llama-cloud 0.1.41__py3-none-any.whl → 1.0.0b4__py3-none-any.whl

llama_cloud/types/pipelines/image_list_page_screenshots_params.py

@@ -0,0 +1,14 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Optional
+from typing_extensions import TypedDict
+
+__all__ = ["ImageListPageScreenshotsParams"]
+
+
+class ImageListPageScreenshotsParams(TypedDict, total=False):
+    organization_id: Optional[str]
+
+    project_id: Optional[str]

llama_cloud/types/pipelines/image_list_page_screenshots_response.py

@@ -0,0 +1,25 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Dict, List, Optional
+from typing_extensions import TypeAlias
+
+from ..._models import BaseModel
+
+__all__ = ["ImageListPageScreenshotsResponse", "ImageListPageScreenshotsResponseItem"]
+
+
+class ImageListPageScreenshotsResponseItem(BaseModel):
+    file_id: str
+    """The ID of the file that the page screenshot was taken from"""
+
+    image_size: int
+    """The size of the image in bytes"""
+
+    page_index: int
+    """The index of the page for which the screenshot is taken (0-indexed)"""
+
+    metadata: Optional[Dict[str, object]] = None
+    """Metadata for the screenshot"""
+
+
+ImageListPageScreenshotsResponse: TypeAlias = List[ImageListPageScreenshotsResponseItem]

llama_cloud/types/pipelines/metadata_create_params.py

@@ -0,0 +1,13 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing_extensions import Required, TypedDict
+
+from ..._types import FileTypes
+
+__all__ = ["MetadataCreateParams"]
+
+
+class MetadataCreateParams(TypedDict, total=False):
+    upload_file: Required[FileTypes]

llama_cloud/types/pipelines/metadata_create_response.py

@@ -0,0 +1,8 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Dict
+from typing_extensions import TypeAlias
+
+__all__ = ["MetadataCreateResponse"]
+
+MetadataCreateResponse: TypeAlias = Dict[str, str]

llama_cloud/types/pipelines/pipeline_data_source.py

@@ -0,0 +1,96 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Dict, List, Union, Optional
+from datetime import datetime
+from typing_extensions import Literal, TypeAlias
+
+from ..._models import BaseModel
+from ..shared.cloud_s3_data_source import CloudS3DataSource
+from ..shared.cloud_box_data_source import CloudBoxDataSource
+from ..shared.cloud_jira_data_source import CloudJiraDataSource
+from ..shared.cloud_slack_data_source import CloudSlackDataSource
+from ..shared.cloud_jira_data_source_v2 import CloudJiraDataSourceV2
+from ..shared.cloud_one_drive_data_source import CloudOneDriveDataSource
+from ..data_source_reader_version_metadata import DataSourceReaderVersionMetadata
+from ..shared.cloud_confluence_data_source import CloudConfluenceDataSource
+from ..shared.cloud_sharepoint_data_source import CloudSharepointDataSource
+from ..shared.cloud_notion_page_data_source import CloudNotionPageDataSource
+from ..shared.cloud_az_storage_blob_data_source import CloudAzStorageBlobDataSource
+
+__all__ = ["PipelineDataSource", "Component"]
+
+Component: TypeAlias = Union[
+    Dict[str, object],
+    CloudS3DataSource,
+    CloudAzStorageBlobDataSource,
+    CloudOneDriveDataSource,
+    CloudSharepointDataSource,
+    CloudSlackDataSource,
+    CloudNotionPageDataSource,
+    CloudConfluenceDataSource,
+    CloudJiraDataSource,
+    CloudJiraDataSourceV2,
+    CloudBoxDataSource,
+]
+
+
+class PipelineDataSource(BaseModel):
+    """Schema for a data source in a pipeline."""
+
+    id: str
+    """Unique identifier"""
+
+    component: Component
+    """Component that implements the data source"""
+
+    data_source_id: str
+    """The ID of the data source."""
+
+    last_synced_at: datetime
+    """The last time the data source was automatically synced."""
+
+    name: str
+    """The name of the data source."""
+
+    pipeline_id: str
+    """The ID of the pipeline."""
+
+    project_id: str
+
+    source_type: Literal[
+        "S3",
+        "AZURE_STORAGE_BLOB",
+        "GOOGLE_DRIVE",
+        "MICROSOFT_ONEDRIVE",
+        "MICROSOFT_SHAREPOINT",
+        "SLACK",
+        "NOTION_PAGE",
+        "CONFLUENCE",
+        "JIRA",
+        "JIRA_V2",
+        "BOX",
+    ]
+
+    created_at: Optional[datetime] = None
+    """Creation datetime"""
+
+    custom_metadata: Optional[Dict[str, Union[Dict[str, object], List[object], str, float, bool, None]]] = None
+    """Custom metadata that will be present on all data loaded from the data source"""
+
+    status: Optional[Literal["NOT_STARTED", "IN_PROGRESS", "SUCCESS", "ERROR", "CANCELLED"]] = None
+    """The status of the data source in the pipeline."""
+
+    status_updated_at: Optional[datetime] = None
+    """The last time the status was updated."""
+
+    sync_interval: Optional[float] = None
+    """The interval at which the data source should be synced."""
+
+    sync_schedule_set_by: Optional[str] = None
+    """The id of the user who set the sync schedule."""
+
+    updated_at: Optional[datetime] = None
+    """Update datetime"""
+
+    version_metadata: Optional[DataSourceReaderVersionMetadata] = None
+    """Version metadata for the data source"""

llama_cloud/types/pipelines/pipeline_file.py

@@ -0,0 +1,70 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Dict, List, Union, Optional
+from datetime import datetime
+from typing_extensions import Literal
+
+from ..._models import BaseModel
+
+__all__ = ["PipelineFile"]
+
+
+class PipelineFile(BaseModel):
+    """Schema for a file that is associated with a pipeline."""
+
+    id: str
+    """Unique identifier"""
+
+    pipeline_id: str
+    """The ID of the pipeline that the file is associated with"""
+
+    config_hash: Optional[Dict[str, Union[Dict[str, object], List[object], str, float, bool, None]]] = None
+    """Hashes for the configuration of the pipeline."""
+
+    created_at: Optional[datetime] = None
+    """Creation datetime"""
+
+    custom_metadata: Optional[Dict[str, Union[Dict[str, object], List[object], str, float, bool, None]]] = None
+    """Custom metadata for the file"""
+
+    data_source_id: Optional[str] = None
+    """The ID of the data source that the file belongs to"""
+
+    external_file_id: Optional[str] = None
+    """The ID of the file in the external system"""
+
+    file_id: Optional[str] = None
+    """The ID of the file"""
+
+    file_size: Optional[int] = None
+    """Size of the file in bytes"""
+
+    file_type: Optional[str] = None
+    """File type (e.g. pdf, docx, etc.)"""
+
+    indexed_page_count: Optional[int] = None
+    """The number of pages that have been indexed for this file"""
+
+    last_modified_at: Optional[datetime] = None
+    """The last modified time of the file"""
+
+    name: Optional[str] = None
+    """Name of the file"""
+
+    permission_info: Optional[Dict[str, Union[Dict[str, object], List[object], str, float, bool, None]]] = None
+    """Permission information for the file"""
+
+    project_id: Optional[str] = None
+    """The ID of the project that the file belongs to"""
+
+    resource_info: Optional[Dict[str, Union[Dict[str, object], List[object], str, float, bool, None]]] = None
+    """Resource information for the file"""
+
+    status: Optional[Literal["NOT_STARTED", "IN_PROGRESS", "SUCCESS", "ERROR", "CANCELLED"]] = None
+    """Status of the pipeline file"""
+
+    status_updated_at: Optional[datetime] = None
+    """The last time the status was updated"""
+
+    updated_at: Optional[datetime] = None
+    """Update datetime"""

llama_cloud/types/pipelines/text_node.py

@@ -0,0 +1,89 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Dict, List, Union, Optional
+from typing_extensions import Literal, TypeAlias
+
+from pydantic import Field as FieldInfo
+
+from ..._models import BaseModel
+
+__all__ = ["TextNode", "Relationships", "RelationshipsRelatedNodeInfo", "RelationshipsUnionMember1"]
+
+
+class RelationshipsRelatedNodeInfo(BaseModel):
+    node_id: str
+
+    class_name: Optional[str] = None
+
+    hash: Optional[str] = None
+
+    metadata: Optional[Dict[str, object]] = None
+
+    node_type: Union[Literal["1", "2", "3", "4", "5"], str, None] = None
+
+
+class RelationshipsUnionMember1(BaseModel):
+    node_id: str
+
+    class_name: Optional[str] = None
+
+    hash: Optional[str] = None
+
+    metadata: Optional[Dict[str, object]] = None
+
+    node_type: Union[Literal["1", "2", "3", "4", "5"], str, None] = None
+
+
+Relationships: TypeAlias = Union[RelationshipsRelatedNodeInfo, List[RelationshipsUnionMember1]]
+
+
+class TextNode(BaseModel):
+    """Provided for backward compatibility.
+
+    Note: we keep the field with the typo "seperator" to maintain backward compatibility for
+    serialized objects.
+    """
+
+    class_name: Optional[str] = None
+
+    embedding: Optional[List[float]] = None
+    """Embedding of the node."""
+
+    end_char_idx: Optional[int] = None
+    """End char index of the node."""
+
+    excluded_embed_metadata_keys: Optional[List[str]] = None
+    """Metadata keys that are excluded from text for the embed model."""
+
+    excluded_llm_metadata_keys: Optional[List[str]] = None
+    """Metadata keys that are excluded from text for the LLM."""
+
+    extra_info: Optional[Dict[str, object]] = None
+    """A flat dictionary of metadata fields"""
+
+    id: Optional[str] = FieldInfo(alias="id_", default=None)
+    """Unique ID of the node."""
+
+    metadata_seperator: Optional[str] = None
+    """Separator between metadata fields when converting to string."""
+
+    metadata_template: Optional[str] = None
+    """Template for how metadata is formatted, with {key} and {value} placeholders."""
+
+    mimetype: Optional[str] = None
+    """MIME type of the node content."""
+
+    relationships: Optional[Dict[str, Relationships]] = None
+    """A mapping of relationships to other node information."""
+
+    start_char_idx: Optional[int] = None
+    """Start char index of the node."""
+
+    text: Optional[str] = None
+    """Text content of the node."""
+
+    text_template: Optional[str] = None
+    """
+    Template for how text is formatted, with {content} and {metadata_str}
+    placeholders.
+    """

llama_cloud/types/preset_retrieval_params.py

@@ -1,59 +1,71 @@
-# This file was auto-generated by Fern from our API Definition.
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
-import datetime as dt
-import typing
+from __future__ import annotations
 
-from ..core.datetime_utils import serialize_datetime
-from .metadata_filters import MetadataFilters
-from .preset_retrieval_params_search_filters_inference_schema_value import (
-    PresetRetrievalParamsSearchFiltersInferenceSchemaValue,
-)
+from typing import Dict, List, Union, Optional
+
+from .._models import BaseModel
 from .retrieval_mode import RetrievalMode
 
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
+__all__ = ["PresetRetrievalParams"]
 
 
-class PresetRetrievalParams(pydantic.BaseModel):
+class PresetRetrievalParams(BaseModel):
     """
     Schema for the search params for an retrieval execution that can be preset for a pipeline.
     """
 
-    dense_similarity_top_k: typing.Optional[int]
-    dense_similarity_cutoff: typing.Optional[float]
-    sparse_similarity_top_k: typing.Optional[int]
-    enable_reranking: typing.Optional[bool]
-    rerank_top_n: typing.Optional[int]
-    alpha: typing.Optional[float]
-    search_filters: typing.Optional[MetadataFilters]
-    search_filters_inference_schema: typing.Optional[
-        typing.Dict[str, typing.Optional[PresetRetrievalParamsSearchFiltersInferenceSchemaValue]]
-    ]
-    files_top_k: typing.Optional[int]
-    retrieval_mode: typing.Optional[RetrievalMode] = pydantic.Field(description="The retrieval mode for the query.")
-    retrieve_image_nodes: typing.Optional[bool] = pydantic.Field(description="Whether to retrieve image nodes.")
-    retrieve_page_screenshot_nodes: typing.Optional[bool] = pydantic.Field(
-        description="Whether to retrieve page screenshot nodes."
-    )
-    retrieve_page_figure_nodes: typing.Optional[bool] = pydantic.Field(
-        description="Whether to retrieve page figure nodes."
-    )
-    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}
+    alpha: Optional[float] = None
+    """
+    Alpha value for hybrid retrieval to determine the weights between dense and
+    sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval.
+    """
+
+    class_name: Optional[str] = None
+
+    dense_similarity_cutoff: Optional[float] = None
+    """Minimum similarity score wrt query for retrieval"""
+
+    dense_similarity_top_k: Optional[int] = None
+    """Number of nodes for dense retrieval."""
+
+    enable_reranking: Optional[bool] = None
+    """Enable reranking for retrieval"""
+
+    files_top_k: Optional[int] = None
+    """
+    Number of files to retrieve (only for retrieval mode files_via_metadata and
+    files_via_content).
+    """
+
+    rerank_top_n: Optional[int] = None
+    """Number of reranked nodes for returning."""
+
+    retrieval_mode: Optional[RetrievalMode] = None
+    """The retrieval mode for the query."""
+
+    retrieve_image_nodes: Optional[bool] = None
+    """Whether to retrieve image nodes."""
+
+    retrieve_page_figure_nodes: Optional[bool] = None
+    """Whether to retrieve page figure nodes."""
+
+    retrieve_page_screenshot_nodes: Optional[bool] = None
+    """Whether to retrieve page screenshot nodes."""
+
+    search_filters: Optional["MetadataFilters"] = None
+    """Metadata filters for vector stores."""
+
+    search_filters_inference_schema: Optional[
+        Dict[str, Union[Dict[str, object], List[object], str, float, bool, None]]
+    ] = None
+    """JSON Schema that will be used to infer search_filters.
+
+    Omit or leave as null to skip inference.
+    """
+
+    sparse_similarity_top_k: Optional[int] = None
+    """Number of nodes for sparse retrieval."""
+
+
+from .metadata_filters import MetadataFilters

llama_cloud/types/preset_retrieval_params_param.py

@@ -0,0 +1,71 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict, Union, Iterable, Optional
+from typing_extensions import TypedDict
+
+from .retrieval_mode import RetrievalMode
+
+__all__ = ["PresetRetrievalParamsParam"]
+
+
+class PresetRetrievalParamsParam(TypedDict, total=False):
+    """
+    Schema for the search params for an retrieval execution that can be preset for a pipeline.
+    """
+
+    alpha: Optional[float]
+    """
+    Alpha value for hybrid retrieval to determine the weights between dense and
+    sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval.
+    """
+
+    class_name: str
+
+    dense_similarity_cutoff: Optional[float]
+    """Minimum similarity score wrt query for retrieval"""
+
+    dense_similarity_top_k: Optional[int]
+    """Number of nodes for dense retrieval."""
+
+    enable_reranking: Optional[bool]
+    """Enable reranking for retrieval"""
+
+    files_top_k: Optional[int]
+    """
+    Number of files to retrieve (only for retrieval mode files_via_metadata and
+    files_via_content).
+    """
+
+    rerank_top_n: Optional[int]
+    """Number of reranked nodes for returning."""
+
+    retrieval_mode: RetrievalMode
+    """The retrieval mode for the query."""
+
+    retrieve_image_nodes: bool
+    """Whether to retrieve image nodes."""
+
+    retrieve_page_figure_nodes: bool
+    """Whether to retrieve page figure nodes."""
+
+    retrieve_page_screenshot_nodes: bool
+    """Whether to retrieve page screenshot nodes."""
+
+    search_filters: Optional["MetadataFiltersParam"]
+    """Metadata filters for vector stores."""
+
+    search_filters_inference_schema: Optional[
+        Dict[str, Union[Dict[str, object], Iterable[object], str, float, bool, None]]
+    ]
+    """JSON Schema that will be used to infer search_filters.
+
+    Omit or leave as null to skip inference.
+    """
+
+    sparse_similarity_top_k: Optional[int]
+    """Number of nodes for sparse retrieval."""
+
+
+from .metadata_filters_param import MetadataFiltersParam

llama_cloud/types/presigned_url.py

@@ -1,37 +1,21 @@
-# This file was auto-generated by Fern from our API Definition.
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
-import datetime as dt
-import typing
+from typing import Dict, Optional
+from datetime import datetime
 
-from ..core.datetime_utils import serialize_datetime
+from .._models import BaseModel
 
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
+__all__ = ["PresignedURL"]
 
 
-class PresignedUrl(pydantic.BaseModel):
-    """
-    Schema for a presigned URL.
-    """
+class PresignedURL(BaseModel):
+    """Schema for a presigned URL."""
 
-    url: str = pydantic.Field(description="A presigned URL for IO operations against a private file")
-    expires_at: dt.datetime = pydantic.Field(description="The time at which the presigned URL expires")
-    form_fields: typing.Optional[typing.Dict[str, typing.Optional[str]]]
+    expires_at: datetime
+    """The time at which the presigned URL expires"""
 
-    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)
+    url: str
+    """A presigned URL for IO operations against a private file"""
 
-    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}
+    form_fields: Optional[Dict[str, str]] = None
+    """Form fields for a presigned POST request"""

llama_cloud/types/project.py

@@ -1,43 +1,31 @@
-# This file was auto-generated by Fern from our API Definition.
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
-import datetime as dt
-import typing
+from typing import Optional
+from datetime import datetime
 
-from ..core.datetime_utils import serialize_datetime
+from .._models import BaseModel
 
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
+__all__ = ["Project"]
 
 
-class Project(pydantic.BaseModel):
-    """
-    Schema for a project.
-    """
+class Project(BaseModel):
+    """Schema for a project."""
+
+    id: str
+    """Unique identifier"""
 
     name: str
-    id: str = pydantic.Field(description="Unique identifier")
-    created_at: typing.Optional[dt.datetime]
-    updated_at: typing.Optional[dt.datetime]
-    ad_hoc_eval_dataset_id: typing.Optional[str]
-    organization_id: str = pydantic.Field(description="The Organization ID the project is under.")
-    is_default: typing.Optional[bool] = pydantic.Field(
-        description="Whether this project is the default project for the user."
-    )
-
-    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}
+
+    organization_id: str
+    """The Organization ID the project is under."""
+
+    ad_hoc_eval_dataset_id: Optional[str] = None
+
+    created_at: Optional[datetime] = None
+    """Creation datetime"""
+
+    is_default: Optional[bool] = None
+    """Whether this project is the default project for the user."""
+
+    updated_at: Optional[datetime] = None
+    """Update datetime"""

llama_cloud/types/project_get_params.py

@@ -0,0 +1,12 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Optional
+from typing_extensions import TypedDict
+
+__all__ = ["ProjectGetParams"]
+
+
+class ProjectGetParams(TypedDict, total=False):
+    organization_id: Optional[str]

llama_cloud/types/project_list_params.py

@@ -0,0 +1,14 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Optional
+from typing_extensions import TypedDict
+
+__all__ = ["ProjectListParams"]
+
+
+class ProjectListParams(TypedDict, total=False):
+    organization_id: Optional[str]
+
+    project_name: Optional[str]