llama-cloud 0.1.34__py3-none-any.whl → 0.1.36__py3-none-any.whl

llama_cloud/types/classify_parsing_configuration.py

@@ -0,0 +1,38 @@
+# 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 .parser_languages import ParserLanguages
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class ClassifyParsingConfiguration(pydantic.BaseModel):
+    """
+    Parsing configuration for a classify job.
+    """
+
+    lang: typing.Optional[ParserLanguages] = pydantic.Field(description="The language to parse the files in")
+    max_pages: typing.Optional[int]
+    target_pages: typing.Optional[typing.List[int]]
+
+    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/cloud_astra_db_vector_store.py

@@ -0,0 +1,51 @@
+# 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 CloudAstraDbVectorStore(pydantic.BaseModel):
+    """
+    Cloud AstraDB Vector Store.
+
+    This class is used to store the configuration for an AstraDB vector store, so that it can be
+    created and used in LlamaCloud.
+
+    Args:
+    token (str): The Astra DB Application Token to use.
+    api_endpoint (str): The Astra DB JSON API endpoint for your database.
+    collection_name (str): Collection name to use. If not existing, it will be created.
+    embedding_dimension (int): Length of the embedding vectors in use.
+    keyspace (optional[str]): The keyspace to use. If not provided, 'default_keyspace'
+    """
+
+    supports_nested_metadata_filters: typing.Optional[bool]
+    token: str = pydantic.Field(description="The Astra DB Application Token to use")
+    api_endpoint: str = pydantic.Field(description="The Astra DB JSON API endpoint for your database")
+    collection_name: str = pydantic.Field(description="Collection name to use. If not existing, it will be created")
+    embedding_dimension: int = pydantic.Field(description="Length of the embedding vectors in use")
+    keyspace: typing.Optional[str]
+    class_name: typing.Optional[str]
+
+    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/cloud_confluence_data_source.py

@@ -4,6 +4,7 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
+from .failure_handling_config import FailureHandlingConfig
 
 try:
     import pydantic
@@ -28,6 +29,20 @@ class CloudConfluenceDataSource(pydantic.BaseModel):
     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.")
+    failure_handling: typing.Optional[FailureHandlingConfig] = pydantic.Field(
+        description=(
+            "Configuration for handling failures during processing. Key-value object controlling failure handling behaviors.\n"
+            "\n"
+            "Example:\n"
+            "{\n"
+            '"skip_list_failures": true\n'
+            "}\n"
+            "\n"
+            "Currently supports:\n"
+            "\n"
+            "- skip_list_failures: Skip failed batches/lists and continue processing\n"
+        )
+    )
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/configurable_data_sink_names.py

@@ -13,6 +13,7 @@ class ConfigurableDataSinkNames(str, enum.Enum):
     AZUREAI_SEARCH = "AZUREAI_SEARCH"
     MONGODB_ATLAS = "MONGODB_ATLAS"
     MILVUS = "MILVUS"
+    ASTRA_DB = "ASTRA_DB"
 
     def visit(
         self,
@@ -22,6 +23,7 @@ class ConfigurableDataSinkNames(str, enum.Enum):
         azureai_search: typing.Callable[[], T_Result],
         mongodb_atlas: typing.Callable[[], T_Result],
         milvus: typing.Callable[[], T_Result],
+        astra_db: typing.Callable[[], T_Result],
     ) -> T_Result:
         if self is ConfigurableDataSinkNames.PINECONE:
             return pinecone()
@@ -35,3 +37,5 @@ class ConfigurableDataSinkNames(str, enum.Enum):
             return mongodb_atlas()
         if self is ConfigurableDataSinkNames.MILVUS:
             return milvus()
+        if self is ConfigurableDataSinkNames.ASTRA_DB:
+            return astra_db()

llama_cloud/types/data_sink_component.py

@@ -2,6 +2,7 @@
 
 import typing
 
+from .cloud_astra_db_vector_store import CloudAstraDbVectorStore
 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
@@ -17,4 +18,5 @@ DataSinkComponent = typing.Union[
     CloudAzureAiSearchVectorStore,
     CloudMongoDbAtlasVectorSearch,
     CloudMilvusVectorStore,
+    CloudAstraDbVectorStore,
 ]

llama_cloud/types/data_sink_create_component.py

@@ -2,6 +2,7 @@
 
 import typing
 
+from .cloud_astra_db_vector_store import CloudAstraDbVectorStore
 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
@@ -17,4 +18,5 @@ DataSinkCreateComponent = typing.Union[
     CloudAzureAiSearchVectorStore,
     CloudMongoDbAtlasVectorSearch,
     CloudMilvusVectorStore,
+    CloudAstraDbVectorStore,
 ]

llama_cloud/types/data_source_reader_version_metadata.py

@@ -4,6 +4,7 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
+from .data_source_reader_version_metadata_reader_version import DataSourceReaderVersionMetadataReaderVersion
 
 try:
     import pydantic
@@ -15,7 +16,7 @@ except ImportError:
 
 
 class DataSourceReaderVersionMetadata(pydantic.BaseModel):
-    reader_version: typing.Optional[str]
+    reader_version: typing.Optional[DataSourceReaderVersionMetadataReaderVersion]
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/data_source_reader_version_metadata_reader_version.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 DataSourceReaderVersionMetadataReaderVersion(str, enum.Enum):
+    ONE_0 = "1.0"
+    TWO_0 = "2.0"
+
+    def visit(self, one_0: typing.Callable[[], T_Result], two_0: typing.Callable[[], T_Result]) -> T_Result:
+        if self is DataSourceReaderVersionMetadataReaderVersion.ONE_0:
+            return one_0()
+        if self is DataSourceReaderVersionMetadataReaderVersion.TWO_0:
+            return two_0()

llama_cloud/types/extract_agent.py

@@ -3,6 +3,8 @@
 import datetime as dt
 import typing
 
+import typing_extensions
+
 from ..core.datetime_utils import serialize_datetime
 from .extract_agent_data_schema_value import ExtractAgentDataSchemaValue
 from .extract_config import ExtractConfig
@@ -28,6 +30,7 @@ class ExtractAgent(pydantic.BaseModel):
         description="The schema of the data."
     )
     config: ExtractConfig = pydantic.Field(description="The configuration parameters for the extraction agent.")
+    custom_configuration: typing.Optional[typing_extensions.Literal["default"]]
     created_at: typing.Optional[dt.datetime]
     updated_at: typing.Optional[dt.datetime]
 

llama_cloud/types/extract_config.py

@@ -38,9 +38,13 @@ class ExtractConfig(pydantic.BaseModel):
     chunk_mode: typing.Optional[DocumentChunkMode] = pydantic.Field(
         description="The mode to use for chunking the document."
     )
+    high_resolution_mode: typing.Optional[bool] = pydantic.Field(
+        description="Whether to use high resolution mode for the extraction."
+    )
     invalidate_cache: typing.Optional[bool] = pydantic.Field(
         description="Whether to invalidate the cache for the extraction."
     )
+    page_range: 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/failure_handling_config.py

@@ -0,0 +1,37 @@
+# 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 FailureHandlingConfig(pydantic.BaseModel):
+    """
+    Configuration for handling different types of failures during data source processing.
+    """
+
+    skip_list_failures: typing.Optional[bool] = pydantic.Field(
+        description="Whether to skip failed batches/lists and continue processing"
+    )
+
+    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/file_classification.py

@@ -0,0 +1,41 @@
+# 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 .classification_result import ClassificationResult
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class FileClassification(pydantic.BaseModel):
+    """
+    A file classification.
+    """
+
+    id: str = pydantic.Field(description="Unique identifier")
+    created_at: typing.Optional[dt.datetime]
+    updated_at: typing.Optional[dt.datetime]
+    classify_job_id: str = pydantic.Field(description="The ID of the classify job")
+    file_id: str = pydantic.Field(description="The ID of the classified file")
+    result: typing.Optional[ClassificationResult]
+
+    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/file_data.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 FileData(pydantic.BaseModel):
+    """
+    Schema for file data with base64 content and MIME type.
+    """
+
+    data: str = pydantic.Field(description="The file content as base64-encoded string")
+    mime_type: str = pydantic.Field(description="The MIME type of the file (e.g., 'application/pdf', 'text/plain')")
+
+    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/file_store_info_response.py

@@ -0,0 +1,34 @@
+# 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_store_info_response_status import FileStoreInfoResponseStatus
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class FileStoreInfoResponse(pydantic.BaseModel):
+    available_buckets: typing.Optional[typing.Dict[str, str]]
+    unavailable_buckets: typing.Optional[typing.Dict[str, str]]
+    status: FileStoreInfoResponseStatus
+
+    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/file_store_info_response_status.py

@@ -0,0 +1,25 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import enum
+import typing
+
+T_Result = typing.TypeVar("T_Result")
+
+
+class FileStoreInfoResponseStatus(str, enum.Enum):
+    OK = "ok"
+    MISSING_BUCKETS = "missing_buckets"
+    MISSING_CREDENTIALS = "missing_credentials"
+
+    def visit(
+        self,
+        ok: typing.Callable[[], T_Result],
+        missing_buckets: typing.Callable[[], T_Result],
+        missing_credentials: typing.Callable[[], T_Result],
+    ) -> T_Result:
+        if self is FileStoreInfoResponseStatus.OK:
+            return ok()
+        if self is FileStoreInfoResponseStatus.MISSING_BUCKETS:
+            return missing_buckets()
+        if self is FileStoreInfoResponseStatus.MISSING_CREDENTIALS:
+            return missing_credentials()

llama_cloud/types/legacy_parse_job_config.py

@@ -43,6 +43,9 @@ class LegacyParseJobConfig(pydantic.BaseModel):
     preserve_layout_alignment_across_pages: typing.Optional[bool] = pydantic.Field(
         alias="preserveLayoutAlignmentAcrossPages", description="Whether to preserve layout alignment across pages."
     )
+    preserve_very_small_text: typing.Optional[bool] = pydantic.Field(
+        alias="preserveVerySmallText", description="Whether to preserve very small text lines."
+    )
     invalidate_cache: bool = pydantic.Field(alias="invalidateCache", description="Whether to invalidate the cache.")
     output_pdf_of_document: typing.Optional[bool] = pydantic.Field(alias="outputPDFOfDocument")
     outlined_table_extraction: typing.Optional[bool] = pydantic.Field(alias="outlinedTableExtraction")

llama_cloud/types/llama_extract_settings.py

@@ -6,6 +6,7 @@ import typing
 from ..core.datetime_utils import serialize_datetime
 from .chunk_mode import ChunkMode
 from .llama_parse_parameters import LlamaParseParameters
+from .multimodal_parse_resolution import MultimodalParseResolution
 from .struct_parse_conf import StructParseConf
 
 try:
@@ -48,6 +49,9 @@ class LlamaExtractSettings(pydantic.BaseModel):
     llama_parse_params: typing.Optional[LlamaParseParameters] = pydantic.Field(
         description="LlamaParse related settings."
     )
+    multimodal_parse_resolution: typing.Optional[MultimodalParseResolution] = pydantic.Field(
+        description="The resolution to use for multimodal parsing."
+    )
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/llama_parse_parameters.py

@@ -8,6 +8,7 @@ from .fail_page_mode import FailPageMode
 from .llama_parse_parameters_priority import LlamaParseParametersPriority
 from .parser_languages import ParserLanguages
 from .parsing_mode import ParsingMode
+from .webhook_configuration import WebhookConfiguration
 
 try:
     import pydantic
@@ -23,6 +24,7 @@ class LlamaParseParameters(pydantic.BaseModel):
     Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline.
     """
 
+    webhook_configurations: typing.Optional[typing.List[WebhookConfiguration]]
     priority: typing.Optional[LlamaParseParametersPriority]
     languages: typing.Optional[typing.List[ParserLanguages]]
     parsing_instruction: typing.Optional[str]
@@ -40,6 +42,7 @@ class LlamaParseParameters(pydantic.BaseModel):
     fast_mode: typing.Optional[bool]
     skip_diagonal_text: typing.Optional[bool]
     preserve_layout_alignment_across_pages: typing.Optional[bool]
+    preserve_very_small_text: typing.Optional[bool]
     gpt_4_o_mode: typing.Optional[bool] = pydantic.Field(alias="gpt4o_mode")
     gpt_4_o_api_key: typing.Optional[str] = pydantic.Field(alias="gpt4o_api_key")
     do_not_unroll_columns: typing.Optional[bool]

llama_cloud/types/managed_open_ai_embedding.py

@@ -0,0 +1,36 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+import typing_extensions
+
+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 ManagedOpenAiEmbedding(pydantic.BaseModel):
+    model_name: typing.Optional[typing_extensions.Literal["openai-text-embedding-3-small"]]
+    embed_batch_size: typing.Optional[int] = pydantic.Field(description="The batch size for embedding calls.")
+    num_workers: typing.Optional[int]
+    class_name: typing.Optional[str]
+
+    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/managed_open_ai_embedding_config.py

@@ -0,0 +1,34 @@
+# 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 .managed_open_ai_embedding import ManagedOpenAiEmbedding
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class ManagedOpenAiEmbeddingConfig(pydantic.BaseModel):
+    component: typing.Optional[ManagedOpenAiEmbedding] = pydantic.Field(
+        description="Configuration for the Managed OpenAI embedding model."
+    )
+
+    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/multimodal_parse_resolution.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 MultimodalParseResolution(str, enum.Enum):
+    MEDIUM = "medium"
+    HIGH = "high"
+
+    def visit(self, medium: typing.Callable[[], T_Result], high: typing.Callable[[], T_Result]) -> T_Result:
+        if self is MultimodalParseResolution.MEDIUM:
+            return medium()
+        if self is MultimodalParseResolution.HIGH:
+            return high()

llama_cloud/types/paginated_response_quota_configuration.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
+from .quota_configuration import QuotaConfiguration
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class PaginatedResponseQuotaConfiguration(pydantic.BaseModel):
+    total: int
+    page: int
+    size: int
+    pages: int
+    items: typing.List[QuotaConfiguration]
+
+    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/parse_job_config.py

@@ -8,6 +8,7 @@ from .fail_page_mode import FailPageMode
 from .parse_job_config_priority import ParseJobConfigPriority
 from .parser_languages import ParserLanguages
 from .parsing_mode import ParsingMode
+from .webhook_configuration import WebhookConfiguration
 
 try:
     import pydantic
@@ -23,6 +24,7 @@ class ParseJobConfig(pydantic.BaseModel):
     Configuration for llamaparse job
     """
 
+    webhook_configurations: typing.Optional[typing.List[WebhookConfiguration]]
     priority: typing.Optional[ParseJobConfigPriority]
     custom_metadata: typing.Optional[typing.Dict[str, typing.Any]]
     resource_info: typing.Optional[typing.Dict[str, typing.Any]]
@@ -42,6 +44,7 @@ class ParseJobConfig(pydantic.BaseModel):
     fast_mode: typing.Optional[bool]
     skip_diagonal_text: typing.Optional[bool]
     preserve_layout_alignment_across_pages: typing.Optional[bool]
+    preserve_very_small_text: typing.Optional[bool]
     gpt_4_o_mode: typing.Optional[bool] = pydantic.Field(alias="gpt4o_mode")
     gpt_4_o_api_key: typing.Optional[str] = pydantic.Field(alias="gpt4o_api_key")
     do_not_unroll_columns: typing.Optional[bool]

llama_cloud/types/pipeline_embedding_config.py

@@ -11,6 +11,7 @@ from .bedrock_embedding_config import BedrockEmbeddingConfig
 from .cohere_embedding_config import CohereEmbeddingConfig
 from .gemini_embedding_config import GeminiEmbeddingConfig
 from .hugging_face_inference_api_embedding_config import HuggingFaceInferenceApiEmbeddingConfig
+from .managed_open_ai_embedding_config import ManagedOpenAiEmbeddingConfig
 from .open_ai_embedding_config import OpenAiEmbeddingConfig
 from .vertex_ai_embedding_config import VertexAiEmbeddingConfig
 
@@ -60,6 +61,15 @@ class PipelineEmbeddingConfig_HuggingfaceApiEmbedding(HuggingFaceInferenceApiEmb
         allow_population_by_field_name = True
 
 
+class PipelineEmbeddingConfig_ManagedOpenaiEmbedding(ManagedOpenAiEmbeddingConfig):
+    type: typing_extensions.Literal["MANAGED_OPENAI_EMBEDDING"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
 class PipelineEmbeddingConfig_OpenaiEmbedding(OpenAiEmbeddingConfig):
     type: typing_extensions.Literal["OPENAI_EMBEDDING"]
 
@@ -84,6 +94,7 @@ PipelineEmbeddingConfig = typing.Union[
     PipelineEmbeddingConfig_CohereEmbedding,
     PipelineEmbeddingConfig_GeminiEmbedding,
     PipelineEmbeddingConfig_HuggingfaceApiEmbedding,
+    PipelineEmbeddingConfig_ManagedOpenaiEmbedding,
     PipelineEmbeddingConfig_OpenaiEmbedding,
     PipelineEmbeddingConfig_VertexaiEmbedding,
 ]