llama-cloud 0.1.19__py3-none-any.whl → 0.1.21__py3-none-any.whl

llama_cloud/types/legacy_parse_job_config.py

@@ -0,0 +1,189 @@
+# 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 LegacyParseJobConfig(pydantic.BaseModel):
+    """
+    Configuration for llamaparse job
+    """
+
+    custom_metadata: typing.Optional[typing.Dict[str, typing.Any]]
+    resource_info: typing.Optional[typing.Dict[str, typing.Any]]
+    user_id: str = pydantic.Field(alias="userId", description="The user ID.")
+    file_name: str = pydantic.Field(alias="fileName", description="The file name.")
+    original_file_name: str = pydantic.Field(alias="originalFileName", description="The original file name.")
+    file_key: str = pydantic.Field(alias="fileKey", description="The file key.")
+    input_url: typing.Optional[str] = pydantic.Field(alias="inputUrl")
+    http_proxy: typing.Optional[str] = pydantic.Field(alias="httpProxy")
+    fast_mode: typing.Optional[bool] = pydantic.Field(alias="fastMode")
+    lang: str = pydantic.Field(description="The language.")
+    template: typing.Optional[str] = pydantic.Field(description="The parsing instruction.")
+    pipeline_id: typing.Optional[str] = pydantic.Field(alias="pipelineId")
+    output_bucket: typing.Optional[str] = pydantic.Field(alias="outputBucket")
+    file_id: typing.Optional[str] = pydantic.Field(alias="fileId")
+    full_file_path: typing.Optional[str] = pydantic.Field(alias="fullFilePath")
+    from_l_lama_cloud: typing.Optional[bool] = pydantic.Field(
+        alias="fromLLamaCloud", description="Whether the file is from LLama cloud."
+    )
+    skip_diagonal_text: typing.Optional[bool] = pydantic.Field(
+        alias="skipDiagonalText", description="Whether to skip diagonal text."
+    )
+    preserve_layout_alignment_across_pages: typing.Optional[bool] = pydantic.Field(
+        alias="preserveLayoutAlignmentAcrossPages", description="Whether to preserve layout alignment across pages."
+    )
+    invalidate_cache: bool = pydantic.Field(alias="invalidateCache", description="Whether to invalidate the cache.")
+    output_pdf_of_document: typing.Optional[bool] = pydantic.Field(alias="outputPDFOfDocument")
+    save_images: typing.Optional[bool] = pydantic.Field(alias="saveImages")
+    gpt_4_o: typing.Optional[bool] = pydantic.Field(alias="gpt4o", description="Whether to use GPT4o.")
+    open_aiapi_key: str = pydantic.Field(alias="openAIAPIKey", description="The OpenAI API key.")
+    do_not_unroll_columns: typing.Optional[bool] = pydantic.Field(
+        alias="doNotUnrollColumns", description="Whether to unroll columns."
+    )
+    spread_sheet_extract_sub_tables: typing.Optional[bool] = pydantic.Field(alias="spreadSheetExtractSubTables")
+    extract_layout: typing.Optional[bool] = pydantic.Field(alias="extractLayout")
+    html_make_all_elements_visible: typing.Optional[bool] = pydantic.Field(alias="htmlMakeAllElementsVisible")
+    html_remove_fixed_elements: typing.Optional[bool] = pydantic.Field(alias="htmlRemoveFixedElements")
+    html_remove_navigation_elements: typing.Optional[bool] = pydantic.Field(alias="htmlRemoveNavigationElements")
+    guess_xlsx_sheet_name: typing.Optional[bool] = pydantic.Field(
+        alias="guessXLSXSheetName", description="Whether to guess the XLSX sheet name when generation output xlsx."
+    )
+    do_not_cache: typing.Optional[bool] = pydantic.Field(alias="doNotCache", description="Whether to cache.")
+    page_separator: typing.Optional[str] = pydantic.Field(alias="pageSeparator")
+    bounding_box: typing.Optional[str] = pydantic.Field(alias="boundingBox")
+    bbox_top: typing.Optional[float] = pydantic.Field(alias="bboxTop")
+    bbox_right: typing.Optional[float] = pydantic.Field(alias="bboxRight")
+    bbox_bottom: typing.Optional[float] = pydantic.Field(alias="bboxBottom")
+    bbox_left: typing.Optional[float] = pydantic.Field(alias="bboxLeft")
+    disable_reconstruction: typing.Optional[bool] = pydantic.Field(alias="disableReconstruction")
+    target_pages: typing.Optional[str] = pydantic.Field(alias="targetPages")
+    multimodal_pipeline: typing.Optional[bool] = pydantic.Field(alias="multimodalPipeline")
+    multimodal_model: typing.Optional[str] = pydantic.Field(alias="multimodalModel")
+    model: typing.Optional[str]
+    vendor_api_key: typing.Optional[str] = pydantic.Field(alias="vendorAPIKey")
+    page_prefix: typing.Optional[str] = pydantic.Field(alias="pagePrefix")
+    page_suffix: typing.Optional[str] = pydantic.Field(alias="pageSuffix")
+    webhook_url: typing.Optional[str] = pydantic.Field(alias="webhookUrl")
+    preset: typing.Optional[str]
+    take_screenshot: typing.Optional[bool] = pydantic.Field(
+        alias="takeScreenshot", description="Force to capture an image of each pages"
+    )
+    is_formatting_instruction: typing.Optional[bool] = pydantic.Field(
+        alias="isFormattingInstruction", description="Allow the parsing instruction to also format the output."
+    )
+    premium_mode: typing.Optional[bool] = pydantic.Field(
+        alias="premiumMode", description="Whether to use premiumMode pipeline."
+    )
+    continuous_mode: typing.Optional[bool] = pydantic.Field(
+        alias="continuousMode", description="Whether to use continuousMode pipeline."
+    )
+    disable_ocr: typing.Optional[bool] = pydantic.Field(
+        alias="disableOcr",
+        description="Disable the OCR on the document. LlamaParse will only extract the copyable text from the document",
+    )
+    disable_image_extraction: typing.Optional[bool] = pydantic.Field(
+        alias="disableImageExtraction",
+        description="Disable the image extraction from the document. LlamaParse will not extract any image from the document.",
+    )
+    annotate_links: typing.Optional[bool] = pydantic.Field(
+        alias="annotateLinks",
+        description="Annotate links in markdown. LlamaParse will try to add links from document into the markdown.",
+    )
+    adaptive_long_table: typing.Optional[bool] = pydantic.Field(
+        alias="adaptiveLongTable",
+        description="Adaptive long table. LlamaParse will try to detect long table and adapt the output.",
+    )
+    compact_markdown_table: typing.Optional[bool] = pydantic.Field(
+        alias="compactMarkdownTable",
+        description="Compact markdown table. LlamaParse will compact the markdown table to not include too many spaces.",
+    )
+    input_s_3_path: typing.Optional[str] = pydantic.Field(alias="inputS3Path")
+    input_s_3_region: typing.Optional[str] = pydantic.Field(alias="inputS3Region")
+    output_s_3_path_prefix: typing.Optional[str] = pydantic.Field(alias="outputS3PathPrefix")
+    output_s_3_region: typing.Optional[str] = pydantic.Field(alias="outputS3Region")
+    project_id: typing.Optional[str] = pydantic.Field(alias="projectId")
+    azure_open_ai_deployment_name: typing.Optional[str] = pydantic.Field(alias="azureOpenAiDeploymentName")
+    azure_open_ai_endpoint: typing.Optional[str] = pydantic.Field(alias="azureOpenAiEndpoint")
+    azure_open_ai_api_version: typing.Optional[str] = pydantic.Field(alias="azureOpenAiApiVersion")
+    azure_open_ai_key: typing.Optional[str] = pydantic.Field(alias="azureOpenAiKey")
+    auto_mode: typing.Optional[bool] = pydantic.Field(alias="autoMode", description="Whether to use auto mode.")
+    auto_mode_trigger_on_table_in_page: typing.Optional[bool] = pydantic.Field(
+        alias="autoModeTriggerOnTableInPage", description="Whether to trigger on table in page."
+    )
+    auto_mode_trigger_on_image_in_page: typing.Optional[bool] = pydantic.Field(
+        alias="autoModeTriggerOnImageInPage", description="Whether to trigger on image in page."
+    )
+    auto_mode_trigger_on_regexp_in_page: typing.Optional[str] = pydantic.Field(alias="autoModeTriggerOnRegexpInPage")
+    auto_mode_trigger_on_text_in_page: typing.Optional[str] = pydantic.Field(alias="autoModeTriggerOnTextInPage")
+    auto_mode_configuration_json: typing.Optional[str] = pydantic.Field(alias="autoModeConfigurationJSON")
+    structured_output: typing.Optional[bool] = pydantic.Field(
+        alias="structuredOutput", description="Whether to use structured output."
+    )
+    structured_output_json_schema: typing.Optional[str] = pydantic.Field(alias="structuredOutputJSONSchema")
+    structured_output_json_schema_name: typing.Optional[str] = pydantic.Field(alias="structuredOutputJSONSchemaName")
+    max_pages: typing.Optional[int] = pydantic.Field(alias="maxPages")
+    extract_charts: typing.Optional[bool] = pydantic.Field(
+        alias="extractCharts", description="Extract charts from the document."
+    )
+    formatting_instruction: typing.Optional[str] = pydantic.Field(alias="formattingInstruction")
+    complemental_formatting_instruction: typing.Optional[str] = pydantic.Field(
+        alias="complementalFormattingInstruction"
+    )
+    content_guideline_instruction: typing.Optional[str] = pydantic.Field(alias="contentGuidelineInstruction")
+    job_timeout_in_seconds: typing.Optional[float] = pydantic.Field(alias="jobTimeoutInSeconds")
+    job_timeout_extra_time_per_page_in_seconds: typing.Optional[float] = pydantic.Field(
+        alias="jobTimeoutExtraTimePerPageInSeconds"
+    )
+    strict_mode_image_extraction: typing.Optional[bool] = pydantic.Field(
+        alias="strictModeImageExtraction",
+        description="If true, the job will fail when we are not able to extract an image from a document.",
+    )
+    strict_mode_image_ocr: typing.Optional[bool] = pydantic.Field(
+        alias="strictModeImageOCR",
+        description="If true, the job will fail when we are not able to OCR an image from a document.",
+    )
+    strict_mode_reconstruction: typing.Optional[bool] = pydantic.Field(
+        alias="strictModeReconstruction",
+        description="If true, the job will fail when we are not able to transform a page to Markdown in a document.",
+    )
+    strict_mode_buggy_font: typing.Optional[bool] = pydantic.Field(
+        alias="strictModeBuggyFont",
+        description="If true, the job will fail when we are not able to extract a glyph from the document due to buggy font.",
+    )
+    ignore_document_elements_for_layout_detection: typing.Optional[bool] = pydantic.Field(
+        alias="ignoreDocumentElementsForLayoutDetection",
+        description="If true, the job will ignore document element for layout detection, and instead just rely on a visual model, only apply to layout detection.",
+    )
+    output_tables_as_html: typing.Optional[bool] = pydantic.Field(
+        alias="outputTablesAsHTML",
+        description="If true, the job will output tables as HTML in the markdown output, useful for merged cells.",
+    )
+    parse_mode: typing.Optional[str] = pydantic.Field(alias="parseMode")
+    system_prompt: typing.Optional[str] = pydantic.Field(alias="systemPrompt")
+    system_prompt_append: typing.Optional[str] = pydantic.Field(alias="systemPromptAppend")
+    user_prompt: typing.Optional[str] = pydantic.Field(alias="userPrompt")
+
+    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
+        allow_population_by_field_name = True
+        json_encoders = {dt.datetime: serialize_datetime}

llama_cloud/types/llama_parse_parameters.py

@@ -79,6 +79,7 @@ class LlamaParseParameters(pydantic.BaseModel):
     auto_mode_trigger_on_text_in_page: typing.Optional[str]
     auto_mode_trigger_on_table_in_page: typing.Optional[bool]
     auto_mode_trigger_on_image_in_page: typing.Optional[bool]
+    auto_mode_configuration_json: typing.Optional[str]
     structured_output: typing.Optional[bool]
     structured_output_json_schema: typing.Optional[str]
     structured_output_json_schema_name: typing.Optional[str]

llama_cloud/types/load_files_job_config.py

@@ -0,0 +1,35 @@
+# 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 LoadFilesJobConfig(pydantic.BaseModel):
+    """
+    Schema for the parameters of a load files job.
+    """
+
+    file_ids: typing.Optional[typing.List[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/parse_job_config.py

@@ -0,0 +1,134 @@
+# 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 .fail_page_mode import FailPageMode
+from .parser_languages import ParserLanguages
+from .parsing_mode import ParsingMode
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class ParseJobConfig(pydantic.BaseModel):
+    """
+    Configuration for llamaparse job
+    """
+
+    custom_metadata: typing.Optional[typing.Dict[str, typing.Any]]
+    resource_info: typing.Optional[typing.Dict[str, typing.Any]]
+    languages: typing.Optional[typing.List[ParserLanguages]]
+    parsing_instruction: typing.Optional[str]
+    disable_ocr: typing.Optional[bool]
+    annotate_links: typing.Optional[bool]
+    adaptive_long_table: typing.Optional[bool]
+    compact_markdown_table: typing.Optional[bool]
+    disable_reconstruction: typing.Optional[bool]
+    disable_image_extraction: typing.Optional[bool]
+    invalidate_cache: typing.Optional[bool]
+    output_pdf_of_document: typing.Optional[bool]
+    do_not_cache: typing.Optional[bool]
+    fast_mode: typing.Optional[bool]
+    skip_diagonal_text: typing.Optional[bool]
+    preserve_layout_alignment_across_pages: typing.Optional[bool]
+    gpt_4_o_mode: typing.Optional[bool] = pydantic.Field(alias="gpt4o_mode")
+    gpt_4_o_api_key: typing.Optional[str] = pydantic.Field(alias="gpt4o_api_key")
+    do_not_unroll_columns: typing.Optional[bool]
+    extract_layout: typing.Optional[bool]
+    html_make_all_elements_visible: typing.Optional[bool]
+    html_remove_navigation_elements: typing.Optional[bool]
+    html_remove_fixed_elements: typing.Optional[bool]
+    guess_xlsx_sheet_name: typing.Optional[bool]
+    page_separator: typing.Optional[str]
+    bounding_box: typing.Optional[str]
+    bbox_top: typing.Optional[float]
+    bbox_right: typing.Optional[float]
+    bbox_bottom: typing.Optional[float]
+    bbox_left: typing.Optional[float]
+    target_pages: typing.Optional[str]
+    use_vendor_multimodal_model: typing.Optional[bool]
+    vendor_multimodal_model_name: typing.Optional[str]
+    model: typing.Optional[str]
+    vendor_multimodal_api_key: typing.Optional[str]
+    page_prefix: typing.Optional[str]
+    page_suffix: typing.Optional[str]
+    webhook_url: typing.Optional[str]
+    preset: typing.Optional[str]
+    take_screenshot: typing.Optional[bool]
+    is_formatting_instruction: typing.Optional[bool]
+    premium_mode: typing.Optional[bool]
+    continuous_mode: typing.Optional[bool]
+    input_s_3_path: typing.Optional[str] = pydantic.Field(alias="input_s3_path")
+    input_s_3_region: typing.Optional[str] = pydantic.Field(alias="input_s3_region")
+    output_s_3_path_prefix: typing.Optional[str] = pydantic.Field(alias="output_s3_path_prefix")
+    output_s_3_region: typing.Optional[str] = pydantic.Field(alias="output_s3_region")
+    project_id: typing.Optional[str]
+    azure_openai_deployment_name: typing.Optional[str]
+    azure_openai_endpoint: typing.Optional[str]
+    azure_openai_api_version: typing.Optional[str]
+    azure_openai_key: typing.Optional[str]
+    input_url: typing.Optional[str]
+    http_proxy: typing.Optional[str]
+    auto_mode: typing.Optional[bool]
+    auto_mode_trigger_on_regexp_in_page: typing.Optional[str]
+    auto_mode_trigger_on_text_in_page: typing.Optional[str]
+    auto_mode_trigger_on_table_in_page: typing.Optional[bool]
+    auto_mode_trigger_on_image_in_page: typing.Optional[bool]
+    auto_mode_configuration_json: typing.Optional[str]
+    structured_output: typing.Optional[bool]
+    structured_output_json_schema: typing.Optional[str]
+    structured_output_json_schema_name: typing.Optional[str]
+    max_pages: typing.Optional[int]
+    max_pages_enforced: typing.Optional[int]
+    extract_charts: typing.Optional[bool]
+    formatting_instruction: typing.Optional[str]
+    complemental_formatting_instruction: typing.Optional[str]
+    content_guideline_instruction: typing.Optional[str]
+    spreadsheet_extract_sub_tables: typing.Optional[bool]
+    job_timeout_in_seconds: typing.Optional[float]
+    job_timeout_extra_time_per_page_in_seconds: typing.Optional[float]
+    strict_mode_image_extraction: typing.Optional[bool]
+    strict_mode_image_ocr: typing.Optional[bool]
+    strict_mode_reconstruction: typing.Optional[bool]
+    strict_mode_buggy_font: typing.Optional[bool]
+    save_images: typing.Optional[bool]
+    ignore_document_elements_for_layout_detection: typing.Optional[bool]
+    output_tables_as_html: typing.Optional[bool] = pydantic.Field(alias="output_tables_as_HTML")
+    internal_is_screenshot_job: typing.Optional[bool]
+    parse_mode: typing.Optional[ParsingMode]
+    system_prompt: typing.Optional[str]
+    system_prompt_append: typing.Optional[str]
+    user_prompt: typing.Optional[str]
+    page_error_tolerance: typing.Optional[float]
+    replace_failed_page_mode: typing.Optional[FailPageMode]
+    replace_failed_page_with_error_message_prefix: typing.Optional[str]
+    replace_failed_page_with_error_message_suffix: typing.Optional[str]
+    markdown_table_multiline_header_separator: typing.Optional[str]
+    file_name: str = pydantic.Field(description="The file name.")
+    original_file_name: str = pydantic.Field(description="The original file name.")
+    file_key: str = pydantic.Field(description="The file key.")
+    lang: str = pydantic.Field(description="The language.")
+    output_bucket: typing.Optional[str] = pydantic.Field(alias="outputBucket")
+    file_id: typing.Optional[str]
+    pipeline_id: 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
+        allow_population_by_field_name = True
+        json_encoders = {dt.datetime: serialize_datetime}

llama_cloud/types/pipeline.py

@@ -4,12 +4,13 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
-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_configuration_hashes import PipelineConfigurationHashes
 from .pipeline_embedding_config import PipelineEmbeddingConfig
+from .pipeline_metadata_config import PipelineMetadataConfig
+from .pipeline_status import PipelineStatus
 from .pipeline_transform_config import PipelineTransformConfig
 from .pipeline_type import PipelineType
 from .preset_retrieval_params import PresetRetrievalParams
@@ -39,9 +40,6 @@ class Pipeline(pydantic.BaseModel):
     )
     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]
     transform_config: typing.Optional[PipelineTransformConfig] = pydantic.Field(
         description="Configuration for the transformation."
@@ -54,6 +52,8 @@ class Pipeline(pydantic.BaseModel):
     )
     llama_parse_parameters: typing.Optional[LlamaParseParameters]
     data_sink: typing.Optional[DataSink]
+    status: typing.Optional[PipelineStatus]
+    metadata_config: typing.Optional[PipelineMetadataConfig]
 
     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

@@ -4,12 +4,12 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
-from .configured_transformation_item import ConfiguredTransformationItem
 from .data_sink_create import DataSinkCreate
 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_metadata_config import PipelineMetadataConfig
 from .pipeline_type import PipelineType
 from .preset_retrieval_params import PresetRetrievalParams
 
@@ -31,7 +31,6 @@ class PipelineCreate(pydantic.BaseModel):
     transform_config: typing.Optional[PipelineCreateTransformConfig] = pydantic.Field(
         description="Configuration for the transformation."
     )
-    configured_transformations: typing.Optional[typing.List[ConfiguredTransformationItem]]
     data_sink_id: typing.Optional[str]
     embedding_model_config_id: typing.Optional[str]
     data_sink: typing.Optional[DataSinkCreate]
@@ -45,6 +44,7 @@ class PipelineCreate(pydantic.BaseModel):
         description="Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline."
     )
     status: typing.Optional[str]
+    metadata_config: typing.Optional[PipelineMetadataConfig]
     name: str
     pipeline_type: typing.Optional[PipelineType] = pydantic.Field(
         description="Type of pipeline. Either PLAYGROUND or MANAGED."

llama_cloud/types/pipeline_file_update_dispatcher_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 .delete_params import DeleteParams
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class PipelineFileUpdateDispatcherConfig(pydantic.BaseModel):
+    """
+    Schema for the parameters of a load files job.
+    """
+
+    pipeline_file_ids: typing.Optional[typing.List[str]]
+    should_delete: typing.Optional[bool]
+    delete_info: typing.Optional[DeleteParams]
+
+    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/{configured_transformation_item.py → pipeline_file_updater_config.py}

@@ -4,8 +4,7 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
-from .configurable_transformation_names import ConfigurableTransformationNames
-from .configured_transformation_item_component import ConfiguredTransformationItemComponent
+from .delete_params import DeleteParams
 
 try:
     import pydantic
@@ -16,20 +15,22 @@ except ImportError:
     import pydantic  # type: ignore
 
 
-class ConfiguredTransformationItem(pydantic.BaseModel):
+class PipelineFileUpdaterConfig(pydantic.BaseModel):
     """
-    Configured transformations for pipelines.
-
-    Similar to ConfigurableTransformation but includes a few
-    more fields that are useful to the platform.
+    Schema for the parameters of a load files job.
     """
 
-    id: typing.Optional[str]
-    configurable_transformation_type: ConfigurableTransformationNames = pydantic.Field(
-        description="Name for the type of transformation this is (e.g. SIMPLE_NODE_PARSER). Can also be an enum instance of llama_index.ingestion.transformations.ConfigurableTransformations. This will be converted to ConfigurableTransformationNames."
+    custom_metadata: typing.Optional[typing.Dict[str, typing.Any]]
+    resource_info: typing.Optional[typing.Dict[str, typing.Any]]
+    should_delete: typing.Optional[bool]
+    should_parse: typing.Optional[bool]
+    delete_info: typing.Optional[DeleteParams]
+    is_new_file: typing.Optional[bool] = pydantic.Field(description="Whether the file is new")
+    data_source_project_file_changed: typing.Optional[bool] = pydantic.Field(
+        description="Whether the data source project file has changed"
     )
-    component: ConfiguredTransformationItemComponent = pydantic.Field(
-        description="Component that implements the transformation"
+    should_migrate_pipeline_file_to_external_file_id: typing.Optional[bool] = pydantic.Field(
+        description="Whether to migrate the pipeline file to the external file id"
     )
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/pipeline_managed_ingestion_job_params.py

@@ -0,0 +1,37 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from .delete_params import DeleteParams
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class PipelineManagedIngestionJobParams(pydantic.BaseModel):
+    """
+    Schema for the parameters of a managed pipeline ingestion job.
+    """
+
+    should_delete: typing.Optional[bool]
+    delete_info: typing.Optional[DeleteParams]
+
+    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/pipeline_metadata_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
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class PipelineMetadataConfig(pydantic.BaseModel):
+    excluded_embed_metadata_keys: typing.Optional[typing.List[str]] = pydantic.Field(
+        description="List of metadata keys to exclude from embeddings"
+    )
+    excluded_llm_metadata_keys: typing.Optional[typing.List[str]] = pydantic.Field(
+        description="List of metadata keys to exclude from LLM during retrieval"
+    )
+
+    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/pipeline_status.py

@@ -0,0 +1,17 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import enum
+import typing
+
+T_Result = typing.TypeVar("T_Result")
+
+
+class PipelineStatus(str, enum.Enum):
+    CREATED = "CREATED"
+    DELETING = "DELETING"
+
+    def visit(self, created: typing.Callable[[], T_Result], deleting: typing.Callable[[], T_Result]) -> T_Result:
+        if self is PipelineStatus.CREATED:
+            return created()
+        if self is PipelineStatus.DELETING:
+            return deleting()

llama_cloud/types/prompt_conf.py

@@ -22,6 +22,7 @@ class PromptConf(pydantic.BaseModel):
     cite_sources_prompt: typing.Optional[typing.Dict[str, str]] = pydantic.Field(
         description="The prompt to use for citing sources."
     )
+    scratchpad_prompt: typing.Optional[str] = pydantic.Field(description="The prompt to use for scratchpad.")
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/supported_llm_model.py

@@ -5,7 +5,6 @@ import typing
 
 from ..core.datetime_utils import serialize_datetime
 from .llm_model_data import LlmModelData
-from .supported_llm_model_names import SupportedLlmModelNames
 
 try:
     import pydantic
@@ -21,7 +20,7 @@ class SupportedLlmModel(pydantic.BaseModel):
     Response Schema for a supported eval LLM model.
     """
 
-    name: SupportedLlmModelNames = pydantic.Field(description="The name of the supported LLM model.")
+    name: str = pydantic.Field(description="The name of the supported LLM model.")
     enabled: typing.Optional[bool] = pydantic.Field(
         description="Whether the LLM model is enabled for use in LlamaCloud."
     )

{llama_cloud-0.1.19.dist-info → llama_cloud-0.1.21.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: llama-cloud
-Version: 0.1.19
+Version: 0.1.21
 Summary: 
 License: MIT
 Author: Logan Markewich
@@ -27,3 +27,7 @@ To publish:
 - update the version in `pyproject.toml`
 - run `poetry publish --build` 
 
+Setup credentials:
+- run `poetry config pypi-token.pypi <my-token>`
+    - Get token form PyPi once logged in with credentials in [1Password](https://start.1password.com/open/i?a=32SA66TZ3JCRXOCMASLSDCT5TI&v=lhv7hvb5o46cwo257c3hviqkle&i=yvslwei7jtf6tgqamzcdantqi4&h=llamaindex.1password.com)
+