed_pipeline_id is not OMIT:
@@ -1024,6 +1024,8 @@ class PipelinesClient:
         self,
         pipeline_id: str,
         *,
+        project_id: typing.Optional[str] = None,
+        organization_id: typing.Optional[str] = None,
         dense_similarity_top_k: typing.Optional[int] = OMIT,
         dense_similarity_cutoff: typing.Optional[float] = OMIT,
         sparse_similarity_top_k: typing.Optional[int] = OMIT,
@@ -1043,6 +1045,10 @@ class PipelinesClient:
         Parameters:
             - pipeline_id: str.
 
+            - project_id: typing.Optional[str].
+
+            - organization_id: typing.Optional[str].
+
             - dense_similarity_top_k: typing.Optional[int].
 
             - dense_similarity_cutoff: typing.Optional[float].
@@ -1109,6 +1115,7 @@ class PipelinesClient:
         _response = self._client_wrapper.httpx_client.request(
             "POST",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/pipelines/{pipeline_id}/retrieve"),
+            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,
@@ -1817,7 +1824,6 @@ class AsyncPipelinesClient:
         *,
         embedding_config: typing.Optional[PipelineUpdateEmbeddingConfig] = OMIT,
         transform_config: typing.Optional[PipelineUpdateTransformConfig] = OMIT,
-        configured_transformations: typing.Optional[typing.List[ConfiguredTransformationItem]] = OMIT,
         data_sink_id: typing.Optional[str] = OMIT,
         embedding_model_config_id: typing.Optional[str] = OMIT,
         data_sink: typing.Optional[DataSinkCreate] = OMIT,
@@ -1825,6 +1831,7 @@ class AsyncPipelinesClient:
         eval_parameters: typing.Optional[EvalExecutionParams] = OMIT,
         llama_parse_parameters: typing.Optional[LlamaParseParameters] = OMIT,
         status: typing.Optional[str] = OMIT,
+        metadata_config: typing.Optional[PipelineMetadataConfig] = OMIT,
         name: typing.Optional[str] = OMIT,
         managed_pipeline_id: typing.Optional[str] = OMIT,
     ) -> Pipeline:
@@ -1838,8 +1845,6 @@ class AsyncPipelinesClient:
 
             - transform_config: typing.Optional[PipelineUpdateTransformConfig]. Configuration for the transformation.
 
-            - configured_transformations: typing.Optional[typing.List[ConfiguredTransformationItem]].
-
             - data_sink_id: typing.Optional[str].
 
             - embedding_model_config_id: typing.Optional[str].
@@ -1854,6 +1859,8 @@ class AsyncPipelinesClient:
 
             - status: typing.Optional[str].
 
+            - metadata_config: typing.Optional[PipelineMetadataConfig].
+
             - name: typing.Optional[str].
 
             - managed_pipeline_id: typing.Optional[str].
@@ -1863,8 +1870,6 @@ class AsyncPipelinesClient:
             _request["embedding_config"] = embedding_config
         if transform_config is not OMIT:
             _request["transform_config"] = transform_config
-        if configured_transformations is not OMIT:
-            _request["configured_transformations"] = configured_transformations
         if data_sink_id is not OMIT:
             _request["data_sink_id"] = data_sink_id
         if embedding_model_config_id is not OMIT:
@@ -1879,6 +1884,8 @@ class AsyncPipelinesClient:
             _request["llama_parse_parameters"] = llama_parse_parameters
         if status is not OMIT:
             _request["status"] = status
+        if metadata_config is not OMIT:
+            _request["metadata_config"] = metadata_config
         if name is not OMIT:
             _request["name"] = name
         if managed_pipeline_id is not OMIT:
@@ -2633,6 +2640,8 @@ class AsyncPipelinesClient:
         self,
         pipeline_id: str,
         *,
+        project_id: typing.Optional[str] = None,
+        organization_id: typing.Optional[str] = None,
         dense_similarity_top_k: typing.Optional[int] = OMIT,
         dense_similarity_cutoff: typing.Optional[float] = OMIT,
         sparse_similarity_top_k: typing.Optional[int] = OMIT,
@@ -2652,6 +2661,10 @@ class AsyncPipelinesClient:
         Parameters:
             - pipeline_id: str.
 
+            - project_id: typing.Optional[str].
+
+            - organization_id: typing.Optional[str].
+
             - dense_similarity_top_k: typing.Optional[int].
 
             - dense_similarity_cutoff: typing.Optional[float].
@@ -2718,6 +2731,7 @@ class AsyncPipelinesClient:
         _response = await self._client_wrapper.httpx_client.request(
             "POST",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/pipelines/{pipeline_id}/retrieve"),
+            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,