llama-cloud 0.0.10__py3-none-any.whl → 0.0.12__py3-none-any.whl

llama_cloud/types/configurable_transformation_names.py

@@ -11,13 +11,12 @@ class ConfigurableTransformationNames(str, enum.Enum):
     An enumeration.
     """
 
+    CHARACTER_SPLITTER = "CHARACTER_SPLITTER"
+    PAGE_SPLITTER_NODE_PARSER = "PAGE_SPLITTER_NODE_PARSER"
     CODE_NODE_PARSER = "CODE_NODE_PARSER"
     SENTENCE_AWARE_NODE_PARSER = "SENTENCE_AWARE_NODE_PARSER"
     TOKEN_AWARE_NODE_PARSER = "TOKEN_AWARE_NODE_PARSER"
-    HTML_NODE_PARSER = "HTML_NODE_PARSER"
     MARKDOWN_NODE_PARSER = "MARKDOWN_NODE_PARSER"
-    JSON_NODE_PARSER = "JSON_NODE_PARSER"
-    SIMPLE_FILE_NODE_PARSER = "SIMPLE_FILE_NODE_PARSER"
     MARKDOWN_ELEMENT_NODE_PARSER = "MARKDOWN_ELEMENT_NODE_PARSER"
     OPENAI_EMBEDDING = "OPENAI_EMBEDDING"
     AZURE_EMBEDDING = "AZURE_EMBEDDING"
@@ -28,13 +27,12 @@ class ConfigurableTransformationNames(str, enum.Enum):
 
     def visit(
         self,
+        character_splitter: typing.Callable[[], T_Result],
+        page_splitter_node_parser: typing.Callable[[], T_Result],
         code_node_parser: typing.Callable[[], T_Result],
         sentence_aware_node_parser: typing.Callable[[], T_Result],
         token_aware_node_parser: typing.Callable[[], T_Result],
-        html_node_parser: typing.Callable[[], T_Result],
         markdown_node_parser: typing.Callable[[], T_Result],
-        json_node_parser: typing.Callable[[], T_Result],
-        simple_file_node_parser: typing.Callable[[], T_Result],
         markdown_element_node_parser: typing.Callable[[], T_Result],
         openai_embedding: typing.Callable[[], T_Result],
         azure_embedding: typing.Callable[[], T_Result],
@@ -43,20 +41,18 @@ class ConfigurableTransformationNames(str, enum.Enum):
         huggingface_api_embedding: typing.Callable[[], T_Result],
         gemini_embedding: typing.Callable[[], T_Result],
     ) -> T_Result:
+        if self is ConfigurableTransformationNames.CHARACTER_SPLITTER:
+            return character_splitter()
+        if self is ConfigurableTransformationNames.PAGE_SPLITTER_NODE_PARSER:
+            return page_splitter_node_parser()
         if self is ConfigurableTransformationNames.CODE_NODE_PARSER:
             return code_node_parser()
         if self is ConfigurableTransformationNames.SENTENCE_AWARE_NODE_PARSER:
             return sentence_aware_node_parser()
         if self is ConfigurableTransformationNames.TOKEN_AWARE_NODE_PARSER:
             return token_aware_node_parser()
-        if self is ConfigurableTransformationNames.HTML_NODE_PARSER:
-            return html_node_parser()
         if self is ConfigurableTransformationNames.MARKDOWN_NODE_PARSER:
             return markdown_node_parser()
-        if self is ConfigurableTransformationNames.JSON_NODE_PARSER:
-            return json_node_parser()
-        if self is ConfigurableTransformationNames.SIMPLE_FILE_NODE_PARSER:
-            return simple_file_node_parser()
         if self is ConfigurableTransformationNames.MARKDOWN_ELEMENT_NODE_PARSER:
             return markdown_element_node_parser()
         if self is ConfigurableTransformationNames.OPENAI_EMBEDDING:

llama_cloud/types/configured_transformation_item_component_one.py

@@ -4,27 +4,25 @@ import typing
 
 from .azure_open_ai_embedding import AzureOpenAiEmbedding
 from .bedrock_embedding import BedrockEmbedding
+from .character_splitter import CharacterSplitter
 from .code_splitter import CodeSplitter
 from .cohere_embedding import CohereEmbedding
 from .gemini_embedding import GeminiEmbedding
-from .html_node_parser import HtmlNodeParser
 from .hugging_face_inference_api_embedding import HuggingFaceInferenceApiEmbedding
-from .json_node_parser import JsonNodeParser
 from .markdown_element_node_parser import MarkdownElementNodeParser
 from .markdown_node_parser import MarkdownNodeParser
 from .open_ai_embedding import OpenAiEmbedding
+from .page_splitter_node_parser import PageSplitterNodeParser
 from .sentence_splitter import SentenceSplitter
-from .simple_file_node_parser import SimpleFileNodeParser
 from .token_text_splitter import TokenTextSplitter
 
 ConfiguredTransformationItemComponentOne = typing.Union[
+    CharacterSplitter,
+    PageSplitterNodeParser,
     CodeSplitter,
     SentenceSplitter,
     TokenTextSplitter,
-    HtmlNodeParser,
     MarkdownNodeParser,
-    JsonNodeParser,
-    SimpleFileNodeParser,
     MarkdownElementNodeParser,
     OpenAiEmbedding,
     AzureOpenAiEmbedding,

llama_cloud/types/custom_claims.py

@@ -0,0 +1,61 @@
+# 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 CustomClaims(pydantic.BaseModel):
+    """
+    Custom claims that dictate various limits or allowed behaviors.
+    Currently these claims reside at a per user level. Claims may expand to a per organization level or project in the future.
+    """
+
+    allowed_index: typing.Optional[bool] = pydantic.Field(
+        description="Whether the user is allowed to access the index."
+    )
+    allowed_playground: typing.Optional[bool] = pydantic.Field(description="Deprecated. Use allowed_index instead")
+    usage_pdf_max_pages_per_day: typing.Optional[int] = pydantic.Field(
+        description="The maximum number of PDF pages the user can generate per day."
+    )
+    parse_premium: typing.Optional[bool] = pydantic.Field(
+        description="Whether the user has a LlamaParse premium claim."
+    )
+    usage_index_max_files_per_pipeline: typing.Optional[int] = pydantic.Field(
+        description="The maximum number of files per pipeline the user can index without LlamaParse premium."
+    )
+    max_jobs_in_execution: typing.Optional[int] = pydantic.Field(
+        description="The maximum number of jobs the user can have in execution."
+    )
+    max_jobs_in_execution_per_job_type: typing.Optional[int] = pydantic.Field(
+        description="The maximum number of jobs the user can have in execution per job type."
+    )
+    max_document_ingestion_jobs_in_execution: typing.Optional[int] = pydantic.Field(
+        description="The maximum number of document ingestion jobs the user can have in execution."
+    )
+    allowed_extraction: typing.Optional[bool] = pydantic.Field(
+        description="Whether the user is allowed to use structured data extraction features."
+    )
+    allowed_eval: typing.Optional[bool] = pydantic.Field(description="Whether the user is allowed to run evals.")
+
+    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/data_sink_component_one.py

@@ -4,6 +4,8 @@ import typing
 
 from .cloud_azure_ai_search_vector_store import CloudAzureAiSearchVectorStore
 from .cloud_chroma_vector_store import CloudChromaVectorStore
+from .cloud_milvus_vector_store import CloudMilvusVectorStore
+from .cloud_mongo_db_atlas_vector_search import CloudMongoDbAtlasVectorSearch
 from .cloud_pinecone_vector_store import CloudPineconeVectorStore
 from .cloud_postgres_vector_store import CloudPostgresVectorStore
 from .cloud_qdrant_vector_store import CloudQdrantVectorStore
@@ -16,4 +18,6 @@ DataSinkComponentOne = typing.Union[
     CloudQdrantVectorStore,
     CloudWeaviateVectorStore,
     CloudAzureAiSearchVectorStore,
+    CloudMongoDbAtlasVectorSearch,
+    CloudMilvusVectorStore,
 ]

llama_cloud/types/data_sink_create_component_one.py

@@ -4,6 +4,8 @@ import typing
 
 from .cloud_azure_ai_search_vector_store import CloudAzureAiSearchVectorStore
 from .cloud_chroma_vector_store import CloudChromaVectorStore
+from .cloud_milvus_vector_store import CloudMilvusVectorStore
+from .cloud_mongo_db_atlas_vector_search import CloudMongoDbAtlasVectorSearch
 from .cloud_pinecone_vector_store import CloudPineconeVectorStore
 from .cloud_postgres_vector_store import CloudPostgresVectorStore
 from .cloud_qdrant_vector_store import CloudQdrantVectorStore
@@ -16,4 +18,6 @@ DataSinkCreateComponentOne = typing.Union[
     CloudQdrantVectorStore,
     CloudWeaviateVectorStore,
     CloudAzureAiSearchVectorStore,
+    CloudMongoDbAtlasVectorSearch,
+    CloudMilvusVectorStore,
 ]

llama_cloud/types/element_segmentation_config.py

@@ -0,0 +1,29 @@
+# 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 ElementSegmentationConfig(pydantic.BaseModel):
+    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/embedding_config.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 .embedding_config_component import EmbeddingConfigComponent
+from .embedding_config_type import EmbeddingConfigType
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class EmbeddingConfig(pydantic.BaseModel):
+    type: typing.Optional[EmbeddingConfigType] = pydantic.Field(description="Type of the embedding model.")
+    component: typing.Optional[EmbeddingConfigComponent] = pydantic.Field(
+        description="Configuration for the transformation."
+    )
+
+    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/embedding_config_component.py

@@ -0,0 +1,7 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+from .embedding_config_component_one import EmbeddingConfigComponentOne
+
+EmbeddingConfigComponent = typing.Union[typing.Dict[str, typing.Any], EmbeddingConfigComponentOne]

llama_cloud/types/embedding_config_component_one.py

@@ -0,0 +1,19 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+from .azure_open_ai_embedding import AzureOpenAiEmbedding
+from .bedrock_embedding import BedrockEmbedding
+from .cohere_embedding import CohereEmbedding
+from .gemini_embedding import GeminiEmbedding
+from .hugging_face_inference_api_embedding import HuggingFaceInferenceApiEmbedding
+from .open_ai_embedding import OpenAiEmbedding
+
+EmbeddingConfigComponentOne = typing.Union[
+    OpenAiEmbedding,
+    AzureOpenAiEmbedding,
+    CohereEmbedding,
+    BedrockEmbedding,
+    HuggingFaceInferenceApiEmbedding,
+    GeminiEmbedding,
+]

llama_cloud/types/embedding_config_type.py

@@ -0,0 +1,41 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import enum
+import typing
+
+T_Result = typing.TypeVar("T_Result")
+
+
+class EmbeddingConfigType(str, enum.Enum):
+    """
+    An enumeration.
+    """
+
+    OPENAI_EMBEDDING = "OPENAI_EMBEDDING"
+    AZURE_EMBEDDING = "AZURE_EMBEDDING"
+    BEDROCK_EMBEDDING = "BEDROCK_EMBEDDING"
+    COHERE_EMBEDDING = "COHERE_EMBEDDING"
+    GEMINI_EMBEDDING = "GEMINI_EMBEDDING"
+    HUGGINGFACE_API_EMBEDDING = "HUGGINGFACE_API_EMBEDDING"
+
+    def visit(
+        self,
+        openai_embedding: typing.Callable[[], T_Result],
+        azure_embedding: typing.Callable[[], T_Result],
+        bedrock_embedding: typing.Callable[[], T_Result],
+        cohere_embedding: typing.Callable[[], T_Result],
+        gemini_embedding: typing.Callable[[], T_Result],
+        huggingface_api_embedding: typing.Callable[[], T_Result],
+    ) -> T_Result:
+        if self is EmbeddingConfigType.OPENAI_EMBEDDING:
+            return openai_embedding()
+        if self is EmbeddingConfigType.AZURE_EMBEDDING:
+            return azure_embedding()
+        if self is EmbeddingConfigType.BEDROCK_EMBEDDING:
+            return bedrock_embedding()
+        if self is EmbeddingConfigType.COHERE_EMBEDDING:
+            return cohere_embedding()
+        if self is EmbeddingConfigType.GEMINI_EMBEDDING:
+            return gemini_embedding()
+        if self is EmbeddingConfigType.HUGGINGFACE_API_EMBEDDING:
+            return huggingface_api_embedding()

llama_cloud/types/eval_dataset_job_record.py

@@ -42,6 +42,7 @@ class EvalDatasetJobRecord(pydantic.BaseModel):
     created_at: typing.Optional[dt.datetime] = pydantic.Field(description="Creation datetime")
     id: typing.Optional[str] = pydantic.Field(description="Unique identifier")
     status: StatusEnum
+    error_code: typing.Optional[str]
     error_message: typing.Optional[str]
     attempts: typing.Optional[int] = pydantic.Field(description="The number of times this job has been attempted")
     started_at: typing.Optional[dt.datetime]

llama_cloud/types/ingestion_error_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 .job_name_mapping import JobNameMapping
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class IngestionErrorResponse(pydantic.BaseModel):
+    job_id: str = pydantic.Field(description="ID of the job that failed.")
+    message: str = pydantic.Field(description="List of errors that occurred during ingestion.")
+    step: JobNameMapping = pydantic.Field(description="Name of the job that failed.")
+
+    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_name_mapping.py

@@ -0,0 +1,45 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import enum
+import typing
+
+T_Result = typing.TypeVar("T_Result")
+
+
+class JobNameMapping(str, enum.Enum):
+    """
+    Enum for mapping original job names to readable names.
+    """
+
+    MANAGED_INGESTION = "MANAGED_INGESTION"
+    DATA_SOURCE = "DATA_SOURCE"
+    FILES_UPDATE = "FILES_UPDATE"
+    FILE_UPDATER = "FILE_UPDATER"
+    PARSE = "PARSE"
+    TRANSFORM = "TRANSFORM"
+    INGESTION = "INGESTION"
+
+    def visit(
+        self,
+        managed_ingestion: typing.Callable[[], T_Result],
+        data_source: typing.Callable[[], T_Result],
+        files_update: typing.Callable[[], T_Result],
+        file_updater: typing.Callable[[], T_Result],
+        parse: typing.Callable[[], T_Result],
+        transform: typing.Callable[[], T_Result],
+        ingestion: typing.Callable[[], T_Result],
+    ) -> T_Result:
+        if self is JobNameMapping.MANAGED_INGESTION:
+            return managed_ingestion()
+        if self is JobNameMapping.DATA_SOURCE:
+            return data_source()
+        if self is JobNameMapping.FILES_UPDATE:
+            return files_update()
+        if self is JobNameMapping.FILE_UPDATER:
+            return file_updater()
+        if self is JobNameMapping.PARSE:
+            return parse()
+        if self is JobNameMapping.TRANSFORM:
+            return transform()
+        if self is JobNameMapping.INGESTION:
+            return ingestion()

llama_cloud/types/llama_parse_supported_file_extensions.py

@@ -45,6 +45,14 @@ class LlamaParseSupportedFileExtensions(str, enum.Enum):
     SXI = ".sxi"
     STI = ".sti"
     EPUB = ".epub"
+    JPG = ".jpg"
+    JPEG = ".jpeg"
+    PNG = ".png"
+    GIF = ".gif"
+    BMP = ".bmp"
+    SVG = ".svg"
+    TIFF = ".tiff"
+    WEBP = ".webp"
     HTML = ".html"
     HTM = ".htm"
     XLS = ".xls"
@@ -115,6 +123,14 @@ class LlamaParseSupportedFileExtensions(str, enum.Enum):
         sxi: typing.Callable[[], T_Result],
         sti: typing.Callable[[], T_Result],
         epub: typing.Callable[[], T_Result],
+        jpg: typing.Callable[[], T_Result],
+        jpeg: typing.Callable[[], T_Result],
+        png: typing.Callable[[], T_Result],
+        gif: typing.Callable[[], T_Result],
+        bmp: typing.Callable[[], T_Result],
+        svg: typing.Callable[[], T_Result],
+        tiff: typing.Callable[[], T_Result],
+        webp: typing.Callable[[], T_Result],
         html: typing.Callable[[], T_Result],
         htm: typing.Callable[[], T_Result],
         xls: typing.Callable[[], T_Result],
@@ -217,6 +233,22 @@ class LlamaParseSupportedFileExtensions(str, enum.Enum):
             return sti()
         if self is LlamaParseSupportedFileExtensions.EPUB:
             return epub()
+        if self is LlamaParseSupportedFileExtensions.JPG:
+            return jpg()
+        if self is LlamaParseSupportedFileExtensions.JPEG:
+            return jpeg()
+        if self is LlamaParseSupportedFileExtensions.PNG:
+            return png()
+        if self is LlamaParseSupportedFileExtensions.GIF:
+            return gif()
+        if self is LlamaParseSupportedFileExtensions.BMP:
+            return bmp()
+        if self is LlamaParseSupportedFileExtensions.SVG:
+            return svg()
+        if self is LlamaParseSupportedFileExtensions.TIFF:
+            return tiff()
+        if self is LlamaParseSupportedFileExtensions.WEBP:
+            return webp()
         if self is LlamaParseSupportedFileExtensions.HTML:
             return html()
         if self is LlamaParseSupportedFileExtensions.HTM:

llama_cloud/types/llm_parameters.py

@@ -0,0 +1,39 @@
+# 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 LlmParameters(pydantic.BaseModel):
+    """
+    Base schema model for BaseComponent classes used in the platform.
+    Comes with special serialization logic for types used commonly in platform codebase.
+    """
+
+    model_name: typing.Optional[str] = pydantic.Field(description="The name of the model to use for retrieval.")
+    system_prompt: typing.Optional[str] = pydantic.Field(description="The system prompt to use for the model.")
+    temperature: typing.Optional[float] = pydantic.Field(description="The temperature value for the model.")
+    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_ingestion_status_response.py

@@ -4,6 +4,7 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
+from .ingestion_error_response import IngestionErrorResponse
 from .managed_ingestion_status import ManagedIngestionStatus
 
 try:
@@ -16,7 +17,12 @@ except ImportError:
 
 
 class ManagedIngestionStatusResponse(pydantic.BaseModel):
+    job_id: typing.Optional[str] = pydantic.Field(description="ID of the latest job.")
+    deployment_date: typing.Optional[dt.datetime] = pydantic.Field(description="Date of the deployment.")
     status: ManagedIngestionStatus = pydantic.Field(description="Status of the ingestion.")
+    error: typing.Optional[typing.List[IngestionErrorResponse]] = pydantic.Field(
+        description="List of errors that occurred during ingestion."
+    )
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/none_chunking_config.py

@@ -0,0 +1,29 @@
+# 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 NoneChunkingConfig(pydantic.BaseModel):
+    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/none_segmentation_config.py

@@ -0,0 +1,29 @@
+# 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 NoneSegmentationConfig(pydantic.BaseModel):
+    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/page_segmentation_config.py

@@ -0,0 +1,29 @@
+# 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 PageSegmentationConfig(pydantic.BaseModel):
+    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/{json_node_parser.py → page_splitter_node_parser.py}

@@ -14,15 +14,9 @@ except ImportError:
     import pydantic  # type: ignore
 
 
-class JsonNodeParser(pydantic.BaseModel):
+class PageSplitterNodeParser(pydantic.BaseModel):
     """
-    JSON node parser.
-
-    Splits a document into Nodes using custom JSON splitting logic.
-
-    Args:
-    include_metadata (bool): whether to include metadata in nodes
-    include_prev_next_rel (bool): whether to include prev/next relationships
+    Split text into pages.
     """
 
     include_metadata: typing.Optional[bool] = pydantic.Field(
@@ -30,6 +24,7 @@ class JsonNodeParser(pydantic.BaseModel):
     )
     include_prev_next_rel: typing.Optional[bool] = pydantic.Field(description="Include prev/next node relationships.")
     callback_manager: typing.Optional[typing.Dict[str, typing.Any]]
+    page_separator: typing.Optional[str] = pydantic.Field(description="Separator to split text into pages.")
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/parsing_job.py

@@ -18,6 +18,8 @@ except ImportError:
 class ParsingJob(pydantic.BaseModel):
     id: str
     status: StatusEnum
+    error_code: typing.Optional[str]
+    error_message: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}