llama-cloud 0.1.20__py3-none-any.whl → 0.1.22__py3-none-any.whl

llama_cloud/resources/retrievers/client.py

@@ -295,6 +295,8 @@ class RetrieversClient:
         self,
         retriever_id: str,
         *,
+        project_id: typing.Optional[str] = None,
+        organization_id: typing.Optional[str] = None,
         mode: typing.Optional[CompositeRetrievalMode] = OMIT,
         rerank_top_n: typing.Optional[int] = OMIT,
         rerank_config: typing.Optional[ReRankConfig] = OMIT,
@@ -306,6 +308,10 @@ class RetrieversClient:
         Parameters:
             - retriever_id: str.
 
+            - project_id: typing.Optional[str].
+
+            - organization_id: typing.Optional[str].
+
             - mode: typing.Optional[CompositeRetrievalMode]. The mode of composite retrieval.
 
             - rerank_top_n: typing.Optional[int].
@@ -341,6 +347,7 @@ class RetrieversClient:
             urllib.parse.urljoin(
                 f"{self._client_wrapper.get_base_url()}/", f"api/v1/retrievers/{retriever_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,
@@ -692,6 +699,8 @@ class AsyncRetrieversClient:
         self,
         retriever_id: str,
         *,
+        project_id: typing.Optional[str] = None,
+        organization_id: typing.Optional[str] = None,
         mode: typing.Optional[CompositeRetrievalMode] = OMIT,
         rerank_top_n: typing.Optional[int] = OMIT,
         rerank_config: typing.Optional[ReRankConfig] = OMIT,
@@ -703,6 +712,10 @@ class AsyncRetrieversClient:
         Parameters:
             - retriever_id: str.
 
+            - project_id: typing.Optional[str].
+
+            - organization_id: typing.Optional[str].
+
             - mode: typing.Optional[CompositeRetrievalMode]. The mode of composite retrieval.
 
             - rerank_top_n: typing.Optional[int].
@@ -738,6 +751,7 @@ class AsyncRetrieversClient:
             urllib.parse.urljoin(
                 f"{self._client_wrapper.get_base_url()}/", f"api/v1/retrievers/{retriever_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,

llama_cloud/types/__init__.py

@@ -63,65 +63,21 @@ 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
-from .configurable_transformation_names import ConfigurableTransformationNames
 from .credit_type import CreditType
 from .data_sink import DataSink
-from .data_sink_component import (
-    DataSinkComponent,
-    DataSinkComponent_AzureAiSearch,
-    DataSinkComponent_Milvus,
-    DataSinkComponent_MongodbAtlas,
-    DataSinkComponent_Pinecone,
-    DataSinkComponent_Postgres,
-    DataSinkComponent_Qdrant,
-)
+from .data_sink_component import DataSinkComponent
 from .data_sink_create import DataSinkCreate
-from .data_sink_create_component import (
-    DataSinkCreateComponent,
-    DataSinkCreateComponent_AzureAiSearch,
-    DataSinkCreateComponent_Milvus,
-    DataSinkCreateComponent_MongodbAtlas,
-    DataSinkCreateComponent_Pinecone,
-    DataSinkCreateComponent_Postgres,
-    DataSinkCreateComponent_Qdrant,
-)
-from .data_sink_definition import DataSinkDefinition
+from .data_sink_create_component import DataSinkCreateComponent
 from .data_source import DataSource
 from .data_source_component import DataSourceComponent
-from .data_source_component_one import (
-    DataSourceComponentOne,
-    DataSourceComponentOne_AzureStorageBlob,
-    DataSourceComponentOne_Box,
-    DataSourceComponentOne_Confluence,
-    DataSourceComponentOne_GoogleDrive,
-    DataSourceComponentOne_Jira,
-    DataSourceComponentOne_MicrosoftOnedrive,
-    DataSourceComponentOne_MicrosoftSharepoint,
-    DataSourceComponentOne_NotionPage,
-    DataSourceComponentOne_S3,
-    DataSourceComponentOne_Slack,
-)
 from .data_source_create import DataSourceCreate
 from .data_source_create_component import DataSourceCreateComponent
-from .data_source_create_component_one import (
-    DataSourceCreateComponentOne,
-    DataSourceCreateComponentOne_AzureStorageBlob,
-    DataSourceCreateComponentOne_Box,
-    DataSourceCreateComponentOne_Confluence,
-    DataSourceCreateComponentOne_GoogleDrive,
-    DataSourceCreateComponentOne_Jira,
-    DataSourceCreateComponentOne_MicrosoftOnedrive,
-    DataSourceCreateComponentOne_MicrosoftSharepoint,
-    DataSourceCreateComponentOne_NotionPage,
-    DataSourceCreateComponentOne_S3,
-    DataSourceCreateComponentOne_Slack,
-)
 from .data_source_create_custom_metadata_value import DataSourceCreateCustomMetadataValue
 from .data_source_custom_metadata_value import DataSourceCustomMetadataValue
-from .data_source_definition import DataSourceDefinition
 from .data_source_update_dispatcher_config import DataSourceUpdateDispatcherConfig
 from .delete_params import DeleteParams
+from .document_block import DocumentBlock
+from .document_chunk_mode import DocumentChunkMode
 from .document_ingestion_job_params import DocumentIngestionJobParams
 from .edit_suggestion import EditSuggestion
 from .edit_suggestion_blocks_item import EditSuggestionBlocksItem
@@ -157,6 +113,7 @@ 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
@@ -213,11 +170,15 @@ from .llama_index_core_base_llms_types_chat_message import LlamaIndexCoreBaseLlm
 from .llama_index_core_base_llms_types_chat_message_blocks_item import (
     LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem,
     LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Audio,
+    LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Document,
     LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Image,
     LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Text,
 )
 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
@@ -277,19 +238,6 @@ from .pipeline_create_embedding_config import (
 from .pipeline_create_transform_config import PipelineCreateTransformConfig
 from .pipeline_data_source import PipelineDataSource
 from .pipeline_data_source_component import PipelineDataSourceComponent
-from .pipeline_data_source_component_one import (
-    PipelineDataSourceComponentOne,
-    PipelineDataSourceComponentOne_AzureStorageBlob,
-    PipelineDataSourceComponentOne_Box,
-    PipelineDataSourceComponentOne_Confluence,
-    PipelineDataSourceComponentOne_GoogleDrive,
-    PipelineDataSourceComponentOne_Jira,
-    PipelineDataSourceComponentOne_MicrosoftOnedrive,
-    PipelineDataSourceComponentOne_MicrosoftSharepoint,
-    PipelineDataSourceComponentOne_NotionPage,
-    PipelineDataSourceComponentOne_S3,
-    PipelineDataSourceComponentOne_Slack,
-)
 from .pipeline_data_source_create import PipelineDataSourceCreate
 from .pipeline_data_source_custom_metadata_value import PipelineDataSourceCustomMetadataValue
 from .pipeline_data_source_status import PipelineDataSourceStatus
@@ -316,6 +264,7 @@ from .pipeline_file_update_dispatcher_config import PipelineFileUpdateDispatcher
 from .pipeline_file_updater_config import PipelineFileUpdaterConfig
 from .pipeline_managed_ingestion_job_params import PipelineManagedIngestionJobParams
 from .pipeline_metadata_config import PipelineMetadataConfig
+from .pipeline_status import PipelineStatus
 from .pipeline_transform_config import (
     PipelineTransformConfig,
     PipelineTransformConfig_Advanced,
@@ -377,7 +326,6 @@ from .text_node import TextNode
 from .text_node_relationships_value import TextNodeRelationshipsValue
 from .text_node_with_score import TextNodeWithScore
 from .token_chunking_config import TokenChunkingConfig
-from .transformation_category_names import TransformationCategoryNames
 from .usage_and_plan import UsageAndPlan
 from .usage_metric_response import UsageMetricResponse
 from .usage_response import UsageResponse
@@ -453,57 +401,21 @@ __all__ = [
     "CompositeRetrievedTextNodeWithScore",
     "ConfigurableDataSinkNames",
     "ConfigurableDataSourceNames",
-    "ConfigurableTransformationDefinition",
-    "ConfigurableTransformationNames",
     "CreditType",
     "DataSink",
     "DataSinkComponent",
-    "DataSinkComponent_AzureAiSearch",
-    "DataSinkComponent_Milvus",
-    "DataSinkComponent_MongodbAtlas",
-    "DataSinkComponent_Pinecone",
-    "DataSinkComponent_Postgres",
-    "DataSinkComponent_Qdrant",
     "DataSinkCreate",
     "DataSinkCreateComponent",
-    "DataSinkCreateComponent_AzureAiSearch",
-    "DataSinkCreateComponent_Milvus",
-    "DataSinkCreateComponent_MongodbAtlas",
-    "DataSinkCreateComponent_Pinecone",
-    "DataSinkCreateComponent_Postgres",
-    "DataSinkCreateComponent_Qdrant",
-    "DataSinkDefinition",
     "DataSource",
     "DataSourceComponent",
-    "DataSourceComponentOne",
-    "DataSourceComponentOne_AzureStorageBlob",
-    "DataSourceComponentOne_Box",
-    "DataSourceComponentOne_Confluence",
-    "DataSourceComponentOne_GoogleDrive",
-    "DataSourceComponentOne_Jira",
-    "DataSourceComponentOne_MicrosoftOnedrive",
-    "DataSourceComponentOne_MicrosoftSharepoint",
-    "DataSourceComponentOne_NotionPage",
-    "DataSourceComponentOne_S3",
-    "DataSourceComponentOne_Slack",
     "DataSourceCreate",
     "DataSourceCreateComponent",
-    "DataSourceCreateComponentOne",
-    "DataSourceCreateComponentOne_AzureStorageBlob",
-    "DataSourceCreateComponentOne_Box",
-    "DataSourceCreateComponentOne_Confluence",
-    "DataSourceCreateComponentOne_GoogleDrive",
-    "DataSourceCreateComponentOne_Jira",
-    "DataSourceCreateComponentOne_MicrosoftOnedrive",
-    "DataSourceCreateComponentOne_MicrosoftSharepoint",
-    "DataSourceCreateComponentOne_NotionPage",
-    "DataSourceCreateComponentOne_S3",
-    "DataSourceCreateComponentOne_Slack",
     "DataSourceCreateCustomMetadataValue",
     "DataSourceCustomMetadataValue",
-    "DataSourceDefinition",
     "DataSourceUpdateDispatcherConfig",
     "DeleteParams",
+    "DocumentBlock",
+    "DocumentChunkMode",
     "DocumentIngestionJobParams",
     "EditSuggestion",
     "EditSuggestionBlocksItem",
@@ -535,6 +447,7 @@ __all__ = [
     "ExtractJobCreateDataSchemaOverride",
     "ExtractJobCreateDataSchemaOverrideZeroValue",
     "ExtractMode",
+    "ExtractModels",
     "ExtractResultset",
     "ExtractResultsetData",
     "ExtractResultsetDataItemValue",
@@ -588,10 +501,14 @@ __all__ = [
     "LlamaIndexCoreBaseLlmsTypesChatMessage",
     "LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem",
     "LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Audio",
+    "LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Document",
     "LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Image",
     "LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Text",
     "LlamaParseParameters",
     "LlamaParseSupportedFileExtensions",
+    "LlmConfigResult",
+    "LlmConfigResultLlmType",
+    "LlmConfigsResponse",
     "LlmModelData",
     "LlmParameters",
     "LoadFilesJobConfig",
@@ -649,17 +566,6 @@ __all__ = [
     "PipelineCreateTransformConfig",
     "PipelineDataSource",
     "PipelineDataSourceComponent",
-    "PipelineDataSourceComponentOne",
-    "PipelineDataSourceComponentOne_AzureStorageBlob",
-    "PipelineDataSourceComponentOne_Box",
-    "PipelineDataSourceComponentOne_Confluence",
-    "PipelineDataSourceComponentOne_GoogleDrive",
-    "PipelineDataSourceComponentOne_Jira",
-    "PipelineDataSourceComponentOne_MicrosoftOnedrive",
-    "PipelineDataSourceComponentOne_MicrosoftSharepoint",
-    "PipelineDataSourceComponentOne_NotionPage",
-    "PipelineDataSourceComponentOne_S3",
-    "PipelineDataSourceComponentOne_Slack",
     "PipelineDataSourceCreate",
     "PipelineDataSourceCustomMetadataValue",
     "PipelineDataSourceStatus",
@@ -684,6 +590,7 @@ __all__ = [
     "PipelineFileUpdaterConfig",
     "PipelineManagedIngestionJobParams",
     "PipelineMetadataConfig",
+    "PipelineStatus",
     "PipelineTransformConfig",
     "PipelineTransformConfig_Advanced",
     "PipelineTransformConfig_Auto",
@@ -741,7 +648,6 @@ __all__ = [
     "TextNodeRelationshipsValue",
     "TextNodeWithScore",
     "TokenChunkingConfig",
-    "TransformationCategoryNames",
     "UsageAndPlan",
     "UsageMetricResponse",
     "UsageResponse",

llama_cloud/types/cloud_jira_data_source.py

@@ -15,6 +15,10 @@ except ImportError:
 
 
 class CloudJiraDataSource(pydantic.BaseModel):
+    """
+    Cloud Jira Data Source integrating JiraReader.
+    """
+
     supports_access_control: typing.Optional[bool]
     email: typing.Optional[str]
     api_token: typing.Optional[str]

llama_cloud/types/cloud_s_3_data_source.py

@@ -18,6 +18,7 @@ class CloudS3DataSource(pydantic.BaseModel):
     supports_access_control: typing.Optional[bool]
     bucket: str = pydantic.Field(description="The name of the S3 bucket to read from.")
     prefix: typing.Optional[str]
+    regex_pattern: typing.Optional[str]
     aws_access_id: typing.Optional[str]
     aws_access_secret: typing.Optional[str]
     s_3_endpoint_url: typing.Optional[str] = pydantic.Field(alias="s3_endpoint_url")

llama_cloud/types/data_sink_component.py

@@ -1,11 +1,7 @@
 # This file was auto-generated by Fern from our API Definition.
 
-from __future__ import annotations
-
 import typing
 
-import typing_extensions
-
 from .cloud_azure_ai_search_vector_store import CloudAzureAiSearchVectorStore
 from .cloud_milvus_vector_store import CloudMilvusVectorStore
 from .cloud_mongo_db_atlas_vector_search import CloudMongoDbAtlasVectorSearch
@@ -13,66 +9,12 @@ from .cloud_pinecone_vector_store import CloudPineconeVectorStore
 from .cloud_postgres_vector_store import CloudPostgresVectorStore
 from .cloud_qdrant_vector_store import CloudQdrantVectorStore
 
-
-class DataSinkComponent_AzureAiSearch(CloudAzureAiSearchVectorStore):
-    type: typing_extensions.Literal["azure_ai_search"]
-
-    class Config:
-        frozen = True
-        smart_union = True
-        allow_population_by_field_name = True
-
-
-class DataSinkComponent_Milvus(CloudMilvusVectorStore):
-    type: typing_extensions.Literal["milvus"]
-
-    class Config:
-        frozen = True
-        smart_union = True
-        allow_population_by_field_name = True
-
-
-class DataSinkComponent_MongodbAtlas(CloudMongoDbAtlasVectorSearch):
-    type: typing_extensions.Literal["mongodb_atlas"]
-
-    class Config:
-        frozen = True
-        smart_union = True
-        allow_population_by_field_name = True
-
-
-class DataSinkComponent_Pinecone(CloudPineconeVectorStore):
-    type: typing_extensions.Literal["pinecone"]
-
-    class Config:
-        frozen = True
-        smart_union = True
-        allow_population_by_field_name = True
-
-
-class DataSinkComponent_Postgres(CloudPostgresVectorStore):
-    type: typing_extensions.Literal["postgres"]
-
-    class Config:
-        frozen = True
-        smart_union = True
-        allow_population_by_field_name = True
-
-
-class DataSinkComponent_Qdrant(CloudQdrantVectorStore):
-    type: typing_extensions.Literal["qdrant"]
-
-    class Config:
-        frozen = True
-        smart_union = True
-        allow_population_by_field_name = True
-
-
 DataSinkComponent = typing.Union[
-    DataSinkComponent_AzureAiSearch,
-    DataSinkComponent_Milvus,
-    DataSinkComponent_MongodbAtlas,
-    DataSinkComponent_Pinecone,
-    DataSinkComponent_Postgres,
-    DataSinkComponent_Qdrant,
+    typing.Dict[str, typing.Any],
+    CloudPineconeVectorStore,
+    CloudPostgresVectorStore,
+    CloudQdrantVectorStore,
+    CloudAzureAiSearchVectorStore,
+    CloudMongoDbAtlasVectorSearch,
+    CloudMilvusVectorStore,
 ]

llama_cloud/types/data_sink_create_component.py

@@ -1,11 +1,7 @@
 # This file was auto-generated by Fern from our API Definition.
 
-from __future__ import annotations
-
 import typing
 
-import typing_extensions
-
 from .cloud_azure_ai_search_vector_store import CloudAzureAiSearchVectorStore
 from .cloud_milvus_vector_store import CloudMilvusVectorStore
 from .cloud_mongo_db_atlas_vector_search import CloudMongoDbAtlasVectorSearch
@@ -13,66 +9,12 @@ from .cloud_pinecone_vector_store import CloudPineconeVectorStore
 from .cloud_postgres_vector_store import CloudPostgresVectorStore
 from .cloud_qdrant_vector_store import CloudQdrantVectorStore
 
-
-class DataSinkCreateComponent_AzureAiSearch(CloudAzureAiSearchVectorStore):
-    type: typing_extensions.Literal["azure_ai_search"]
-
-    class Config:
-        frozen = True
-        smart_union = True
-        allow_population_by_field_name = True
-
-
-class DataSinkCreateComponent_Milvus(CloudMilvusVectorStore):
-    type: typing_extensions.Literal["milvus"]
-
-    class Config:
-        frozen = True
-        smart_union = True
-        allow_population_by_field_name = True
-
-
-class DataSinkCreateComponent_MongodbAtlas(CloudMongoDbAtlasVectorSearch):
-    type: typing_extensions.Literal["mongodb_atlas"]
-
-    class Config:
-        frozen = True
-        smart_union = True
-        allow_population_by_field_name = True
-
-
-class DataSinkCreateComponent_Pinecone(CloudPineconeVectorStore):
-    type: typing_extensions.Literal["pinecone"]
-
-    class Config:
-        frozen = True
-        smart_union = True
-        allow_population_by_field_name = True
-
-
-class DataSinkCreateComponent_Postgres(CloudPostgresVectorStore):
-    type: typing_extensions.Literal["postgres"]
-
-    class Config:
-        frozen = True
-        smart_union = True
-        allow_population_by_field_name = True
-
-
-class DataSinkCreateComponent_Qdrant(CloudQdrantVectorStore):
-    type: typing_extensions.Literal["qdrant"]
-
-    class Config:
-        frozen = True
-        smart_union = True
-        allow_population_by_field_name = True
-
-
 DataSinkCreateComponent = typing.Union[
-    DataSinkCreateComponent_AzureAiSearch,
-    DataSinkCreateComponent_Milvus,
-    DataSinkCreateComponent_MongodbAtlas,
-    DataSinkCreateComponent_Pinecone,
-    DataSinkCreateComponent_Postgres,
-    DataSinkCreateComponent_Qdrant,
+    typing.Dict[str, typing.Any],
+    CloudPineconeVectorStore,
+    CloudPostgresVectorStore,
+    CloudQdrantVectorStore,
+    CloudAzureAiSearchVectorStore,
+    CloudMongoDbAtlasVectorSearch,
+    CloudMilvusVectorStore,
 ]

llama_cloud/types/data_source_component.py

@@ -2,6 +2,27 @@
 
 import typing
 
-from .data_source_component_one import DataSourceComponentOne
+from .cloud_az_storage_blob_data_source import CloudAzStorageBlobDataSource
+from .cloud_box_data_source import CloudBoxDataSource
+from .cloud_confluence_data_source import CloudConfluenceDataSource
+from .cloud_google_drive_data_source import CloudGoogleDriveDataSource
+from .cloud_jira_data_source import CloudJiraDataSource
+from .cloud_notion_page_data_source import CloudNotionPageDataSource
+from .cloud_one_drive_data_source import CloudOneDriveDataSource
+from .cloud_s_3_data_source import CloudS3DataSource
+from .cloud_sharepoint_data_source import CloudSharepointDataSource
+from .cloud_slack_data_source import CloudSlackDataSource
 
-DataSourceComponent = typing.Union[typing.Dict[str, typing.Any], DataSourceComponentOne]
+DataSourceComponent = typing.Union[
+    typing.Dict[str, typing.Any],
+    CloudS3DataSource,
+    CloudAzStorageBlobDataSource,
+    CloudGoogleDriveDataSource,
+    CloudOneDriveDataSource,
+    CloudSharepointDataSource,
+    CloudSlackDataSource,
+    CloudNotionPageDataSource,
+    CloudConfluenceDataSource,
+    CloudJiraDataSource,
+    CloudBoxDataSource,
+]

llama_cloud/types/data_source_create_component.py

@@ -2,6 +2,27 @@
 
 import typing
 
-from .data_source_create_component_one import DataSourceCreateComponentOne
+from .cloud_az_storage_blob_data_source import CloudAzStorageBlobDataSource
+from .cloud_box_data_source import CloudBoxDataSource
+from .cloud_confluence_data_source import CloudConfluenceDataSource
+from .cloud_google_drive_data_source import CloudGoogleDriveDataSource
+from .cloud_jira_data_source import CloudJiraDataSource
+from .cloud_notion_page_data_source import CloudNotionPageDataSource
+from .cloud_one_drive_data_source import CloudOneDriveDataSource
+from .cloud_s_3_data_source import CloudS3DataSource
+from .cloud_sharepoint_data_source import CloudSharepointDataSource
+from .cloud_slack_data_source import CloudSlackDataSource
 
-DataSourceCreateComponent = typing.Union[typing.Dict[str, typing.Any], DataSourceCreateComponentOne]
+DataSourceCreateComponent = typing.Union[
+    typing.Dict[str, typing.Any],
+    CloudS3DataSource,
+    CloudAzStorageBlobDataSource,
+    CloudGoogleDriveDataSource,
+    CloudOneDriveDataSource,
+    CloudSharepointDataSource,
+    CloudSlackDataSource,
+    CloudNotionPageDataSource,
+    CloudConfluenceDataSource,
+    CloudJiraDataSource,
+    CloudBoxDataSource,
+]

llama_cloud/types/{data_sink_definition.py → document_block.py}

@@ -4,7 +4,6 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
-from .configurable_data_sink_names import ConfigurableDataSinkNames
 
 try:
     import pydantic
@@ -15,20 +14,12 @@ except ImportError:
     import pydantic  # type: ignore
 
 
-class DataSinkDefinition(pydantic.BaseModel):
-    """
-    Schema for a data sink definition.
-    """
-
-    label: str = pydantic.Field(
-        description="The label field will be used to display the name of the component in the UI"
-    )
-    json_schema: typing.Dict[str, typing.Any] = pydantic.Field(
-        description="The json_schema field can be used by clients to determine how to construct the component"
-    )
-    sink_type: ConfigurableDataSinkNames = pydantic.Field(
-        description="The name field will act as the unique identifier of DataSinkDefinition objects"
-    )
+class DocumentBlock(pydantic.BaseModel):
+    data: typing.Optional[str]
+    path: typing.Optional[str]
+    url: typing.Optional[str]
+    title: typing.Optional[str]
+    document_mimetype: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/document_chunk_mode.py

@@ -0,0 +1,17 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import enum
+import typing
+
+T_Result = typing.TypeVar("T_Result")
+
+
+class DocumentChunkMode(str, enum.Enum):
+    PAGE = "PAGE"
+    SECTION = "SECTION"
+
+    def visit(self, page: typing.Callable[[], T_Result], section: typing.Callable[[], T_Result]) -> T_Result:
+        if self is DocumentChunkMode.PAGE:
+            return page()
+        if self is DocumentChunkMode.SECTION:
+            return section()

llama_cloud/types/extract_config.py

@@ -4,6 +4,7 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
+from .document_chunk_mode import DocumentChunkMode
 from .extract_mode import ExtractMode
 from .extract_target import ExtractTarget
 
@@ -26,6 +27,12 @@ class ExtractConfig(pydantic.BaseModel):
     system_prompt: typing.Optional[str]
     use_reasoning: typing.Optional[bool] = pydantic.Field(description="Whether to use reasoning for the extraction.")
     cite_sources: typing.Optional[bool] = pydantic.Field(description="Whether to cite sources for the extraction.")
+    chunk_mode: typing.Optional[DocumentChunkMode] = pydantic.Field(
+        description="The mode to use for chunking the document."
+    )
+    invalidate_cache: typing.Optional[bool] = pydantic.Field(
+        description="Whether to invalidate the cache for the extraction."
+    )
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/extract_mode.py

@@ -9,6 +9,7 @@ T_Result = typing.TypeVar("T_Result")
 class ExtractMode(str, enum.Enum):
     FAST = "FAST"
     BALANCED = "BALANCED"
+    PREMIUM = "PREMIUM"
     MULTIMODAL = "MULTIMODAL"
     ACCURATE = "ACCURATE"
 
@@ -16,6 +17,7 @@ class ExtractMode(str, enum.Enum):
         self,
         fast: typing.Callable[[], T_Result],
         balanced: typing.Callable[[], T_Result],
+        premium: typing.Callable[[], T_Result],
         multimodal: typing.Callable[[], T_Result],
         accurate: typing.Callable[[], T_Result],
     ) -> T_Result:
@@ -23,6 +25,8 @@ class ExtractMode(str, enum.Enum):
             return fast()
         if self is ExtractMode.BALANCED:
             return balanced()
+        if self is ExtractMode.PREMIUM:
+            return premium()
         if self is ExtractMode.MULTIMODAL:
             return multimodal()
         if self is ExtractMode.ACCURATE: