llama-cloud 0.1.17__py3-none-any.whl → 0.1.19__py3-none-any.whl

llama_cloud/types/__init__.py

@@ -16,6 +16,7 @@ from .advanced_mode_transform_config_segmentation_config import (
     AdvancedModeTransformConfigSegmentationConfig_Page,
 )
 from .app_schema_chat_chat_message import AppSchemaChatChatMessage
+from .audio_block import AudioBlock
 from .auto_transform_config import AutoTransformConfig
 from .azure_open_ai_embedding import AzureOpenAiEmbedding
 from .azure_open_ai_embedding_config import AzureOpenAiEmbeddingConfig
@@ -24,6 +25,10 @@ from .base_plan_metronome_plan_type import BasePlanMetronomePlanType
 from .base_plan_name import BasePlanName
 from .base_plan_plan_frequency import BasePlanPlanFrequency
 from .base_prompt_template import BasePromptTemplate
+from .batch import Batch
+from .batch_item import BatchItem
+from .batch_paginated_list import BatchPaginatedList
+from .batch_public_output import BatchPublicOutput
 from .bedrock_embedding import BedrockEmbedding
 from .bedrock_embedding_config import BedrockEmbeddingConfig
 from .billing_period import BillingPeriod
@@ -105,19 +110,10 @@ from .embedding_model_config_update_embedding_config import (
 )
 from .eval_execution_params import EvalExecutionParams
 from .extract_agent import ExtractAgent
-from .extract_agent_create import ExtractAgentCreate
-from .extract_agent_create_data_schema import ExtractAgentCreateDataSchema
-from .extract_agent_create_data_schema_zero_value import ExtractAgentCreateDataSchemaZeroValue
 from .extract_agent_data_schema_value import ExtractAgentDataSchemaValue
-from .extract_agent_update import ExtractAgentUpdate
-from .extract_agent_update_data_schema import ExtractAgentUpdateDataSchema
-from .extract_agent_update_data_schema_zero_value import ExtractAgentUpdateDataSchemaZeroValue
 from .extract_config import ExtractConfig
 from .extract_job import ExtractJob
 from .extract_job_create import ExtractJobCreate
-from .extract_job_create_batch import ExtractJobCreateBatch
-from .extract_job_create_batch_data_schema_override import ExtractJobCreateBatchDataSchemaOverride
-from .extract_job_create_batch_data_schema_override_zero_value import ExtractJobCreateBatchDataSchemaOverrideZeroValue
 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
@@ -132,14 +128,14 @@ 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_request import ExtractSchemaValidateRequest
-from .extract_schema_validate_request_data_schema import ExtractSchemaValidateRequestDataSchema
-from .extract_schema_validate_request_data_schema_zero_value import ExtractSchemaValidateRequestDataSchemaZeroValue
 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_parse_public import FileParsePublic
 from .file_permission_info_value import FilePermissionInfoValue
 from .file_resource_info_value import FileResourceInfoValue
 from .filter_condition import FilterCondition
@@ -162,6 +158,7 @@ from .llama_extract_settings import LlamaExtractSettings
 from .llama_index_core_base_llms_types_chat_message import LlamaIndexCoreBaseLlmsTypesChatMessage
 from .llama_index_core_base_llms_types_chat_message_blocks_item import (
     LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem,
+    LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Audio,
     LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Image,
     LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Text,
 )
@@ -208,9 +205,11 @@ from .parsing_job_markdown_result import ParsingJobMarkdownResult
 from .parsing_job_structured_result import ParsingJobStructuredResult
 from .parsing_job_text_result import ParsingJobTextResult
 from .parsing_mode import ParsingMode
-from .parsing_usage import ParsingUsage
 from .partition_names import PartitionNames
 from .permission import Permission
+from .pg_vector_distance_method import PgVectorDistanceMethod
+from .pg_vector_hnsw_settings import PgVectorHnswSettings
+from .pg_vector_vector_type import PgVectorVectorType
 from .pipeline import Pipeline
 from .pipeline_configuration_hashes import PipelineConfigurationHashes
 from .pipeline_create import PipelineCreate
@@ -229,6 +228,7 @@ 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 (
     PipelineEmbeddingConfig,
@@ -341,6 +341,7 @@ __all__ = [
     "AdvancedModeTransformConfigSegmentationConfig_None",
     "AdvancedModeTransformConfigSegmentationConfig_Page",
     "AppSchemaChatChatMessage",
+    "AudioBlock",
     "AutoTransformConfig",
     "AzureOpenAiEmbedding",
     "AzureOpenAiEmbeddingConfig",
@@ -349,6 +350,10 @@ __all__ = [
     "BasePlanName",
     "BasePlanPlanFrequency",
     "BasePromptTemplate",
+    "Batch",
+    "BatchItem",
+    "BatchPaginatedList",
+    "BatchPublicOutput",
     "BedrockEmbedding",
     "BedrockEmbeddingConfig",
     "BillingPeriod",
@@ -426,19 +431,10 @@ __all__ = [
     "EmbeddingModelConfigUpdateEmbeddingConfig_VertexaiEmbedding",
     "EvalExecutionParams",
     "ExtractAgent",
-    "ExtractAgentCreate",
-    "ExtractAgentCreateDataSchema",
-    "ExtractAgentCreateDataSchemaZeroValue",
     "ExtractAgentDataSchemaValue",
-    "ExtractAgentUpdate",
-    "ExtractAgentUpdateDataSchema",
-    "ExtractAgentUpdateDataSchemaZeroValue",
     "ExtractConfig",
     "ExtractJob",
     "ExtractJobCreate",
-    "ExtractJobCreateBatch",
-    "ExtractJobCreateBatchDataSchemaOverride",
-    "ExtractJobCreateBatchDataSchemaOverrideZeroValue",
     "ExtractJobCreateDataSchemaOverride",
     "ExtractJobCreateDataSchemaOverrideZeroValue",
     "ExtractMode",
@@ -453,14 +449,14 @@ __all__ = [
     "ExtractRunDataSchemaValue",
     "ExtractRunDataZeroValue",
     "ExtractRunExtractionMetadataValue",
-    "ExtractSchemaValidateRequest",
-    "ExtractSchemaValidateRequestDataSchema",
-    "ExtractSchemaValidateRequestDataSchemaZeroValue",
     "ExtractSchemaValidateResponse",
     "ExtractSchemaValidateResponseDataSchemaValue",
     "ExtractState",
     "ExtractTarget",
+    "FailPageMode",
     "File",
+    "FileCountByStatusResponse",
+    "FileParsePublic",
     "FilePermissionInfoValue",
     "FileResourceInfoValue",
     "FilterCondition",
@@ -482,6 +478,7 @@ __all__ = [
     "LlamaExtractSettings",
     "LlamaIndexCoreBaseLlmsTypesChatMessage",
     "LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem",
+    "LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Audio",
     "LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Image",
     "LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Text",
     "LlamaParseParameters",
@@ -527,9 +524,11 @@ __all__ = [
     "ParsingJobStructuredResult",
     "ParsingJobTextResult",
     "ParsingMode",
-    "ParsingUsage",
     "PartitionNames",
     "Permission",
+    "PgVectorDistanceMethod",
+    "PgVectorHnswSettings",
+    "PgVectorVectorType",
     "Pipeline",
     "PipelineConfigurationHashes",
     "PipelineCreate",
@@ -546,6 +545,7 @@ __all__ = [
     "PipelineDataSourceComponent",
     "PipelineDataSourceCreate",
     "PipelineDataSourceCustomMetadataValue",
+    "PipelineDataSourceStatus",
     "PipelineDeployment",
     "PipelineEmbeddingConfig",
     "PipelineEmbeddingConfig_AzureEmbedding",

llama_cloud/types/{parsing_usage.py → audio_block.py}

@@ -14,9 +14,11 @@ except ImportError:
     import pydantic  # type: ignore
 
 
-class ParsingUsage(pydantic.BaseModel):
-    usage_pdf_pages: int
-    max_pdf_pages: typing.Optional[int]
+class AudioBlock(pydantic.BaseModel):
+    audio: typing.Optional[str]
+    path: typing.Optional[str]
+    url: typing.Optional[str]
+    format: 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/batch.py

@@ -0,0 +1,47 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from .llama_parse_parameters import LlamaParseParameters
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class Batch(pydantic.BaseModel):
+    tool: str = pydantic.Field(description="The tool to be used for all requests in the batch.")
+    tool_data: typing.Optional[LlamaParseParameters]
+    input_type: str = pydantic.Field(description="The type of input file. Currently only 'datasource' is supported.")
+    input_id: str = pydantic.Field(description="The ID of the input file for the batch.")
+    output_type: typing.Optional[str]
+    output_id: typing.Optional[str]
+    id: str = pydantic.Field(description="Unique identifier for the batch")
+    project_id: str = pydantic.Field(description="The ID of the project to which the batch belongs")
+    organization_id: str = pydantic.Field(description="The ID of the organization to which the batch belongs")
+    user_id: str = pydantic.Field(description="The ID of the user who created the batch")
+    external_id: typing.Optional[str]
+    completion_window: int = pydantic.Field(description="The time frame within which the batch should be processed")
+    pipeline_id: str = pydantic.Field(description="The ID of the pipeline to which the batch belongs")
+    status: str = pydantic.Field(description="The current status of the batch")
+    created_at: typing.Optional[dt.datetime]
+    updated_at: typing.Optional[dt.datetime]
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        json_encoders = {dt.datetime: serialize_datetime}

llama_cloud/types/batch_item.py

@@ -0,0 +1,40 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from .file_parse_public import FileParsePublic
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class BatchItem(pydantic.BaseModel):
+    id: str = pydantic.Field(description="Unique identifier for the batch item")
+    batch_id: str = pydantic.Field(description="The ID of the batch to which the item belongs")
+    status: str = pydantic.Field(description="The current status of the batch item")
+    status_updated_at: typing.Optional[dt.datetime]
+    created_at: typing.Optional[dt.datetime]
+    updated_at: typing.Optional[dt.datetime]
+    input_file: str = pydantic.Field(description="The input file associated with the batch item")
+    output_file: typing.Optional[str]
+    task: typing.Optional[FileParsePublic]
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        json_encoders = {dt.datetime: serialize_datetime}

llama_cloud/types/{extract_agent_update.py → batch_paginated_list.py}

@@ -4,8 +4,7 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
-from .extract_agent_update_data_schema import ExtractAgentUpdateDataSchema
-from .extract_config import ExtractConfig
+from .batch import Batch
 
 try:
     import pydantic
@@ -16,13 +15,11 @@ except ImportError:
     import pydantic  # type: ignore
 
 
-class ExtractAgentUpdate(pydantic.BaseModel):
-    """
-    Settings for updating an extraction schema.
-    """
-
-    data_schema: ExtractAgentUpdateDataSchema = pydantic.Field(description="The schema of the data")
-    config: ExtractConfig = pydantic.Field(description="The configuration parameters for the extraction agent.")
+class BatchPaginatedList(pydantic.BaseModel):
+    data: typing.List[Batch] = pydantic.Field(description="List of batches")
+    limit: int = pydantic.Field(description="Pagination limit")
+    offset: int = pydantic.Field(description="Pagination offset")
+    total_count: int = pydantic.Field(description="Total number of batches")
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/{extract_schema_validate_request.py → batch_public_output.py}

@@ -4,7 +4,9 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
-from .extract_schema_validate_request_data_schema import ExtractSchemaValidateRequestDataSchema
+from .batch import Batch
+from .batch_item import BatchItem
+from .managed_ingestion_status_response import ManagedIngestionStatusResponse
 
 try:
     import pydantic
@@ -15,8 +17,10 @@ except ImportError:
     import pydantic  # type: ignore
 
 
-class ExtractSchemaValidateRequest(pydantic.BaseModel):
-    data_schema: ExtractSchemaValidateRequestDataSchema
+class BatchPublicOutput(pydantic.BaseModel):
+    batch: Batch
+    batch_items: typing.List[BatchItem]
+    ingestion_status: ManagedIngestionStatusResponse
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/cloud_confluence_data_source.py

@@ -27,6 +27,7 @@ class CloudConfluenceDataSource(pydantic.BaseModel):
     cql: typing.Optional[str]
     label: typing.Optional[str]
     index_restricted_pages: typing.Optional[bool] = pydantic.Field(description="Whether to index restricted pages.")
+    keep_markdown_format: typing.Optional[bool] = pydantic.Field(description="Whether to keep the markdown format.")
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/cloud_postgres_vector_store.py

@@ -4,6 +4,7 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
+from .pg_vector_hnsw_settings import PgVectorHnswSettings
 
 try:
     import pydantic
@@ -26,6 +27,7 @@ class CloudPostgresVectorStore(pydantic.BaseModel):
     embed_dim: int
     hybrid_search: typing.Optional[bool]
     perform_setup: typing.Optional[bool]
+    hnsw_settings: typing.Optional[PgVectorHnswSettings]
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/cloud_sharepoint_data_source.py

@@ -25,6 +25,7 @@ class CloudSharepointDataSource(pydantic.BaseModel):
     client_secret: str = pydantic.Field(description="The client secret to use for authentication.")
     tenant_id: str = pydantic.Field(description="The tenant ID to use for authentication.")
     required_exts: typing.Optional[typing.List[str]]
+    get_permissions: typing.Optional[bool]
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/extract_config.py

@@ -24,6 +24,8 @@ class ExtractConfig(pydantic.BaseModel):
     extraction_target: typing.Optional[ExtractTarget] = pydantic.Field(description="The extraction target specified.")
     extraction_mode: typing.Optional[ExtractMode] = pydantic.Field(description="The extraction mode specified.")
     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.")
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/fail_page_mode.py

@@ -0,0 +1,29 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import enum
+import typing
+
+T_Result = typing.TypeVar("T_Result")
+
+
+class FailPageMode(str, enum.Enum):
+    """
+    Enum for representing the different available page error handling modes
+    """
+
+    RAW_TEXT = "raw_text"
+    BLANK_PAGE = "blank_page"
+    ERROR_MESSAGE = "error_message"
+
+    def visit(
+        self,
+        raw_text: typing.Callable[[], T_Result],
+        blank_page: typing.Callable[[], T_Result],
+        error_message: typing.Callable[[], T_Result],
+    ) -> T_Result:
+        if self is FailPageMode.RAW_TEXT:
+            return raw_text()
+        if self is FailPageMode.BLANK_PAGE:
+            return blank_page()
+        if self is FailPageMode.ERROR_MESSAGE:
+            return error_message()

llama_cloud/types/{extract_agent_create.py → file_count_by_status_response.py}

@@ -4,8 +4,6 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
-from .extract_agent_create_data_schema import ExtractAgentCreateDataSchema
-from .extract_config import ExtractConfig
 
 try:
     import pydantic
@@ -16,14 +14,14 @@ except ImportError:
     import pydantic  # type: ignore
 
 
-class ExtractAgentCreate(pydantic.BaseModel):
-    """
-    Settings for creating an extraction agent.
-    """
-
-    name: str = pydantic.Field(description="The name of the extraction schema")
-    data_schema: ExtractAgentCreateDataSchema = pydantic.Field(description="The schema of the data.")
-    config: ExtractConfig = pydantic.Field(description="The configuration parameters for the extraction agent.")
+class FileCountByStatusResponse(pydantic.BaseModel):
+    counts: typing.Dict[str, int] = pydantic.Field(description="The counts of files by status")
+    total_count: int = pydantic.Field(description="The total number of files")
+    pipeline_id: typing.Optional[str]
+    data_source_id: typing.Optional[str]
+    only_manually_uploaded: typing.Optional[bool] = pydantic.Field(
+        description="Whether to only count manually uploaded files"
+    )
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/file_parse_public.py

@@ -0,0 +1,36 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class FileParsePublic(pydantic.BaseModel):
+    created_at: dt.datetime = pydantic.Field(description="The date and time when the file was parsed.")
+    status: str = pydantic.Field(description="The status of the parse task.")
+    started_at: typing.Optional[dt.datetime]
+    ended_at: typing.Optional[dt.datetime]
+    input_path: str = pydantic.Field(description="The path to the input file.")
+    data_path: str = pydantic.Field(description="The path to the data file.")
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        json_encoders = {dt.datetime: serialize_datetime}

llama_cloud/types/job_names.py

@@ -14,7 +14,6 @@ class JobNames(str, enum.Enum):
     LOAD_DOCUMENTS_JOB = "load_documents_job"
     LOAD_FILES_JOB = "load_files_job"
     PLAYGROUND_JOB = "playground_job"
-    EVAL_DATASET_JOB = "eval_dataset_job"
     PIPELINE_MANAGED_INGESTION_JOB = "pipeline_managed_ingestion_job"
     DATA_SOURCE_MANAGED_INGESTION_JOB = "data_source_managed_ingestion_job"
     DATA_SOURCE_UPDATE_DISPATCHER_JOB = "data_source_update_dispatcher_job"
@@ -22,20 +21,19 @@ class JobNames(str, enum.Enum):
     PIPELINE_FILE_UPDATER_JOB = "pipeline_file_updater_job"
     FILE_MANAGED_INGESTION_JOB = "file_managed_ingestion_job"
     DOCUMENT_INGESTION_JOB = "document_ingestion_job"
-    PARSE_RAW_FILE_JOB = "parse_raw_file_job"
-    LLAMA_PARSE_TRANSFORM_JOB = "llama_parse_transform_job"
     METADATA_UPDATE_JOB = "metadata_update_job"
     PARSE_RAW_FILE_JOB_CACHED = "parse_raw_file_job_cached"
     EXTRACTION_JOB = "extraction_job"
     EXTRACT_JOB = "extract_job"
     ASYNCIO_TEST_JOB = "asyncio_test_job"
+    PARSE_RAW_FILE_JOB = "parse_raw_file_job"
+    LLAMA_PARSE_TRANSFORM_JOB = "llama_parse_transform_job"
 
     def visit(
         self,
         load_documents_job: typing.Callable[[], T_Result],
         load_files_job: typing.Callable[[], T_Result],
         playground_job: typing.Callable[[], T_Result],
-        eval_dataset_job: typing.Callable[[], T_Result],
         pipeline_managed_ingestion_job: typing.Callable[[], T_Result],
         data_source_managed_ingestion_job: typing.Callable[[], T_Result],
         data_source_update_dispatcher_job: typing.Callable[[], T_Result],
@@ -43,13 +41,13 @@ class JobNames(str, enum.Enum):
         pipeline_file_updater_job: typing.Callable[[], T_Result],
         file_managed_ingestion_job: typing.Callable[[], T_Result],
         document_ingestion_job: typing.Callable[[], T_Result],
-        parse_raw_file_job: typing.Callable[[], T_Result],
-        llama_parse_transform_job: typing.Callable[[], T_Result],
         metadata_update_job: typing.Callable[[], T_Result],
         parse_raw_file_job_cached: typing.Callable[[], T_Result],
         extraction_job: typing.Callable[[], T_Result],
         extract_job: typing.Callable[[], T_Result],
         asyncio_test_job: typing.Callable[[], T_Result],
+        parse_raw_file_job: typing.Callable[[], T_Result],
+        llama_parse_transform_job: typing.Callable[[], T_Result],
     ) -> T_Result:
         if self is JobNames.LOAD_DOCUMENTS_JOB:
             return load_documents_job()
@@ -57,8 +55,6 @@ class JobNames(str, enum.Enum):
             return load_files_job()
         if self is JobNames.PLAYGROUND_JOB:
             return playground_job()
-        if self is JobNames.EVAL_DATASET_JOB:
-            return eval_dataset_job()
         if self is JobNames.PIPELINE_MANAGED_INGESTION_JOB:
             return pipeline_managed_ingestion_job()
         if self is JobNames.DATA_SOURCE_MANAGED_INGESTION_JOB:
@@ -73,10 +69,6 @@ class JobNames(str, enum.Enum):
             return file_managed_ingestion_job()
         if self is JobNames.DOCUMENT_INGESTION_JOB:
             return document_ingestion_job()
-        if self is JobNames.PARSE_RAW_FILE_JOB:
-            return parse_raw_file_job()
-        if self is JobNames.LLAMA_PARSE_TRANSFORM_JOB:
-            return llama_parse_transform_job()
         if self is JobNames.METADATA_UPDATE_JOB:
             return metadata_update_job()
         if self is JobNames.PARSE_RAW_FILE_JOB_CACHED:
@@ -87,3 +79,7 @@ class JobNames(str, enum.Enum):
             return extract_job()
         if self is JobNames.ASYNCIO_TEST_JOB:
             return asyncio_test_job()
+        if self is JobNames.PARSE_RAW_FILE_JOB:
+            return parse_raw_file_job()
+        if self is JobNames.LLAMA_PARSE_TRANSFORM_JOB:
+            return llama_parse_transform_job()

llama_cloud/types/llama_extract_settings.py

@@ -26,8 +26,8 @@ class LlamaExtractSettings(pydantic.BaseModel):
     max_file_size: typing.Optional[int] = pydantic.Field(
         description="The maximum file size (in bytes) allowed for the document."
     )
-    max_tokens: typing.Optional[int] = pydantic.Field(
-        description="The maximum number of tokens allowed for the document."
+    max_file_size_ui: typing.Optional[int] = pydantic.Field(
+        description="The maximum file size (in bytes) allowed for the document."
     )
     max_pages: typing.Optional[int] = pydantic.Field(
         description="The maximum number of pages allowed for the document."

llama_cloud/types/llama_index_core_base_llms_types_chat_message_blocks_item.py

@@ -6,10 +6,20 @@ import typing
 
 import typing_extensions
 
+from .audio_block import AudioBlock
 from .image_block import ImageBlock
 from .text_block import TextBlock
 
 
+class LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Audio(AudioBlock):
+    block_type: typing_extensions.Literal["audio"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
 class LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Image(ImageBlock):
     block_type: typing_extensions.Literal["image"]
 
@@ -29,5 +39,7 @@ class LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Text(TextBlock):
 
 
 LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem = typing.Union[
-    LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Image, LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Text
+    LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Audio,
+    LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Image,
+    LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Text,
 ]

llama_cloud/types/llama_parse_parameters.py

@@ -4,6 +4,7 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
+from .fail_page_mode import FailPageMode
 from .parser_languages import ParserLanguages
 from .parsing_mode import ParsingMode
 
@@ -26,6 +27,7 @@ class LlamaParseParameters(pydantic.BaseModel):
     disable_ocr: typing.Optional[bool]
     annotate_links: typing.Optional[bool]
     adaptive_long_table: typing.Optional[bool]
+    compact_markdown_table: typing.Optional[bool]
     disable_reconstruction: typing.Optional[bool]
     disable_image_extraction: typing.Optional[bool]
     invalidate_cache: typing.Optional[bool]
@@ -61,9 +63,9 @@ class LlamaParseParameters(pydantic.BaseModel):
     is_formatting_instruction: typing.Optional[bool]
     premium_mode: typing.Optional[bool]
     continuous_mode: typing.Optional[bool]
-    s_3_input_path: typing.Optional[str] = pydantic.Field(alias="s3_input_path")
+    input_s_3_path: typing.Optional[str] = pydantic.Field(alias="input_s3_path")
     input_s_3_region: typing.Optional[str] = pydantic.Field(alias="input_s3_region")
-    s_3_output_path_prefix: typing.Optional[str] = pydantic.Field(alias="s3_output_path_prefix")
+    output_s_3_path_prefix: typing.Optional[str] = pydantic.Field(alias="output_s3_path_prefix")
     output_s_3_region: typing.Optional[str] = pydantic.Field(alias="output_s3_region")
     project_id: typing.Optional[str]
     azure_openai_deployment_name: typing.Optional[str]
@@ -93,6 +95,7 @@ class LlamaParseParameters(pydantic.BaseModel):
     strict_mode_image_ocr: typing.Optional[bool]
     strict_mode_reconstruction: typing.Optional[bool]
     strict_mode_buggy_font: typing.Optional[bool]
+    save_images: typing.Optional[bool]
     ignore_document_elements_for_layout_detection: typing.Optional[bool]
     output_tables_as_html: typing.Optional[bool] = pydantic.Field(alias="output_tables_as_HTML")
     internal_is_screenshot_job: typing.Optional[bool]
@@ -100,6 +103,11 @@ class LlamaParseParameters(pydantic.BaseModel):
     system_prompt: typing.Optional[str]
     system_prompt_append: typing.Optional[str]
     user_prompt: typing.Optional[str]
+    page_error_tolerance: typing.Optional[float]
+    replace_failed_page_mode: typing.Optional[FailPageMode]
+    replace_failed_page_with_error_message_prefix: typing.Optional[str]
+    replace_failed_page_with_error_message_suffix: typing.Optional[str]
+    markdown_table_multiline_header_separator: 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/markdown_node_parser.py

@@ -24,6 +24,7 @@ class MarkdownNodeParser(pydantic.BaseModel):
     Args:
     include_metadata (bool): whether to include metadata in nodes
     include_prev_next_rel (bool): whether to include prev/next relationships
+    header_path_separator (str): separator char used for section header path metadata
     """
 
     include_metadata: typing.Optional[bool] = pydantic.Field(
@@ -32,6 +33,9 @@ class MarkdownNodeParser(pydantic.BaseModel):
     include_prev_next_rel: typing.Optional[bool] = pydantic.Field(description="Include prev/next node relationships.")
     callback_manager: typing.Optional[typing.Any]
     id_func: typing.Optional[str]
+    header_path_separator: typing.Optional[str] = pydantic.Field(
+        description="Separator char used for section header path metadata."
+    )
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str: