llama-cloud 0.0.16__py3-none-any.whl → 0.1.0__py3-none-any.whl

llama_cloud/types/hugging_face_inference_api_embedding.py

@@ -25,36 +25,20 @@ class HuggingFaceInferenceApiEmbedding(pydantic.BaseModel):
     - Uses the feature extraction task: https://huggingface.co/tasks/feature-extraction
     """
 
-    model_name: typing.Optional[str] = pydantic.Field(
-        description="Hugging Face model name. If None, the task will be used."
-    )
+    model_name: typing.Optional[str]
     embed_batch_size: typing.Optional[int] = pydantic.Field(description="The batch size for embedding calls.")
-    callback_manager: typing.Optional[typing.Dict[str, typing.Any]]
-    num_workers: typing.Optional[int] = pydantic.Field(
-        description="The number of workers to use for async embedding calls."
-    )
-    pooling: typing.Optional[Pooling] = pydantic.Field(
-        description="Pooling strategy. If None, the model's default pooling is used."
-    )
-    query_instruction: typing.Optional[str] = pydantic.Field(
-        description="Instruction to prepend during query embedding."
-    )
-    text_instruction: typing.Optional[str] = pydantic.Field(description="Instruction to prepend during text embedding.")
+    callback_manager: typing.Optional[typing.Any]
+    num_workers: typing.Optional[int]
+    pooling: typing.Optional[Pooling]
+    query_instruction: typing.Optional[str]
+    text_instruction: typing.Optional[str]
     token: typing.Optional[HuggingFaceInferenceApiEmbeddingToken] = pydantic.Field(
         description="Hugging Face token. Will default to the locally saved token. Pass token=False if you don’t want to send your token to the server."
     )
-    timeout: typing.Optional[float] = pydantic.Field(
-        description="The maximum number of seconds to wait for a response from the server. Loading a new model in Inference API can take up to several minutes. Defaults to None, meaning it will loop until the server is available."
-    )
-    headers: typing.Optional[typing.Dict[str, str]] = pydantic.Field(
-        description="Additional headers to send to the server. By default only the authorization and user-agent headers are sent. Values in this dictionary will override the default values."
-    )
-    cookies: typing.Optional[typing.Dict[str, str]] = pydantic.Field(
-        description="Additional cookies to send to the server."
-    )
-    task: typing.Optional[str] = pydantic.Field(
-        description="Optional task to pick Hugging Face's recommended model, used when model_name is left as default of None."
-    )
+    timeout: typing.Optional[float]
+    headers: typing.Optional[typing.Dict[str, typing.Optional[str]]]
+    cookies: typing.Optional[typing.Dict[str, typing.Optional[str]]]
+    task: typing.Optional[str]
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/input_message.py

@@ -20,12 +20,10 @@ 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.")
+    id: typing.Optional[str]
     role: MessageRole
     content: str
-    data: typing.Optional[typing.Dict[str, typing.Any]] = pydantic.Field(
-        description="Additional data to be stored with the message."
-    )
+    data: typing.Optional[typing.Dict[str, typing.Any]]
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/llama_parse_parameters.py

@@ -41,6 +41,7 @@ class LlamaParseParameters(pydantic.BaseModel):
     page_suffix: typing.Optional[str]
     webhook_url: typing.Optional[str]
     take_screenshot: typing.Optional[bool]
+    premium_mode: 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")
 

llama_cloud/types/llama_parse_supported_file_extensions.py

@@ -7,10 +7,6 @@ T_Result = typing.TypeVar("T_Result")
 
 
 class LlamaParseSupportedFileExtensions(str, enum.Enum):
-    """
-    An enumeration.
-    """
-
     PDF = ".pdf"
     DOC = ".doc"
     DOCX = ".docx"

llama_cloud/types/llm.py

@@ -33,16 +33,17 @@ class Llm(pydantic.BaseModel):
     Pydantic program mode to use for structured prediction.
     """
 
-    callback_manager: typing.Optional[typing.Dict[str, typing.Any]]
-    system_prompt: typing.Optional[str] = pydantic.Field(description="System prompt for LLM calls.")
-    output_parser: typing.Optional[typing.Dict[str, typing.Any]] = pydantic.Field(
-        description="Output parser to parse, validate, and correct errors programmatically."
+    callback_manager: typing.Optional[typing.Any]
+    system_prompt: typing.Optional[str]
+    messages_to_prompt: typing.Optional[str] = pydantic.Field(
+        description="Function to convert a list of messages to an LLM prompt."
     )
-    pydantic_program_mode: typing.Optional[PydanticProgramMode]
-    query_wrapper_prompt: typing.Optional[BasePromptTemplate] = pydantic.Field(
-        description="Query wrapper prompt for LLM calls."
+    completion_to_prompt: typing.Optional[str] = pydantic.Field(
+        description="Function to convert a completion to an LLM prompt."
     )
-    class_name: typing.Optional[str]
+    output_parser: typing.Optional[typing.Any]
+    pydantic_program_mode: typing.Optional[PydanticProgramMode]
+    query_wrapper_prompt: typing.Optional[BasePromptTemplate]
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/llm_parameters.py

@@ -16,16 +16,11 @@ except ImportError:
 
 
 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[SupportedLlmModelNames] = 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.")
+    system_prompt: typing.Optional[str]
+    temperature: typing.Optional[float]
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/local_eval.py

@@ -21,19 +21,17 @@ class LocalEval(pydantic.BaseModel):
     Output of an BaseEvaluator.
     """
 
-    query: typing.Optional[str] = pydantic.Field(description="Query string")
-    contexts: typing.Optional[typing.List[str]] = pydantic.Field(description="Context strings")
-    response: typing.Optional[str] = pydantic.Field(description="Response string")
-    passing: typing.Optional[bool] = pydantic.Field(description="Binary evaluation result (passing or not)")
-    feedback: typing.Optional[str] = pydantic.Field(description="Feedback or reasoning for the response")
-    score: typing.Optional[float] = pydantic.Field(description="Score for the response")
-    pairwise_source: typing.Optional[str] = pydantic.Field(
-        description="Used only for pairwise and specifies whether it is from original order of presented answers or flipped order"
-    )
+    query: typing.Optional[str]
+    contexts: typing.Optional[typing.List[str]]
+    response: typing.Optional[str]
+    passing: typing.Optional[bool]
+    feedback: typing.Optional[str]
+    score: typing.Optional[float]
+    pairwise_source: typing.Optional[str]
     invalid_result: typing.Optional[bool] = pydantic.Field(
         description="Whether the evaluation result is an invalid one."
     )
-    invalid_reason: typing.Optional[str] = pydantic.Field(description="Reason for invalid evaluation.")
+    invalid_reason: 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/local_eval_results.py

@@ -21,7 +21,7 @@ class LocalEvalResults(pydantic.BaseModel):
     """
 
     project_id: str = pydantic.Field(description="The ID of the project.")
-    eval_set_id: typing.Optional[str] = pydantic.Field(description="The ID of the local eval result set.")
+    eval_set_id: typing.Optional[str]
     app_name: str = pydantic.Field(description="The name of the app.")
     eval_name: str = pydantic.Field(description="The name of the eval.")
     result: LocalEval = pydantic.Field(description="The eval results.")

llama_cloud/types/managed_ingestion_status_response.py

@@ -17,12 +17,10 @@ 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.")
+    job_id: typing.Optional[str]
+    deployment_date: typing.Optional[dt.datetime]
     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."
-    )
+    error: typing.Optional[typing.List[IngestionErrorResponse]]
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/markdown_element_node_parser.py

@@ -28,14 +28,13 @@ class MarkdownElementNodeParser(pydantic.BaseModel):
         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]]
-    llm: typing.Optional[Llm] = pydantic.Field(description="LLM model to use for summarization.")
+    callback_manager: typing.Optional[typing.Any]
+    id_func: typing.Optional[str]
+    llm: typing.Optional[Llm]
     summary_query_str: typing.Optional[str] = pydantic.Field(description="Query string to use for summarization.")
     num_workers: typing.Optional[int] = pydantic.Field(description="Num of workers for async jobs.")
     show_progress: typing.Optional[bool] = pydantic.Field(description="Whether to show progress.")
-    nested_node_parser: typing.Optional[NodeParser] = pydantic.Field(
-        description="Other types of node parsers to handle some types of nodes."
-    )
+    nested_node_parser: typing.Optional[NodeParser]
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/markdown_node_parser.py

@@ -29,7 +29,8 @@ class MarkdownNodeParser(pydantic.BaseModel):
         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]]
+    callback_manager: typing.Optional[typing.Any]
+    id_func: typing.Optional[str]
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/message_annotation.py

@@ -15,13 +15,8 @@ except ImportError:
 
 
 class MessageAnnotation(pydantic.BaseModel):
-    """
-    Base schema model for BaseComponent classes used in the platform.
-    Comes with special serialization logic for types used commonly in platform codebase.
-    """
-
     type: str
-    data: typing.Optional[typing.Any]
+    data: str
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/metric_result.py

@@ -15,9 +15,9 @@ except ImportError:
 
 
 class MetricResult(pydantic.BaseModel):
-    passing: typing.Optional[bool] = pydantic.Field(description="Whether the metric passed or not.")
-    score: typing.Optional[float] = pydantic.Field(description="The score for the metric.")
-    feedback: typing.Optional[str] = pydantic.Field(description="The reasoning for the metric.")
+    passing: typing.Optional[bool]
+    score: typing.Optional[float]
+    feedback: 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/node_parser.py

@@ -23,7 +23,8 @@ class NodeParser(pydantic.BaseModel):
         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]]
+    callback_manager: typing.Optional[typing.Any]
+    id_func: typing.Optional[str]
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/node_relationship.py

@@ -0,0 +1,44 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import enum
+import typing
+
+T_Result = typing.TypeVar("T_Result")
+
+
+class NodeRelationship(str, enum.Enum):
+    """
+    Node relationships used in `BaseNode` class.
+
+    Attributes:
+    SOURCE: The node is the source document.
+    PREVIOUS: The node is the previous node in the document.
+    NEXT: The node is the next node in the document.
+    PARENT: The node is the parent node in the document.
+    CHILD: The node is a child node in the document.
+    """
+
+    ONE = "1"
+    TWO = "2"
+    THREE = "3"
+    FOUR = "4"
+    FIVE = "5"
+
+    def visit(
+        self,
+        one: typing.Callable[[], T_Result],
+        two: typing.Callable[[], T_Result],
+        three: typing.Callable[[], T_Result],
+        four: typing.Callable[[], T_Result],
+        five: typing.Callable[[], T_Result],
+    ) -> T_Result:
+        if self is NodeRelationship.ONE:
+            return one()
+        if self is NodeRelationship.TWO:
+            return two()
+        if self is NodeRelationship.THREE:
+            return three()
+        if self is NodeRelationship.FOUR:
+            return four()
+        if self is NodeRelationship.FIVE:
+            return five()

llama_cloud/types/object_type.py

@@ -7,10 +7,6 @@ T_Result = typing.TypeVar("T_Result")
 
 
 class ObjectType(str, enum.Enum):
-    """
-    An enumeration.
-    """
-
     ONE = "1"
     TWO = "2"
     THREE = "3"

llama_cloud/types/open_ai_embedding.py

@@ -39,27 +39,21 @@ class OpenAiEmbedding(pydantic.BaseModel):
 
     model_name: typing.Optional[str] = pydantic.Field(description="The name of the embedding model.")
     embed_batch_size: typing.Optional[int] = pydantic.Field(description="The batch size for embedding calls.")
-    callback_manager: typing.Optional[typing.Dict[str, typing.Any]]
-    num_workers: typing.Optional[int] = pydantic.Field(
-        description="The number of workers to use for async embedding calls."
-    )
+    callback_manager: typing.Optional[typing.Any]
+    num_workers: typing.Optional[int]
     additional_kwargs: typing.Optional[typing.Dict[str, typing.Any]] = pydantic.Field(
         description="Additional kwargs for the OpenAI API."
     )
     api_key: str = pydantic.Field(description="The OpenAI API key.")
-    api_base: typing.Optional[str] = pydantic.Field(description="The base URL for OpenAI API.")
-    api_version: typing.Optional[str] = pydantic.Field(description="The version for OpenAI API.")
+    api_base: typing.Optional[str]
+    api_version: typing.Optional[str]
     max_retries: typing.Optional[int] = pydantic.Field(description="Maximum number of retries.")
     timeout: typing.Optional[float] = pydantic.Field(description="Timeout for each request.")
-    default_headers: typing.Optional[typing.Dict[str, str]] = pydantic.Field(
-        description="The default headers for API requests."
-    )
+    default_headers: typing.Optional[typing.Dict[str, typing.Optional[str]]]
     reuse_client: typing.Optional[bool] = pydantic.Field(
         description="Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability."
     )
-    dimensions: typing.Optional[int] = pydantic.Field(
-        description="The number of dimensions on the output embedding vectors. Works only with v3 embedding models."
-    )
+    dimensions: typing.Optional[int]
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/organization.py

@@ -20,8 +20,8 @@ class Organization(pydantic.BaseModel):
     """
 
     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")
+    created_at: typing.Optional[dt.datetime]
+    updated_at: typing.Optional[dt.datetime]
     name: str = pydantic.Field(description="A name for the organization.")
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/page_splitter_node_parser.py

@@ -23,8 +23,9 @@ class PageSplitterNodeParser(pydantic.BaseModel):
         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]]
-    page_separator: typing.Optional[str] = pydantic.Field(description="Separator to split text into pages.")
+    callback_manager: typing.Optional[typing.Any]
+    id_func: typing.Optional[str]
+    page_separator: typing.Optional[str]
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/parsing_job_json_result.py

@@ -15,8 +15,8 @@ except ImportError:
 
 
 class ParsingJobJsonResult(pydantic.BaseModel):
-    pages: typing.Optional[typing.Any]
-    job_metadata: typing.Optional[typing.Any]
+    pages: typing.Any
+    job_metadata: typing.Any
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/parsing_job_markdown_result.py

@@ -16,7 +16,7 @@ except ImportError:
 
 class ParsingJobMarkdownResult(pydantic.BaseModel):
     markdown: str = pydantic.Field(description="The markdown result of the parsing job")
-    job_metadata: typing.Optional[typing.Any]
+    job_metadata: typing.Any
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/parsing_job_text_result.py

@@ -16,7 +16,7 @@ except ImportError:
 
 class ParsingJobTextResult(pydantic.BaseModel):
     text: str = pydantic.Field(description="The text result of the parsing job")
-    job_metadata: typing.Optional[typing.Any]
+    job_metadata: typing.Any
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/partition_names.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 PartitionNames(str, enum.Enum):
+    """
+    Enum for dataset partition names.
+    """
+
+    DATA_SOURCE_ID_PARTITION = "data_source_id_partition"
+    PIPELINE_ID_PARTITION = "pipeline_id_partition"
+    EVAL_DATASET_ID_PARTITION = "eval_dataset_id_partition"
+    FILE_ID_PARTITION = "file_id_partition"
+    PIPELINE_FILE_ID_PARTITION = "pipeline_file_id_partition"
+    FILE_PARSING_ID_PARTITION = "file_parsing_id_partition"
+    EXTRACTION_SCHEMA_ID_PARTITION = "extraction_schema_id_partition"
+
+    def visit(
+        self,
+        data_source_id_partition: typing.Callable[[], T_Result],
+        pipeline_id_partition: typing.Callable[[], T_Result],
+        eval_dataset_id_partition: typing.Callable[[], T_Result],
+        file_id_partition: typing.Callable[[], T_Result],
+        pipeline_file_id_partition: typing.Callable[[], T_Result],
+        file_parsing_id_partition: typing.Callable[[], T_Result],
+        extraction_schema_id_partition: typing.Callable[[], T_Result],
+    ) -> T_Result:
+        if self is PartitionNames.DATA_SOURCE_ID_PARTITION:
+            return data_source_id_partition()
+        if self is PartitionNames.PIPELINE_ID_PARTITION:
+            return pipeline_id_partition()
+        if self is PartitionNames.EVAL_DATASET_ID_PARTITION:
+            return eval_dataset_id_partition()
+        if self is PartitionNames.FILE_ID_PARTITION:
+            return file_id_partition()
+        if self is PartitionNames.PIPELINE_FILE_ID_PARTITION:
+            return pipeline_file_id_partition()
+        if self is PartitionNames.FILE_PARSING_ID_PARTITION:
+            return file_parsing_id_partition()
+        if self is PartitionNames.EXTRACTION_SCHEMA_ID_PARTITION:
+            return extraction_schema_id_partition()

llama_cloud/types/pipeline.py

@@ -29,25 +29,19 @@ class Pipeline(pydantic.BaseModel):
     """
 
     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")
+    created_at: typing.Optional[dt.datetime]
+    updated_at: typing.Optional[dt.datetime]
     name: str
     project_id: str
     pipeline_type: typing.Optional[PipelineType] = pydantic.Field(
         description="Type of pipeline. Either PLAYGROUND or MANAGED."
     )
-    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."
-    )
+    managed_pipeline_id: typing.Optional[str]
+    embedding_config: PipelineEmbeddingConfig
     configured_transformations: typing.Optional[typing.List[ConfiguredTransformationItem]] = pydantic.Field(
         description="Deprecated don't use it, List of configured transformations."
     )
-    config_hash: typing.Optional[PipelineConfigurationHashes] = pydantic.Field(
-        description="Hashes for the configuration of the pipeline."
-    )
+    config_hash: typing.Optional[PipelineConfigurationHashes]
     transform_config: typing.Optional[PipelineTransformConfig] = pydantic.Field(
         description="Configuration for the transformation."
     )
@@ -57,12 +51,8 @@ class Pipeline(pydantic.BaseModel):
     eval_parameters: typing.Optional[EvalExecutionParams] = pydantic.Field(
         description="Eval parameters for the pipeline."
     )
-    llama_parse_parameters: typing.Optional[LlamaParseParameters] = pydantic.Field(
-        description="Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline."
-    )
-    data_sink: typing.Optional[DataSink] = pydantic.Field(
-        description="The data sink for the pipeline. If None, the pipeline will use the fully managed data sink."
-    )
+    llama_parse_parameters: typing.Optional[LlamaParseParameters]
+    data_sink: typing.Optional[DataSink]
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/pipeline_configuration_hashes.py

@@ -19,9 +19,9 @@ class PipelineConfigurationHashes(pydantic.BaseModel):
     Hashes for the configuration of a pipeline.
     """
 
-    embedding_config_hash: typing.Optional[str] = pydantic.Field(description="Hash of the embedding config.")
-    parsing_config_hash: typing.Optional[str] = pydantic.Field(description="Hash of the llama parse parameters.")
-    transform_config_hash: typing.Optional[str] = pydantic.Field(description="Hash of the transform config.")
+    embedding_config_hash: typing.Optional[str]
+    parsing_config_hash: typing.Optional[str]
+    transform_config_hash: 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/pipeline_create.py

@@ -27,37 +27,25 @@ class PipelineCreate(pydantic.BaseModel):
     Schema for creating a pipeline.
     """
 
-    embedding_config: typing.Optional[PipelineCreateEmbeddingConfig] = pydantic.Field(
-        description="Configuration for the embedding model."
-    )
+    embedding_config: typing.Optional[PipelineCreateEmbeddingConfig]
     transform_config: typing.Optional[PipelineCreateTransformConfig] = pydantic.Field(
         description="Configuration for the transformation."
     )
-    configured_transformations: typing.Optional[typing.List[ConfiguredTransformationItem]] = pydantic.Field(
-        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."
-    )
-    data_sink: typing.Optional[DataSinkCreate] = pydantic.Field(
-        description="Data sink. When provided instead of data_sink_id, the data sink will be created."
-    )
+    configured_transformations: typing.Optional[typing.List[ConfiguredTransformationItem]]
+    data_sink_id: typing.Optional[str]
+    data_sink: typing.Optional[DataSinkCreate]
     preset_retrieval_parameters: typing.Optional[PresetRetrievalParams] = pydantic.Field(
         description="Preset retrieval parameters for the pipeline."
     )
     eval_parameters: typing.Optional[EvalExecutionParams] = pydantic.Field(
         description="Eval parameters for the pipeline."
     )
-    llama_parse_parameters: typing.Optional[LlamaParseParameters] = pydantic.Field(
-        description="Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline."
-    )
+    llama_parse_parameters: typing.Optional[LlamaParseParameters]
     name: str
     pipeline_type: typing.Optional[PipelineType] = pydantic.Field(
         description="Type of pipeline. Either PLAYGROUND or MANAGED."
     )
-    managed_pipeline_id: typing.Optional[str] = pydantic.Field(
-        description="The ID of the ManagedPipeline this playground pipeline is linked to."
-    )
+    managed_pipeline_id: 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/pipeline_create_embedding_config.py

@@ -15,8 +15,8 @@ from .open_ai_embedding_config import OpenAiEmbeddingConfig
 from .vertex_ai_embedding_config import VertexAiEmbeddingConfig
 
 
-class PipelineCreateEmbeddingConfig_OpenaiEmbedding(OpenAiEmbeddingConfig):
-    type: typing_extensions.Literal["OPENAI_EMBEDDING"]
+class PipelineCreateEmbeddingConfig_AzureEmbedding(AzureOpenAiEmbeddingConfig):
+    type: typing_extensions.Literal["AZURE_EMBEDDING"]
 
     class Config:
         frozen = True
@@ -24,8 +24,8 @@ class PipelineCreateEmbeddingConfig_OpenaiEmbedding(OpenAiEmbeddingConfig):
         allow_population_by_field_name = True
 
 
-class PipelineCreateEmbeddingConfig_AzureEmbedding(AzureOpenAiEmbeddingConfig):
-    type: typing_extensions.Literal["AZURE_EMBEDDING"]
+class PipelineCreateEmbeddingConfig_BedrockEmbedding(BedrockEmbeddingConfig):
+    type: typing_extensions.Literal["BEDROCK_EMBEDDING"]
 
     class Config:
         frozen = True
@@ -33,8 +33,8 @@ class PipelineCreateEmbeddingConfig_AzureEmbedding(AzureOpenAiEmbeddingConfig):
         allow_population_by_field_name = True
 
 
-class PipelineCreateEmbeddingConfig_HuggingfaceApiEmbedding(HuggingFaceInferenceApiEmbeddingConfig):
-    type: typing_extensions.Literal["HUGGINGFACE_API_EMBEDDING"]
+class PipelineCreateEmbeddingConfig_CohereEmbedding(CohereEmbeddingConfig):
+    type: typing_extensions.Literal["COHERE_EMBEDDING"]
 
     class Config:
         frozen = True
@@ -42,8 +42,8 @@ class PipelineCreateEmbeddingConfig_HuggingfaceApiEmbedding(HuggingFaceInference
         allow_population_by_field_name = True
 
 
-class PipelineCreateEmbeddingConfig_BedrockEmbedding(BedrockEmbeddingConfig):
-    type: typing_extensions.Literal["BEDROCK_EMBEDDING"]
+class PipelineCreateEmbeddingConfig_GeminiEmbedding(GeminiEmbeddingConfig):
+    type: typing_extensions.Literal["GEMINI_EMBEDDING"]
 
     class Config:
         frozen = True
@@ -51,8 +51,8 @@ class PipelineCreateEmbeddingConfig_BedrockEmbedding(BedrockEmbeddingConfig):
         allow_population_by_field_name = True
 
 
-class PipelineCreateEmbeddingConfig_GeminiEmbedding(GeminiEmbeddingConfig):
-    type: typing_extensions.Literal["GEMINI_EMBEDDING"]
+class PipelineCreateEmbeddingConfig_HuggingfaceApiEmbedding(HuggingFaceInferenceApiEmbeddingConfig):
+    type: typing_extensions.Literal["HUGGINGFACE_API_EMBEDDING"]
 
     class Config:
         frozen = True
@@ -60,8 +60,8 @@ class PipelineCreateEmbeddingConfig_GeminiEmbedding(GeminiEmbeddingConfig):
         allow_population_by_field_name = True
 
 
-class PipelineCreateEmbeddingConfig_CohereEmbedding(CohereEmbeddingConfig):
-    type: typing_extensions.Literal["COHERE_EMBEDDING"]
+class PipelineCreateEmbeddingConfig_OpenaiEmbedding(OpenAiEmbeddingConfig):
+    type: typing_extensions.Literal["OPENAI_EMBEDDING"]
 
     class Config:
         frozen = True
@@ -79,11 +79,11 @@ class PipelineCreateEmbeddingConfig_VertexaiEmbedding(VertexAiEmbeddingConfig):
 
 
 PipelineCreateEmbeddingConfig = typing.Union[
-    PipelineCreateEmbeddingConfig_OpenaiEmbedding,
     PipelineCreateEmbeddingConfig_AzureEmbedding,
-    PipelineCreateEmbeddingConfig_HuggingfaceApiEmbedding,
     PipelineCreateEmbeddingConfig_BedrockEmbedding,
-    PipelineCreateEmbeddingConfig_GeminiEmbedding,
     PipelineCreateEmbeddingConfig_CohereEmbedding,
+    PipelineCreateEmbeddingConfig_GeminiEmbedding,
+    PipelineCreateEmbeddingConfig_HuggingfaceApiEmbedding,
+    PipelineCreateEmbeddingConfig_OpenaiEmbedding,
     PipelineCreateEmbeddingConfig_VertexaiEmbedding,
 ]