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

llama_cloud/types/__init__.py

@@ -1,9 +1,27 @@
 # This file was auto-generated by Fern from our API Definition.
 
+from .advanced_mode_transform_config import AdvancedModeTransformConfig
+from .advanced_mode_transform_config_chunking_config import (
+    AdvancedModeTransformConfigChunkingConfig,
+    AdvancedModeTransformConfigChunkingConfig_Character,
+    AdvancedModeTransformConfigChunkingConfig_None,
+    AdvancedModeTransformConfigChunkingConfig_Semantic,
+    AdvancedModeTransformConfigChunkingConfig_Sentence,
+    AdvancedModeTransformConfigChunkingConfig_Token,
+)
+from .advanced_mode_transform_config_segmentation_config import (
+    AdvancedModeTransformConfigSegmentationConfig,
+    AdvancedModeTransformConfigSegmentationConfig_Element,
+    AdvancedModeTransformConfigSegmentationConfig_None,
+    AdvancedModeTransformConfigSegmentationConfig_Page,
+)
+from .auto_transform_config import AutoTransformConfig
 from .azure_open_ai_embedding import AzureOpenAiEmbedding
 from .base import Base
 from .base_prompt_template import BasePromptTemplate
 from .bedrock_embedding import BedrockEmbedding
+from .character_chunking_config import CharacterChunkingConfig
+from .character_splitter import CharacterSplitter
 from .chat_data import ChatData
 from .chat_message import ChatMessage
 from .cloud_az_storage_blob_data_source import CloudAzStorageBlobDataSource
@@ -13,6 +31,8 @@ from .cloud_confluence_data_source import CloudConfluenceDataSource
 from .cloud_document import CloudDocument
 from .cloud_document_create import CloudDocumentCreate
 from .cloud_jira_data_source import CloudJiraDataSource
+from .cloud_milvus_vector_store import CloudMilvusVectorStore
+from .cloud_mongo_db_atlas_vector_search import CloudMongoDbAtlasVectorSearch
 from .cloud_notion_page_data_source import CloudNotionPageDataSource
 from .cloud_one_drive_data_source import CloudOneDriveDataSource
 from .cloud_pinecone_vector_store import CloudPineconeVectorStore
@@ -31,6 +51,7 @@ from .configurable_transformation_names import ConfigurableTransformationNames
 from .configured_transformation_item import ConfiguredTransformationItem
 from .configured_transformation_item_component import ConfiguredTransformationItemComponent
 from .configured_transformation_item_component_one import ConfiguredTransformationItemComponentOne
+from .custom_claims import CustomClaims
 from .data_sink import DataSink
 from .data_sink_component import DataSinkComponent
 from .data_sink_component_one import DataSinkComponentOne
@@ -47,6 +68,11 @@ from .data_source_create_component_one import DataSourceCreateComponentOne
 from .data_source_create_custom_metadata_value import DataSourceCreateCustomMetadataValue
 from .data_source_custom_metadata_value import DataSourceCustomMetadataValue
 from .data_source_definition import DataSourceDefinition
+from .element_segmentation_config import ElementSegmentationConfig
+from .embedding_config import EmbeddingConfig
+from .embedding_config_component import EmbeddingConfigComponent
+from .embedding_config_component_one import EmbeddingConfigComponentOne
+from .embedding_config_type import EmbeddingConfigType
 from .eval_dataset import EvalDataset
 from .eval_dataset_job_params import EvalDatasetJobParams
 from .eval_dataset_job_record import EvalDatasetJobRecord
@@ -66,14 +92,15 @@ from .file_resource_info_value import FileResourceInfoValue
 from .filter_condition import FilterCondition
 from .filter_operator import FilterOperator
 from .gemini_embedding import GeminiEmbedding
-from .html_node_parser import HtmlNodeParser
 from .http_validation_error import HttpValidationError
 from .hugging_face_inference_api_embedding import HuggingFaceInferenceApiEmbedding
 from .hugging_face_inference_api_embedding_token import HuggingFaceInferenceApiEmbeddingToken
-from .json_node_parser import JsonNodeParser
+from .ingestion_error_response import IngestionErrorResponse
+from .job_name_mapping import JobNameMapping
 from .llama_parse_parameters import LlamaParseParameters
 from .llama_parse_supported_file_extensions import LlamaParseSupportedFileExtensions
 from .llm import Llm
+from .llm_parameters import LlmParameters
 from .local_eval import LocalEval
 from .local_eval_results import LocalEvalResults
 from .local_eval_sets import LocalEvalSets
@@ -88,10 +115,14 @@ from .metadata_filters import MetadataFilters
 from .metadata_filters_filters_item import MetadataFiltersFiltersItem
 from .metric_result import MetricResult
 from .node_parser import NodeParser
+from .none_chunking_config import NoneChunkingConfig
+from .none_segmentation_config import NoneSegmentationConfig
 from .object_type import ObjectType
 from .open_ai_embedding import OpenAiEmbedding
 from .organization import Organization
 from .organization_create import OrganizationCreate
+from .page_segmentation_config import PageSegmentationConfig
+from .page_splitter_node_parser import PageSplitterNodeParser
 from .parser_languages import ParserLanguages
 from .parsing_history_item import ParsingHistoryItem
 from .parsing_job import ParsingJob
@@ -101,6 +132,11 @@ from .parsing_job_text_result import ParsingJobTextResult
 from .parsing_usage import ParsingUsage
 from .pipeline import Pipeline
 from .pipeline_create import PipelineCreate
+from .pipeline_create_transform_config import (
+    PipelineCreateTransformConfig,
+    PipelineCreateTransformConfig_Advanced,
+    PipelineCreateTransformConfig_Auto,
+)
 from .pipeline_data_source import PipelineDataSource
 from .pipeline_data_source_component import PipelineDataSourceComponent
 from .pipeline_data_source_component_one import PipelineDataSourceComponentOne
@@ -124,16 +160,19 @@ from .pydantic_program_mode import PydanticProgramMode
 from .related_node_info import RelatedNodeInfo
 from .retrieval_mode import RetrievalMode
 from .retrieve_results import RetrieveResults
+from .semantic_chunking_config import SemanticChunkingConfig
+from .sentence_chunking_config import SentenceChunkingConfig
 from .sentence_splitter import SentenceSplitter
-from .simple_file_node_parser import SimpleFileNodeParser
 from .status_enum import StatusEnum
 from .supported_eval_llm_model import SupportedEvalLlmModel
 from .supported_eval_llm_model_names import SupportedEvalLlmModelNames
 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 .token_text_splitter import TokenTextSplitter
 from .transformation_category_names import TransformationCategoryNames
+from .user import User
 from .user_organization import UserOrganization
 from .user_organization_create import UserOrganizationCreate
 from .user_organization_delete import UserOrganizationDelete
@@ -141,10 +180,24 @@ from .validation_error import ValidationError
 from .validation_error_loc_item import ValidationErrorLocItem
 
 __all__ = [
+    "AdvancedModeTransformConfig",
+    "AdvancedModeTransformConfigChunkingConfig",
+    "AdvancedModeTransformConfigChunkingConfig_Character",
+    "AdvancedModeTransformConfigChunkingConfig_None",
+    "AdvancedModeTransformConfigChunkingConfig_Semantic",
+    "AdvancedModeTransformConfigChunkingConfig_Sentence",
+    "AdvancedModeTransformConfigChunkingConfig_Token",
+    "AdvancedModeTransformConfigSegmentationConfig",
+    "AdvancedModeTransformConfigSegmentationConfig_Element",
+    "AdvancedModeTransformConfigSegmentationConfig_None",
+    "AdvancedModeTransformConfigSegmentationConfig_Page",
+    "AutoTransformConfig",
     "AzureOpenAiEmbedding",
     "Base",
     "BasePromptTemplate",
     "BedrockEmbedding",
+    "CharacterChunkingConfig",
+    "CharacterSplitter",
     "ChatData",
     "ChatMessage",
     "CloudAzStorageBlobDataSource",
@@ -154,6 +207,8 @@ __all__ = [
     "CloudDocument",
     "CloudDocumentCreate",
     "CloudJiraDataSource",
+    "CloudMilvusVectorStore",
+    "CloudMongoDbAtlasVectorSearch",
     "CloudNotionPageDataSource",
     "CloudOneDriveDataSource",
     "CloudPineconeVectorStore",
@@ -172,6 +227,7 @@ __all__ = [
     "ConfiguredTransformationItem",
     "ConfiguredTransformationItemComponent",
     "ConfiguredTransformationItemComponentOne",
+    "CustomClaims",
     "DataSink",
     "DataSinkComponent",
     "DataSinkComponentOne",
@@ -188,6 +244,11 @@ __all__ = [
     "DataSourceCreateCustomMetadataValue",
     "DataSourceCustomMetadataValue",
     "DataSourceDefinition",
+    "ElementSegmentationConfig",
+    "EmbeddingConfig",
+    "EmbeddingConfigComponent",
+    "EmbeddingConfigComponentOne",
+    "EmbeddingConfigType",
     "EvalDataset",
     "EvalDatasetJobParams",
     "EvalDatasetJobRecord",
@@ -207,14 +268,15 @@ __all__ = [
     "FilterCondition",
     "FilterOperator",
     "GeminiEmbedding",
-    "HtmlNodeParser",
     "HttpValidationError",
     "HuggingFaceInferenceApiEmbedding",
     "HuggingFaceInferenceApiEmbeddingToken",
-    "JsonNodeParser",
+    "IngestionErrorResponse",
+    "JobNameMapping",
     "LlamaParseParameters",
     "LlamaParseSupportedFileExtensions",
     "Llm",
+    "LlmParameters",
     "LocalEval",
     "LocalEvalResults",
     "LocalEvalSets",
@@ -229,10 +291,14 @@ __all__ = [
     "MetadataFiltersFiltersItem",
     "MetricResult",
     "NodeParser",
+    "NoneChunkingConfig",
+    "NoneSegmentationConfig",
     "ObjectType",
     "OpenAiEmbedding",
     "Organization",
     "OrganizationCreate",
+    "PageSegmentationConfig",
+    "PageSplitterNodeParser",
     "ParserLanguages",
     "ParsingHistoryItem",
     "ParsingJob",
@@ -242,6 +308,9 @@ __all__ = [
     "ParsingUsage",
     "Pipeline",
     "PipelineCreate",
+    "PipelineCreateTransformConfig",
+    "PipelineCreateTransformConfig_Advanced",
+    "PipelineCreateTransformConfig_Auto",
     "PipelineDataSource",
     "PipelineDataSourceComponent",
     "PipelineDataSourceComponentOne",
@@ -265,16 +334,19 @@ __all__ = [
     "RelatedNodeInfo",
     "RetrievalMode",
     "RetrieveResults",
+    "SemanticChunkingConfig",
+    "SentenceChunkingConfig",
     "SentenceSplitter",
-    "SimpleFileNodeParser",
     "StatusEnum",
     "SupportedEvalLlmModel",
     "SupportedEvalLlmModelNames",
     "TextNode",
     "TextNodeRelationshipsValue",
     "TextNodeWithScore",
+    "TokenChunkingConfig",
     "TokenTextSplitter",
     "TransformationCategoryNames",
+    "User",
     "UserOrganization",
     "UserOrganizationCreate",
     "UserOrganizationDelete",

llama_cloud/types/advanced_mode_transform_config.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 .advanced_mode_transform_config_chunking_config import AdvancedModeTransformConfigChunkingConfig
+from .advanced_mode_transform_config_segmentation_config import AdvancedModeTransformConfigSegmentationConfig
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class AdvancedModeTransformConfig(pydantic.BaseModel):
+    segmentation_config: typing.Optional[AdvancedModeTransformConfigSegmentationConfig] = pydantic.Field(
+        description="Configuration for the segmentation."
+    )
+    chunking_config: typing.Optional[AdvancedModeTransformConfigChunkingConfig] = pydantic.Field(
+        description="Configuration for the chunking."
+    )
+
+    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/advanced_mode_transform_config_chunking_config.py

@@ -0,0 +1,67 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from __future__ import annotations
+
+import typing
+
+import typing_extensions
+
+from .character_chunking_config import CharacterChunkingConfig
+from .none_chunking_config import NoneChunkingConfig
+from .semantic_chunking_config import SemanticChunkingConfig
+from .sentence_chunking_config import SentenceChunkingConfig
+from .token_chunking_config import TokenChunkingConfig
+
+
+class AdvancedModeTransformConfigChunkingConfig_None(NoneChunkingConfig):
+    mode: typing_extensions.Literal["none"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class AdvancedModeTransformConfigChunkingConfig_Character(CharacterChunkingConfig):
+    mode: typing_extensions.Literal["character"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class AdvancedModeTransformConfigChunkingConfig_Token(TokenChunkingConfig):
+    mode: typing_extensions.Literal["token"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class AdvancedModeTransformConfigChunkingConfig_Sentence(SentenceChunkingConfig):
+    mode: typing_extensions.Literal["sentence"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class AdvancedModeTransformConfigChunkingConfig_Semantic(SemanticChunkingConfig):
+    mode: typing_extensions.Literal["semantic"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+AdvancedModeTransformConfigChunkingConfig = typing.Union[
+    AdvancedModeTransformConfigChunkingConfig_None,
+    AdvancedModeTransformConfigChunkingConfig_Character,
+    AdvancedModeTransformConfigChunkingConfig_Token,
+    AdvancedModeTransformConfigChunkingConfig_Sentence,
+    AdvancedModeTransformConfigChunkingConfig_Semantic,
+]

llama_cloud/types/advanced_mode_transform_config_segmentation_config.py

@@ -0,0 +1,45 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from __future__ import annotations
+
+import typing
+
+import typing_extensions
+
+from .element_segmentation_config import ElementSegmentationConfig
+from .none_segmentation_config import NoneSegmentationConfig
+from .page_segmentation_config import PageSegmentationConfig
+
+
+class AdvancedModeTransformConfigSegmentationConfig_None(NoneSegmentationConfig):
+    mode: typing_extensions.Literal["none"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class AdvancedModeTransformConfigSegmentationConfig_Page(PageSegmentationConfig):
+    mode: typing_extensions.Literal["page"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class AdvancedModeTransformConfigSegmentationConfig_Element(ElementSegmentationConfig):
+    mode: typing_extensions.Literal["element"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+AdvancedModeTransformConfigSegmentationConfig = typing.Union[
+    AdvancedModeTransformConfigSegmentationConfig_None,
+    AdvancedModeTransformConfigSegmentationConfig_Page,
+    AdvancedModeTransformConfigSegmentationConfig_Element,
+]

llama_cloud/types/auto_transform_config.py

@@ -0,0 +1,32 @@
+# 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 AutoTransformConfig(pydantic.BaseModel):
+    chunk_size: typing.Optional[int] = pydantic.Field(description="Chunk size for the transformation.")
+    chunk_overlap: typing.Optional[int] = pydantic.Field(description="Chunk overlap 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/character_chunking_config.py

@@ -0,0 +1,32 @@
+# 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 CharacterChunkingConfig(pydantic.BaseModel):
+    chunk_size: typing.Optional[int]
+    chunk_overlap: typing.Optional[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/{html_node_parser.py → character_splitter.py}

@@ -14,15 +14,9 @@ except ImportError:
     import pydantic  # type: ignore
 
 
-class HtmlNodeParser(pydantic.BaseModel):
+class CharacterSplitter(pydantic.BaseModel):
     """
-    HTML node parser.
-
-    Splits a document into Nodes using custom HTML splitting logic.
-
-    Args:
-    include_metadata (bool): whether to include metadata in nodes
-    include_prev_next_rel (bool): whether to include prev/next relationships
+    A splitter that splits text into characters.
     """
 
     include_metadata: typing.Optional[bool] = pydantic.Field(
@@ -30,7 +24,13 @@ class HtmlNodeParser(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]]
-    tags: typing.Optional[typing.List[str]] = pydantic.Field(description="HTML tags to extract text from.")
+    chunk_size: typing.Optional[int] = pydantic.Field(description="The token chunk size for each chunk.")
+    chunk_overlap: typing.Optional[int] = pydantic.Field(description="The token overlap of each chunk when splitting.")
+    separator: typing.Optional[str] = pydantic.Field(description="Default separator for splitting into words")
+    paragraph_separator: typing.Optional[str] = pydantic.Field(description="Separator between paragraphs.")
+    secondary_chunking_regex: typing.Optional[str] = pydantic.Field(
+        description="Backup regex for splitting into sentences."
+    )
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/chat_data.py

@@ -4,6 +4,7 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
+from .llm_parameters import LlmParameters
 from .preset_retrieval_params import PresetRetrievalParams
 
 try:
@@ -22,6 +23,7 @@ class ChatData(pydantic.BaseModel):
     """
 
     retrieval_parameters: PresetRetrievalParams
+    llm_parameters: typing.Optional[LlmParameters]
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/cloud_az_storage_blob_data_source.py

@@ -25,8 +25,17 @@ class CloudAzStorageBlobDataSource(pydantic.BaseModel):
     prefix: typing.Optional[str] = pydantic.Field(
         description="The prefix of the Azure Storage Blob objects to read from."
     )
-    account_name: str = pydantic.Field(description="The Azure Storage Blob account name to use for authentication.")
-    account_key: str = pydantic.Field(description="The Azure Storage Blob account key to use for authentication.")
+    account_name: typing.Optional[str] = pydantic.Field(
+        description="The Azure Storage Blob account name to use for authentication."
+    )
+    account_key: typing.Optional[str] = pydantic.Field(
+        description="The Azure Storage Blob account key to use for authentication."
+    )
+    tenant_id: typing.Optional[str] = pydantic.Field(description="The Azure AD tenant ID to use for authentication.")
+    client_id: typing.Optional[str] = pydantic.Field(description="The Azure AD client ID to use for authentication.")
+    client_secret: typing.Optional[str] = pydantic.Field(
+        description="The Azure AD client secret to use for authentication."
+    )
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/{simple_file_node_parser.py → cloud_milvus_vector_store.py}

@@ -14,23 +14,16 @@ except ImportError:
     import pydantic  # type: ignore
 
 
-class SimpleFileNodeParser(pydantic.BaseModel):
+class CloudMilvusVectorStore(pydantic.BaseModel):
     """
-    Simple file node parser.
-
-    Splits a document loaded from a file into Nodes using logic based on the file type
-    automatically detects the NodeParser to use based on file type
-
-    Args:
-    include_metadata (bool): whether to include metadata in nodes
-    include_prev_next_rel (bool): whether to include prev/next relationships
+    Cloud Milvus Vector Store.
     """
 
-    include_metadata: typing.Optional[bool] = pydantic.Field(
-        description="Whether or not to consider metadata when splitting."
-    )
-    include_prev_next_rel: typing.Optional[bool] = pydantic.Field(description="Include prev/next node relationships.")
-    callback_manager: typing.Optional[typing.Dict[str, typing.Any]]
+    supports_nested_metadata_filters: typing.Optional[bool]
+    uri: str
+    collection_name: typing.Optional[str]
+    token: typing.Optional[str]
+    embedding_dimension: typing.Optional[int]
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/cloud_mongo_db_atlas_vector_search.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 CloudMongoDbAtlasVectorSearch(pydantic.BaseModel):
+    """
+    Cloud MongoDB Atlas Vector Store.
+
+    This class is used to store the configuration for a MongoDB Atlas vector store,
+    so that it can be created and used in LlamaCloud.
+
+    Args:
+    mongodb_uri (str): URI for connecting to MongoDB Atlas
+    db_name (str): name of the MongoDB database
+    collection_name (str): name of the MongoDB collection
+    vector_index_name (str): name of the MongoDB Atlas vector index
+    fulltext_index_name (str): name of the MongoDB Atlas full-text index
+    """
+
+    supports_nested_metadata_filters: typing.Optional[bool]
+    mongodb_uri: str
+    db_name: str
+    collection_name: str
+    vector_index_name: typing.Optional[str]
+    fulltext_index_name: 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/configurable_data_sink_names.py

@@ -17,6 +17,8 @@ class ConfigurableDataSinkNames(str, enum.Enum):
     QDRANT = "QDRANT"
     WEAVIATE = "WEAVIATE"
     AZUREAI_SEARCH = "AZUREAI_SEARCH"
+    MONGODB_ATLAS = "MONGODB_ATLAS"
+    MILVUS = "MILVUS"
 
     def visit(
         self,
@@ -26,6 +28,8 @@ class ConfigurableDataSinkNames(str, enum.Enum):
         qdrant: typing.Callable[[], T_Result],
         weaviate: typing.Callable[[], T_Result],
         azureai_search: typing.Callable[[], T_Result],
+        mongodb_atlas: typing.Callable[[], T_Result],
+        milvus: typing.Callable[[], T_Result],
     ) -> T_Result:
         if self is ConfigurableDataSinkNames.CHROMA:
             return chroma()
@@ -39,3 +43,7 @@ class ConfigurableDataSinkNames(str, enum.Enum):
             return weaviate()
         if self is ConfigurableDataSinkNames.AZUREAI_SEARCH:
             return azureai_search()
+        if self is ConfigurableDataSinkNames.MONGODB_ATLAS:
+            return mongodb_atlas()
+        if self is ConfigurableDataSinkNames.MILVUS:
+            return milvus()