llama-cloud 0.0.6__py3-none-any.whl → 0.0.8__py3-none-any.whl

llama_cloud/types/{cloud_google_drive_data_source.py → cloud_notion_page_data_source.py}

@@ -14,15 +14,14 @@ except ImportError:
     import pydantic  # type: ignore
 
 
-class CloudGoogleDriveDataSource(pydantic.BaseModel):
+class CloudNotionPageDataSource(pydantic.BaseModel):
     """
     Base component object to capture class names.
     """
 
-    folder_id: str = pydantic.Field(description="The ID of the Google Drive folder to read from.")
-    service_account_key: typing.Dict[str, typing.Any] = pydantic.Field(
-        description="The service account key JSON to use for authentication."
-    )
+    integration_token: str = pydantic.Field(description="The integration token to use for authentication.")
+    database_ids: typing.Optional[str] = pydantic.Field(description="The Notion Database Id to read content from.")
+    page_ids: typing.Optional[str] = pydantic.Field(description="The Page ID's of the Notion to read from.")
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/cloud_slack_data_source.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
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class CloudSlackDataSource(pydantic.BaseModel):
+    """
+    Base component object to capture class names.
+    """
+
+    slack_token: str = pydantic.Field(description="Slack Bot Token.")
+    channel_ids: typing.Optional[str] = pydantic.Field(description="Slack Channel.")
+    latest_date: typing.Optional[str] = pydantic.Field(description="Latest date.")
+    earliest_date: typing.Optional[str] = pydantic.Field(description="Earliest date.")
+    earliest_date_timestamp: typing.Optional[float] = pydantic.Field(description="Earliest date timestamp.")
+    latest_date_timestamp: typing.Optional[float] = pydantic.Field(description="Latest date timestamp.")
+    channel_patterns: typing.Optional[str] = pydantic.Field(description="Slack Channel name pattern.")
+    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

@@ -16,6 +16,7 @@ class ConfigurableDataSinkNames(str, enum.Enum):
     POSTGRES = "POSTGRES"
     QDRANT = "QDRANT"
     WEAVIATE = "WEAVIATE"
+    AZUREAI_SEARCH = "AZUREAI_SEARCH"
 
     def visit(
         self,
@@ -24,6 +25,7 @@ class ConfigurableDataSinkNames(str, enum.Enum):
         postgres: typing.Callable[[], T_Result],
         qdrant: typing.Callable[[], T_Result],
         weaviate: typing.Callable[[], T_Result],
+        azureai_search: typing.Callable[[], T_Result],
     ) -> T_Result:
         if self is ConfigurableDataSinkNames.CHROMA:
             return chroma()
@@ -35,3 +37,5 @@ class ConfigurableDataSinkNames(str, enum.Enum):
             return qdrant()
         if self is ConfigurableDataSinkNames.WEAVIATE:
             return weaviate()
+        if self is ConfigurableDataSinkNames.AZUREAI_SEARCH:
+            return azureai_search()

llama_cloud/types/configurable_data_source_names.py

@@ -13,29 +13,29 @@ class ConfigurableDataSourceNames(str, enum.Enum):
 
     S_3 = "S3"
     AZURE_STORAGE_BLOB = "AZURE_STORAGE_BLOB"
-    GCS = "GCS"
-    GOOGLE_DRIVE = "GOOGLE_DRIVE"
     MICROSOFT_ONEDRIVE = "MICROSOFT_ONEDRIVE"
     MICROSOFT_SHAREPOINT = "MICROSOFT_SHAREPOINT"
+    SLACK = "SLACK"
+    NOTION_PAGE = "NOTION_PAGE"
 
     def visit(
         self,
         s_3: typing.Callable[[], T_Result],
         azure_storage_blob: typing.Callable[[], T_Result],
-        gcs: typing.Callable[[], T_Result],
-        google_drive: typing.Callable[[], T_Result],
         microsoft_onedrive: typing.Callable[[], T_Result],
         microsoft_sharepoint: typing.Callable[[], T_Result],
+        slack: typing.Callable[[], T_Result],
+        notion_page: typing.Callable[[], T_Result],
     ) -> T_Result:
         if self is ConfigurableDataSourceNames.S_3:
             return s_3()
         if self is ConfigurableDataSourceNames.AZURE_STORAGE_BLOB:
             return azure_storage_blob()
-        if self is ConfigurableDataSourceNames.GCS:
-            return gcs()
-        if self is ConfigurableDataSourceNames.GOOGLE_DRIVE:
-            return google_drive()
         if self is ConfigurableDataSourceNames.MICROSOFT_ONEDRIVE:
             return microsoft_onedrive()
         if self is ConfigurableDataSourceNames.MICROSOFT_SHAREPOINT:
             return microsoft_sharepoint()
+        if self is ConfigurableDataSourceNames.SLACK:
+            return slack()
+        if self is ConfigurableDataSourceNames.NOTION_PAGE:
+            return notion_page()

llama_cloud/types/data_sink_component_one.py

@@ -2,6 +2,7 @@
 
 import typing
 
+from .cloud_azure_ai_search_vector_store import CloudAzureAiSearchVectorStore
 from .cloud_chroma_vector_store import CloudChromaVectorStore
 from .cloud_pinecone_vector_store import CloudPineconeVectorStore
 from .cloud_postgres_vector_store import CloudPostgresVectorStore
@@ -14,4 +15,5 @@ DataSinkComponentOne = typing.Union[
     CloudPostgresVectorStore,
     CloudQdrantVectorStore,
     CloudWeaviateVectorStore,
+    CloudAzureAiSearchVectorStore,
 ]

llama_cloud/types/data_sink_create_component_one.py

@@ -2,6 +2,7 @@
 
 import typing
 
+from .cloud_azure_ai_search_vector_store import CloudAzureAiSearchVectorStore
 from .cloud_chroma_vector_store import CloudChromaVectorStore
 from .cloud_pinecone_vector_store import CloudPineconeVectorStore
 from .cloud_postgres_vector_store import CloudPostgresVectorStore
@@ -14,4 +15,5 @@ DataSinkCreateComponentOne = typing.Union[
     CloudPostgresVectorStore,
     CloudQdrantVectorStore,
     CloudWeaviateVectorStore,
+    CloudAzureAiSearchVectorStore,
 ]

llama_cloud/types/data_source_component_one.py

@@ -3,17 +3,17 @@
 import typing
 
 from .cloud_az_storage_blob_data_source import CloudAzStorageBlobDataSource
-from .cloud_gcs_data_source import CloudGcsDataSource
-from .cloud_google_drive_data_source import CloudGoogleDriveDataSource
+from .cloud_notion_page_data_source import CloudNotionPageDataSource
 from .cloud_one_drive_data_source import CloudOneDriveDataSource
 from .cloud_s_3_data_source import CloudS3DataSource
 from .cloud_sharepoint_data_source import CloudSharepointDataSource
+from .cloud_slack_data_source import CloudSlackDataSource
 
 DataSourceComponentOne = typing.Union[
     CloudS3DataSource,
     CloudAzStorageBlobDataSource,
-    CloudGcsDataSource,
-    CloudGoogleDriveDataSource,
     CloudOneDriveDataSource,
     CloudSharepointDataSource,
+    CloudSlackDataSource,
+    CloudNotionPageDataSource,
 ]

llama_cloud/types/data_source_create_component_one.py

@@ -3,17 +3,17 @@
 import typing
 
 from .cloud_az_storage_blob_data_source import CloudAzStorageBlobDataSource
-from .cloud_gcs_data_source import CloudGcsDataSource
-from .cloud_google_drive_data_source import CloudGoogleDriveDataSource
+from .cloud_notion_page_data_source import CloudNotionPageDataSource
 from .cloud_one_drive_data_source import CloudOneDriveDataSource
 from .cloud_s_3_data_source import CloudS3DataSource
 from .cloud_sharepoint_data_source import CloudSharepointDataSource
+from .cloud_slack_data_source import CloudSlackDataSource
 
 DataSourceCreateComponentOne = typing.Union[
     CloudS3DataSource,
     CloudAzStorageBlobDataSource,
-    CloudGcsDataSource,
-    CloudGoogleDriveDataSource,
     CloudOneDriveDataSource,
     CloudSharepointDataSource,
+    CloudSlackDataSource,
+    CloudNotionPageDataSource,
 ]

llama_cloud/types/eval_dataset_job_record.py

@@ -38,13 +38,13 @@ class EvalDatasetJobRecord(pydantic.BaseModel):
         description="The correlation ID for this job. Used for tracking the job across services."
     )
     parent_job_execution_id: typing.Optional[str] = pydantic.Field(description="The ID of the parent job execution.")
+    created_at: typing.Optional[dt.datetime] = pydantic.Field(description="Creation datetime")
     id: typing.Optional[str] = pydantic.Field(description="Unique identifier")
     status: StatusEnum
     error_message: typing.Optional[str]
     attempts: typing.Optional[int] = pydantic.Field(description="The number of times this job has been attempted")
     started_at: typing.Optional[dt.datetime]
     ended_at: typing.Optional[dt.datetime]
-    created_at: typing.Optional[dt.datetime] = pydantic.Field(description="Creation datetime")
     updated_at: typing.Optional[dt.datetime] = pydantic.Field(description="Update datetime")
     data: typing.Optional[Base] = pydantic.Field(description="Additional metadata for the job execution.")
 

llama_cloud/types/extraction_result.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 .extraction_result_data_value import ExtractionResultDataValue
+from .file import File
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class ExtractionResult(pydantic.BaseModel):
+    """
+    Schema for an extraction result.
+    """
+
+    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")
+    schema_id: str = pydantic.Field(description="The id of the schema")
+    data: typing.Dict[str, ExtractionResultDataValue] = pydantic.Field(description="The data extracted from the file")
+    file: File = pydantic.Field(description="The file that the extract was extracted from")
+
+    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/extraction_result_data_value.py

@@ -0,0 +1,5 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+ExtractionResultDataValue = typing.Union[typing.Dict[str, typing.Any], typing.List[typing.Any], str, int, float, bool]

llama_cloud/types/extraction_schema.py

@@ -0,0 +1,44 @@
+# 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 .extraction_schema_data_schema_value import ExtractionSchemaDataSchemaValue
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class ExtractionSchema(pydantic.BaseModel):
+    """
+    Schema for extraction schema.
+    """
+
+    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")
+    name: str = pydantic.Field(description="The name of the extraction schema")
+    project_id: str = pydantic.Field(description="The ID of the project that the extraction schema belongs to")
+    data_schema: typing.Dict[str, ExtractionSchemaDataSchemaValue] = pydantic.Field(
+        description="The schema of the data"
+    )
+    openai_api_key: str = pydantic.Field(description="The API key for the OpenAI API")
+
+    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/extraction_schema_data_schema_value.py

@@ -0,0 +1,7 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+ExtractionSchemaDataSchemaValue = typing.Union[
+    typing.Dict[str, typing.Any], typing.List[typing.Any], str, int, float, bool
+]

llama_cloud/types/llama_parse_parameters.py

@@ -31,6 +31,8 @@ class LlamaParseParameters(pydantic.BaseModel):
     gpt_4_o_api_key: typing.Optional[str] = pydantic.Field(alias="gpt4o_api_key")
     do_not_unroll_columns: typing.Optional[bool]
     page_separator: typing.Optional[str]
+    bounding_box: typing.Optional[str]
+    target_pages: 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/llama_parse_supported_file_extensions.py

@@ -47,6 +47,37 @@ class LlamaParseSupportedFileExtensions(str, enum.Enum):
     EPUB = ".epub"
     HTML = ".html"
     HTM = ".htm"
+    XLS = ".xls"
+    XLSX = ".xlsx"
+    XLSM = ".xlsm"
+    XLSB = ".xlsb"
+    XLW = ".xlw"
+    CSV = ".csv"
+    DIF = ".dif"
+    SYLK = ".sylk"
+    SLK = ".slk"
+    PRN = ".prn"
+    NUMBERS = ".numbers"
+    ET = ".et"
+    ODS = ".ods"
+    FODS = ".fods"
+    UOS_1 = ".uos1"
+    UOS_2 = ".uos2"
+    DBF = ".dbf"
+    WK_1 = ".wk1"
+    WK_2 = ".wk2"
+    WK_3 = ".wk3"
+    WK_4 = ".wk4"
+    WKS = ".wks"
+    WQ_1 = ".wq1"
+    WQ_2 = ".wq2"
+    WB_1 = ".wb1"
+    WB_2 = ".wb2"
+    WB_3 = ".wb3"
+    QPW = ".qpw"
+    XLR = ".xlr"
+    ETH = ".eth"
+    TSV = ".tsv"
 
     def visit(
         self,
@@ -86,6 +117,37 @@ class LlamaParseSupportedFileExtensions(str, enum.Enum):
         epub: typing.Callable[[], T_Result],
         html: typing.Callable[[], T_Result],
         htm: typing.Callable[[], T_Result],
+        xls: typing.Callable[[], T_Result],
+        xlsx: typing.Callable[[], T_Result],
+        xlsm: typing.Callable[[], T_Result],
+        xlsb: typing.Callable[[], T_Result],
+        xlw: typing.Callable[[], T_Result],
+        csv: typing.Callable[[], T_Result],
+        dif: typing.Callable[[], T_Result],
+        sylk: typing.Callable[[], T_Result],
+        slk: typing.Callable[[], T_Result],
+        prn: typing.Callable[[], T_Result],
+        numbers: typing.Callable[[], T_Result],
+        et: typing.Callable[[], T_Result],
+        ods: typing.Callable[[], T_Result],
+        fods: typing.Callable[[], T_Result],
+        uos_1: typing.Callable[[], T_Result],
+        uos_2: typing.Callable[[], T_Result],
+        dbf: typing.Callable[[], T_Result],
+        wk_1: typing.Callable[[], T_Result],
+        wk_2: typing.Callable[[], T_Result],
+        wk_3: typing.Callable[[], T_Result],
+        wk_4: typing.Callable[[], T_Result],
+        wks: typing.Callable[[], T_Result],
+        wq_1: typing.Callable[[], T_Result],
+        wq_2: typing.Callable[[], T_Result],
+        wb_1: typing.Callable[[], T_Result],
+        wb_2: typing.Callable[[], T_Result],
+        wb_3: typing.Callable[[], T_Result],
+        qpw: typing.Callable[[], T_Result],
+        xlr: typing.Callable[[], T_Result],
+        eth: typing.Callable[[], T_Result],
+        tsv: typing.Callable[[], T_Result],
     ) -> T_Result:
         if self is LlamaParseSupportedFileExtensions.PDF:
             return pdf()
@@ -159,3 +221,65 @@ class LlamaParseSupportedFileExtensions(str, enum.Enum):
             return html()
         if self is LlamaParseSupportedFileExtensions.HTM:
             return htm()
+        if self is LlamaParseSupportedFileExtensions.XLS:
+            return xls()
+        if self is LlamaParseSupportedFileExtensions.XLSX:
+            return xlsx()
+        if self is LlamaParseSupportedFileExtensions.XLSM:
+            return xlsm()
+        if self is LlamaParseSupportedFileExtensions.XLSB:
+            return xlsb()
+        if self is LlamaParseSupportedFileExtensions.XLW:
+            return xlw()
+        if self is LlamaParseSupportedFileExtensions.CSV:
+            return csv()
+        if self is LlamaParseSupportedFileExtensions.DIF:
+            return dif()
+        if self is LlamaParseSupportedFileExtensions.SYLK:
+            return sylk()
+        if self is LlamaParseSupportedFileExtensions.SLK:
+            return slk()
+        if self is LlamaParseSupportedFileExtensions.PRN:
+            return prn()
+        if self is LlamaParseSupportedFileExtensions.NUMBERS:
+            return numbers()
+        if self is LlamaParseSupportedFileExtensions.ET:
+            return et()
+        if self is LlamaParseSupportedFileExtensions.ODS:
+            return ods()
+        if self is LlamaParseSupportedFileExtensions.FODS:
+            return fods()
+        if self is LlamaParseSupportedFileExtensions.UOS_1:
+            return uos_1()
+        if self is LlamaParseSupportedFileExtensions.UOS_2:
+            return uos_2()
+        if self is LlamaParseSupportedFileExtensions.DBF:
+            return dbf()
+        if self is LlamaParseSupportedFileExtensions.WK_1:
+            return wk_1()
+        if self is LlamaParseSupportedFileExtensions.WK_2:
+            return wk_2()
+        if self is LlamaParseSupportedFileExtensions.WK_3:
+            return wk_3()
+        if self is LlamaParseSupportedFileExtensions.WK_4:
+            return wk_4()
+        if self is LlamaParseSupportedFileExtensions.WKS:
+            return wks()
+        if self is LlamaParseSupportedFileExtensions.WQ_1:
+            return wq_1()
+        if self is LlamaParseSupportedFileExtensions.WQ_2:
+            return wq_2()
+        if self is LlamaParseSupportedFileExtensions.WB_1:
+            return wb_1()
+        if self is LlamaParseSupportedFileExtensions.WB_2:
+            return wb_2()
+        if self is LlamaParseSupportedFileExtensions.WB_3:
+            return wb_3()
+        if self is LlamaParseSupportedFileExtensions.QPW:
+            return qpw()
+        if self is LlamaParseSupportedFileExtensions.XLR:
+            return xlr()
+        if self is LlamaParseSupportedFileExtensions.ETH:
+            return eth()
+        if self is LlamaParseSupportedFileExtensions.TSV:
+            return tsv()

llama_cloud/types/pipeline.py

@@ -8,7 +8,6 @@ from .configured_transformation_item import ConfiguredTransformationItem
 from .data_sink import DataSink
 from .eval_execution_params import EvalExecutionParams
 from .llama_parse_parameters import LlamaParseParameters
-from .managed_ingestion_status import ManagedIngestionStatus
 from .pipeline_type import PipelineType
 from .preset_retrieval_params import PresetRetrievalParams
 
@@ -50,9 +49,6 @@ class Pipeline(pydantic.BaseModel):
     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."
     )
-    managed_ingestion_status: typing.Optional[ManagedIngestionStatus] = pydantic.Field(
-        description="Status of Managed Ingestion."
-    )
     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_cloud/types/pipeline_data_source_component_one.py

@@ -3,17 +3,17 @@
 import typing
 
 from .cloud_az_storage_blob_data_source import CloudAzStorageBlobDataSource
-from .cloud_gcs_data_source import CloudGcsDataSource
-from .cloud_google_drive_data_source import CloudGoogleDriveDataSource
+from .cloud_notion_page_data_source import CloudNotionPageDataSource
 from .cloud_one_drive_data_source import CloudOneDriveDataSource
 from .cloud_s_3_data_source import CloudS3DataSource
 from .cloud_sharepoint_data_source import CloudSharepointDataSource
+from .cloud_slack_data_source import CloudSlackDataSource
 
 PipelineDataSourceComponentOne = typing.Union[
     CloudS3DataSource,
     CloudAzStorageBlobDataSource,
-    CloudGcsDataSource,
-    CloudGoogleDriveDataSource,
     CloudOneDriveDataSource,
     CloudSharepointDataSource,
+    CloudSlackDataSource,
+    CloudNotionPageDataSource,
 ]

llama_cloud/types/text_node.py

@@ -37,6 +37,7 @@ class TextNode(pydantic.BaseModel):
         description="A mapping of relationships to other node information."
     )
     text: typing.Optional[str] = pydantic.Field(description="Text content of the node.")
+    mimetype: typing.Optional[str] = pydantic.Field(description="MIME type of the node content.")
     start_char_idx: typing.Optional[int] = pydantic.Field(description="Start char index of the node.")
     end_char_idx: typing.Optional[int] = pydantic.Field(description="End char index of the node.")
     text_template: typing.Optional[str] = pydantic.Field(

{llama_cloud-0.0.6.dist-info → llama_cloud-0.0.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: llama-cloud
-Version: 0.0.6
+Version: 0.0.8
 Summary: 
 Author: Logan Markewich
 Author-email: logan@runllama.ai
@@ -10,7 +10,6 @@ Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
 Requires-Dist: httpx (>=0.20.0)
 Requires-Dist: pydantic (>=1.10)
 Description-Content-Type: text/markdown