llama-cloud 0.0.13__py3-none-any.whl → 0.0.15__py3-none-any.whl

llama_cloud/types/data_source_create_component_one.py

@@ -3,6 +3,7 @@
 import typing
 
 from .cloud_az_storage_blob_data_source import CloudAzStorageBlobDataSource
+from .cloud_box_data_source import CloudBoxDataSource
 from .cloud_confluence_data_source import CloudConfluenceDataSource
 from .cloud_jira_data_source import CloudJiraDataSource
 from .cloud_notion_page_data_source import CloudNotionPageDataSource
@@ -20,4 +21,5 @@ DataSourceCreateComponentOne = typing.Union[
     CloudNotionPageDataSource,
     CloudConfluenceDataSource,
     CloudJiraDataSource,
+    CloudBoxDataSource,
 ]

llama_cloud/types/eval_execution_params.py

@@ -4,7 +4,7 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
-from .supported_eval_llm_model_names import SupportedEvalLlmModelNames
+from .supported_llm_model_names import SupportedLlmModelNames
 
 try:
     import pydantic
@@ -20,7 +20,7 @@ class EvalExecutionParams(pydantic.BaseModel):
     Schema for the params for an eval execution.
     """
 
-    llm_model: typing.Optional[SupportedEvalLlmModelNames] = pydantic.Field(
+    llm_model: typing.Optional[SupportedLlmModelNames] = pydantic.Field(
         description="The LLM model to use within eval execution."
     )
     qa_prompt_tmpl: typing.Optional[str] = pydantic.Field(

llama_cloud/types/eval_execution_params_override.py

@@ -4,7 +4,7 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
-from .supported_eval_llm_model_names import SupportedEvalLlmModelNames
+from .supported_llm_model_names import SupportedLlmModelNames
 
 try:
     import pydantic
@@ -20,7 +20,7 @@ class EvalExecutionParamsOverride(pydantic.BaseModel):
     Schema for the params override for an eval execution.
     """
 
-    llm_model: typing.Optional[SupportedEvalLlmModelNames] = pydantic.Field(
+    llm_model: typing.Optional[SupportedLlmModelNames] = pydantic.Field(
         description="The LLM model to use within eval execution."
     )
     qa_prompt_tmpl: typing.Optional[str] = pydantic.Field(

llama_cloud/types/filter_operator.py

@@ -23,6 +23,7 @@ class FilterOperator(str, enum.Enum):
     ALL = "all"
     TEXT_MATCH = "text_match"
     CONTAINS = "contains"
+    IS_EMPTY = "is_empty"
 
     def visit(
         self,
@@ -38,6 +39,7 @@ class FilterOperator(str, enum.Enum):
         all: typing.Callable[[], T_Result],
         text_match: typing.Callable[[], T_Result],
         contains: typing.Callable[[], T_Result],
+        is_empty: typing.Callable[[], T_Result],
     ) -> T_Result:
         if self is FilterOperator.EQUAL_TO:
             return equal_to()
@@ -63,3 +65,5 @@ class FilterOperator(str, enum.Enum):
             return text_match()
         if self is FilterOperator.CONTAINS:
             return contains()
+        if self is FilterOperator.IS_EMPTY:
+            return is_empty()

llama_cloud/types/gemini_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 .gemini_embedding import GeminiEmbedding
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class GeminiEmbeddingConfig(pydantic.BaseModel):
+    component: typing.Optional[GeminiEmbedding] = pydantic.Field(
+        description="Configuration for the Gemini 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/hugging_face_inference_api_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 .hugging_face_inference_api_embedding import HuggingFaceInferenceApiEmbedding
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class HuggingFaceInferenceApiEmbeddingConfig(pydantic.BaseModel):
+    component: typing.Optional[HuggingFaceInferenceApiEmbedding] = pydantic.Field(
+        description="Configuration for the HuggingFace Inference API 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/input_message.py

@@ -0,0 +1,42 @@
+# 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 .message_role import MessageRole
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class InputMessage(pydantic.BaseModel):
+    """
+    This is distinct from a ChatMessage because this schema is enforced by the AI Chat library used in the frontend
+    """
+
+    id: typing.Optional[str] = pydantic.Field(description="ID of the message, if any. Not necessarily a UUID.")
+    role: MessageRole
+    content: str
+    data: typing.Optional[typing.Dict[str, typing.Any]] = pydantic.Field(
+        description="Additional data to be stored with the message."
+    )
+    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/llama_parse_parameters.py

@@ -17,7 +17,7 @@ except ImportError:
 
 class LlamaParseParameters(pydantic.BaseModel):
     """
-    Settings that can be configured for how to use LlamaParse to parse files witin a LlamaCloud pipeline.
+    Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline.
     """
 
     languages: typing.Optional[typing.List[ParserLanguages]]
@@ -38,6 +38,9 @@ class LlamaParseParameters(pydantic.BaseModel):
     vendor_multimodal_api_key: typing.Optional[str]
     page_prefix: typing.Optional[str]
     page_suffix: typing.Optional[str]
+    take_screenshot: typing.Optional[bool]
+    s_3_input_path: typing.Optional[str] = pydantic.Field(alias="s3_input_path")
+    s_3_output_path_prefix: typing.Optional[str] = pydantic.Field(alias="s3_output_path_prefix")
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/{eval_llm_model_data.py → llm_model_data.py}

@@ -14,7 +14,7 @@ except ImportError:
     import pydantic  # type: ignore
 
 
-class EvalLlmModelData(pydantic.BaseModel):
+class LlmModelData(pydantic.BaseModel):
     """
     Schema for an eval LLM model.
     """

llama_cloud/types/llm_parameters.py

@@ -20,8 +20,8 @@ class LlmParameters(pydantic.BaseModel):
     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.")
+    model_name: typing.Optional[str] = pydantic.Field(description="The name of the model to use for LLM completions.")
+    system_prompt: typing.Optional[str] = pydantic.Field(description="The system prompt to use for the completion.")
     temperature: typing.Optional[float] = pydantic.Field(description="The temperature value for the model.")
     class_name: typing.Optional[str]
 

llama_cloud/types/{supported_eval_llm_model.py → message_annotation.py}

@@ -4,8 +4,6 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
-from .eval_llm_model_data import EvalLlmModelData
-from .supported_eval_llm_model_names import SupportedEvalLlmModelNames
 
 try:
     import pydantic
@@ -16,13 +14,15 @@ except ImportError:
     import pydantic  # type: ignore
 
 
-class SupportedEvalLlmModel(pydantic.BaseModel):
+class MessageAnnotation(pydantic.BaseModel):
     """
-    Response Schema for a supported eval LLM model.
+    Base schema model for BaseComponent classes used in the platform.
+    Comes with special serialization logic for types used commonly in platform codebase.
     """
 
-    name: SupportedEvalLlmModelNames = pydantic.Field(description="The name of the supported eval LLM model.")
-    details: EvalLlmModelData = pydantic.Field(description="The details of the supported eval LLM model.")
+    type: str
+    data: typing.Optional[typing.Any]
+    class_name: 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/metadata_filter.py

@@ -27,7 +27,7 @@ class MetadataFilter(pydantic.BaseModel):
     """
 
     key: str
-    value: MetadataFilterValue
+    value: typing.Optional[MetadataFilterValue]
     operator: typing.Optional[FilterOperator]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/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 .open_ai_embedding import OpenAiEmbedding
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class OpenAiEmbeddingConfig(pydantic.BaseModel):
+    component: typing.Optional[OpenAiEmbedding] = pydantic.Field(
+        description="Configuration for the 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/page_segmentation_config.py

@@ -15,6 +15,8 @@ except ImportError:
 
 
 class PageSegmentationConfig(pydantic.BaseModel):
+    page_separator: 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)

llama_cloud/types/pipeline.py

@@ -8,6 +8,8 @@ from .configured_transformation_item import ConfiguredTransformationItem
 from .data_sink import DataSink
 from .eval_execution_params import EvalExecutionParams
 from .llama_parse_parameters import LlamaParseParameters
+from .pipeline_embedding_config import PipelineEmbeddingConfig
+from .pipeline_transform_config import PipelineTransformConfig
 from .pipeline_type import PipelineType
 from .preset_retrieval_params import PresetRetrievalParams
 
@@ -25,7 +27,6 @@ class Pipeline(pydantic.BaseModel):
     Schema for a pipeline.
     """
 
-    configured_transformations: typing.List[ConfiguredTransformationItem]
     id: str = pydantic.Field(description="Unique identifier")
     created_at: typing.Optional[dt.datetime] = pydantic.Field(description="Creation datetime")
     updated_at: typing.Optional[dt.datetime] = pydantic.Field(description="Update datetime")
@@ -37,6 +38,15 @@ class Pipeline(pydantic.BaseModel):
     managed_pipeline_id: typing.Optional[str] = pydantic.Field(
         description="The ID of the ManagedPipeline this playground pipeline is linked to."
     )
+    embedding_config: typing.Optional[PipelineEmbeddingConfig] = pydantic.Field(
+        description="Configuration for the embedding model."
+    )
+    configured_transformations: typing.Optional[typing.List[ConfiguredTransformationItem]] = pydantic.Field(
+        description="Deprecated don't use it, List of configured transformations."
+    )
+    transform_config: typing.Optional[PipelineTransformConfig] = pydantic.Field(
+        description="Configuration for the transformation."
+    )
     preset_retrieval_parameters: typing.Optional[PresetRetrievalParams] = pydantic.Field(
         description="Preset retrieval parameters for the pipeline."
     )

llama_cloud/types/pipeline_create.py

@@ -6,9 +6,9 @@ import typing
 from ..core.datetime_utils import serialize_datetime
 from .configured_transformation_item import ConfiguredTransformationItem
 from .data_sink_create import DataSinkCreate
-from .embedding_config import EmbeddingConfig
 from .eval_execution_params import EvalExecutionParams
 from .llama_parse_parameters import LlamaParseParameters
+from .pipeline_create_embedding_config import PipelineCreateEmbeddingConfig
 from .pipeline_create_transform_config import PipelineCreateTransformConfig
 from .pipeline_type import PipelineType
 from .preset_retrieval_params import PresetRetrievalParams
@@ -27,14 +27,14 @@ class PipelineCreate(pydantic.BaseModel):
     Schema for creating a pipeline.
     """
 
-    embedding_config: typing.Optional[EmbeddingConfig] = pydantic.Field(
+    embedding_config: typing.Optional[PipelineCreateEmbeddingConfig] = pydantic.Field(
         description="Configuration for the embedding model."
     )
     transform_config: typing.Optional[PipelineCreateTransformConfig] = pydantic.Field(
         description="Configuration for the transformation."
     )
     configured_transformations: typing.Optional[typing.List[ConfiguredTransformationItem]] = pydantic.Field(
-        description="List of configured transformations."
+        description="Deprecated, use embedding_config or transform_config instead. configured transformations for the pipeline."
     )
     data_sink_id: typing.Optional[str] = pydantic.Field(
         description="Data sink ID. When provided instead of data_sink, the data sink will be looked up by ID."

llama_cloud/types/pipeline_create_embedding_config.py

@@ -0,0 +1,78 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from __future__ import annotations
+
+import typing
+
+import typing_extensions
+
+from .azure_open_ai_embedding_config import AzureOpenAiEmbeddingConfig
+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 .open_ai_embedding_config import OpenAiEmbeddingConfig
+
+
+class PipelineCreateEmbeddingConfig_OpenaiEmbedding(OpenAiEmbeddingConfig):
+    type: typing_extensions.Literal["OPENAI_EMBEDDING"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class PipelineCreateEmbeddingConfig_AzureEmbedding(AzureOpenAiEmbeddingConfig):
+    type: typing_extensions.Literal["AZURE_EMBEDDING"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class PipelineCreateEmbeddingConfig_HuggingfaceApiEmbedding(HuggingFaceInferenceApiEmbeddingConfig):
+    type: typing_extensions.Literal["HUGGINGFACE_API_EMBEDDING"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class PipelineCreateEmbeddingConfig_BedrockEmbedding(BedrockEmbeddingConfig):
+    type: typing_extensions.Literal["BEDROCK_EMBEDDING"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class PipelineCreateEmbeddingConfig_GeminiEmbedding(GeminiEmbeddingConfig):
+    type: typing_extensions.Literal["GEMINI_EMBEDDING"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class PipelineCreateEmbeddingConfig_CohereEmbedding(CohereEmbeddingConfig):
+    type: typing_extensions.Literal["COHERE_EMBEDDING"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+PipelineCreateEmbeddingConfig = typing.Union[
+    PipelineCreateEmbeddingConfig_OpenaiEmbedding,
+    PipelineCreateEmbeddingConfig_AzureEmbedding,
+    PipelineCreateEmbeddingConfig_HuggingfaceApiEmbedding,
+    PipelineCreateEmbeddingConfig_BedrockEmbedding,
+    PipelineCreateEmbeddingConfig_GeminiEmbedding,
+    PipelineCreateEmbeddingConfig_CohereEmbedding,
+]

llama_cloud/types/pipeline_data_source.py

@@ -34,6 +34,13 @@ class PipelineDataSource(pydantic.BaseModel):
     project_id: str
     data_source_id: str = pydantic.Field(description="The ID of the data source.")
     pipeline_id: str = pydantic.Field(description="The ID of the pipeline.")
+    last_synced_at: dt.datetime = pydantic.Field(description="The last time the data source was automatically synced.")
+    sync_interval: typing.Optional[float] = pydantic.Field(
+        description="The interval at which the data source should be synced."
+    )
+    sync_schedule_set_by: typing.Optional[str] = pydantic.Field(
+        description="The id of the user who set the sync schedule."
+    )
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/pipeline_data_source_component_one.py

@@ -3,6 +3,7 @@
 import typing
 
 from .cloud_az_storage_blob_data_source import CloudAzStorageBlobDataSource
+from .cloud_box_data_source import CloudBoxDataSource
 from .cloud_confluence_data_source import CloudConfluenceDataSource
 from .cloud_jira_data_source import CloudJiraDataSource
 from .cloud_notion_page_data_source import CloudNotionPageDataSource
@@ -20,4 +21,5 @@ PipelineDataSourceComponentOne = typing.Union[
     CloudNotionPageDataSource,
     CloudConfluenceDataSource,
     CloudJiraDataSource,
+    CloudBoxDataSource,
 ]

llama_cloud/types/pipeline_data_source_create.py

@@ -20,6 +20,9 @@ class PipelineDataSourceCreate(pydantic.BaseModel):
     """
 
     data_source_id: str = pydantic.Field(description="The ID of the data source.")
+    sync_interval: typing.Optional[float] = pydantic.Field(
+        description="The interval at which the data source should be synced."
+    )
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/pipeline_embedding_config.py

@@ -0,0 +1,78 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from __future__ import annotations
+
+import typing
+
+import typing_extensions
+
+from .azure_open_ai_embedding_config import AzureOpenAiEmbeddingConfig
+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 .open_ai_embedding_config import OpenAiEmbeddingConfig
+
+
+class PipelineEmbeddingConfig_OpenaiEmbedding(OpenAiEmbeddingConfig):
+    type: typing_extensions.Literal["OPENAI_EMBEDDING"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class PipelineEmbeddingConfig_AzureEmbedding(AzureOpenAiEmbeddingConfig):
+    type: typing_extensions.Literal["AZURE_EMBEDDING"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class PipelineEmbeddingConfig_HuggingfaceApiEmbedding(HuggingFaceInferenceApiEmbeddingConfig):
+    type: typing_extensions.Literal["HUGGINGFACE_API_EMBEDDING"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class PipelineEmbeddingConfig_BedrockEmbedding(BedrockEmbeddingConfig):
+    type: typing_extensions.Literal["BEDROCK_EMBEDDING"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class PipelineEmbeddingConfig_GeminiEmbedding(GeminiEmbeddingConfig):
+    type: typing_extensions.Literal["GEMINI_EMBEDDING"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class PipelineEmbeddingConfig_CohereEmbedding(CohereEmbeddingConfig):
+    type: typing_extensions.Literal["COHERE_EMBEDDING"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+PipelineEmbeddingConfig = typing.Union[
+    PipelineEmbeddingConfig_OpenaiEmbedding,
+    PipelineEmbeddingConfig_AzureEmbedding,
+    PipelineEmbeddingConfig_HuggingfaceApiEmbedding,
+    PipelineEmbeddingConfig_BedrockEmbedding,
+    PipelineEmbeddingConfig_GeminiEmbedding,
+    PipelineEmbeddingConfig_CohereEmbedding,
+]

llama_cloud/types/pipeline_transform_config.py

@@ -0,0 +1,31 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from __future__ import annotations
+
+import typing
+
+import typing_extensions
+
+from .advanced_mode_transform_config import AdvancedModeTransformConfig
+from .auto_transform_config import AutoTransformConfig
+
+
+class PipelineTransformConfig_Auto(AutoTransformConfig):
+    mode: typing_extensions.Literal["auto"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class PipelineTransformConfig_Advanced(AdvancedModeTransformConfig):
+    mode: typing_extensions.Literal["advanced"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+PipelineTransformConfig = typing.Union[PipelineTransformConfig_Auto, PipelineTransformConfig_Advanced]

llama_cloud/types/playground_session.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
+from .chat_message import ChatMessage
+from .llm_parameters import LlmParameters
+from .preset_retrieval_params import PresetRetrievalParams
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class PlaygroundSession(pydantic.BaseModel):
+    """
+    A playground session for a user.
+    """
+
+    id: str = pydantic.Field(description="Unique identifier")
+    created_at: typing.Optional[dt.datetime] = pydantic.Field(description="Creation datetime")
+    updated_at: typing.Optional[dt.datetime] = pydantic.Field(description="Update datetime")
+    pipeline_id: str
+    user_id: str
+    llm_params_id: str
+    llm_params: typing.Optional[LlmParameters] = pydantic.Field(description="LLM parameters last used in this session.")
+    retrieval_params_id: str
+    retrieval_params: typing.Optional[PresetRetrievalParams] = pydantic.Field(
+        description="Preset retrieval parameters last used in this session."
+    )
+    chat_messages: typing.Optional[typing.List[ChatMessage]] = pydantic.Field(
+        description="Chat message history for this session."
+    )
+
+    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}