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

llama_cloud/types/file_query_response.py

@@ -1,38 +1,58 @@
-# 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 List, Optional
+from datetime import datetime
 
-from ..core.datetime_utils import serialize_datetime
-from .file import File
+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__ = ["FileQueryResponse", "Item"]
 
 
-class FileQueryResponse(pydantic.BaseModel):
+class Item(BaseModel):
+    """Schema for a file in the v2 API."""
+
+    id: str
+    """Unique identifier"""
+
+    name: str
+
+    project_id: str
+    """The ID of the project that the file belongs to"""
+
+    expires_at: Optional[datetime] = None
+    """The expiration date for the file. Files past this date can be deleted."""
+
+    external_file_id: Optional[str] = None
+    """The ID of the file in the external system"""
+
+    file_type: Optional[str] = None
+    """File type (e.g. pdf, docx, etc.)"""
+
+    last_modified_at: Optional[datetime] = None
+    """The last modified time of the file"""
+
+    purpose: Optional[str] = None
     """
-    Response schema for paginated file queries.
+    The intended purpose of the file (e.g., 'user_data', 'parse', 'extract',
+    'split', 'classify', 'sheet')
     """
 
-    items: typing.List[File] = pydantic.Field(description="The list of items.")
-    next_page_token: typing.Optional[str]
-    total_size: typing.Optional[int]
 
-    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)
+class FileQueryResponse(BaseModel):
+    """Response schema for paginated file queries in V2 API."""
+
+    items: List[Item]
+    """The list of items."""
+
+    next_page_token: Optional[str] = None
+    """A token, which can be sent as page_token to retrieve the next page.
 
-    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)
+    If this field is omitted, there are no subsequent pages.
+    """
+
+    total_size: Optional[int] = None
+    """The total number of items available.
 
-    class Config:
-        frozen = True
-        smart_union = True
-        json_encoders = {dt.datetime: serialize_datetime}
+    This is only populated when specifically requested. The value may be an estimate
+    and can be used for display purposes only.
+    """

llama_cloud/types/gemini_embedding.py

@@ -1,39 +1,40 @@
-# 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 GeminiEmbedding(pydantic.BaseModel):
-    model_name: typing.Optional[str] = pydantic.Field(description="The modelId of the Gemini model to use.")
-    embed_batch_size: typing.Optional[int] = pydantic.Field(description="The batch size for embedding calls.")
-    num_workers: typing.Optional[int]
-    title: typing.Optional[str]
-    task_type: typing.Optional[str]
-    api_key: typing.Optional[str]
-    api_base: typing.Optional[str]
-    transport: typing.Optional[str]
-    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}
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Optional
+
+from pydantic import Field as FieldInfo
+
+from .._models import BaseModel
+
+__all__ = ["GeminiEmbedding"]
+
+
+class GeminiEmbedding(BaseModel):
+    api_base: Optional[str] = None
+    """API base to access the model. Defaults to None."""
+
+    api_key: Optional[str] = None
+    """API key to access the model. Defaults to None."""
+
+    class_name: Optional[str] = None
+
+    embed_batch_size: Optional[int] = None
+    """The batch size for embedding calls."""
+
+    api_model_name: Optional[str] = FieldInfo(alias="model_name", default=None)
+    """The modelId of the Gemini model to use."""
+
+    num_workers: Optional[int] = None
+    """The number of workers to use for async embedding calls."""
+
+    task_type: Optional[str] = None
+    """The task for embedding model."""
+
+    title: Optional[str] = None
+    """
+    Title is only applicable for retrieval_document tasks, and is used to represent
+    a document title. For other tasks, title is invalid.
+    """
+
+    transport: Optional[str] = None
+    """Transport to access the model. Defaults to None."""

llama_cloud/types/gemini_embedding_config.py

@@ -1,34 +1,17 @@
-# 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 typing_extensions import Literal
 
-from ..core.datetime_utils import serialize_datetime
+from .._models import BaseModel
 from .gemini_embedding import GeminiEmbedding
 
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
+__all__ = ["GeminiEmbeddingConfig"]
 
 
-class GeminiEmbeddingConfig(pydantic.BaseModel):
-    component: typing.Optional[GeminiEmbedding] = pydantic.Field(
-        description="Configuration for the Gemini embedding model."
-    )
+class GeminiEmbeddingConfig(BaseModel):
+    component: Optional[GeminiEmbedding] = None
+    """Configuration for the Gemini embedding model."""
 
-    def json(self, **kwargs: typing.Any) -> str:
-        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
-        return super().json(**kwargs_with_defaults)
-
-    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
-        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
-        return super().dict(**kwargs_with_defaults)
-
-    class Config:
-        frozen = True
-        smart_union = True
-        json_encoders = {dt.datetime: serialize_datetime}
+    type: Optional[Literal["GEMINI_EMBEDDING"]] = None
+    """Type of the embedding model."""

llama_cloud/types/gemini_embedding_config_param.py

@@ -0,0 +1,17 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing_extensions import Literal, TypedDict
+
+from .gemini_embedding_param import GeminiEmbeddingParam
+
+__all__ = ["GeminiEmbeddingConfigParam"]
+
+
+class GeminiEmbeddingConfigParam(TypedDict, total=False):
+    component: GeminiEmbeddingParam
+    """Configuration for the Gemini embedding model."""
+
+    type: Literal["GEMINI_EMBEDDING"]
+    """Type of the embedding model."""

llama_cloud/types/gemini_embedding_param.py

@@ -0,0 +1,39 @@
+# 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__ = ["GeminiEmbeddingParam"]
+
+
+class GeminiEmbeddingParam(TypedDict, total=False):
+    api_base: Optional[str]
+    """API base to access the model. Defaults to None."""
+
+    api_key: Optional[str]
+    """API key to access the model. Defaults to None."""
+
+    class_name: str
+
+    embed_batch_size: int
+    """The batch size for embedding calls."""
+
+    model_name: str
+    """The modelId of the Gemini model to use."""
+
+    num_workers: Optional[int]
+    """The number of workers to use for async embedding calls."""
+
+    task_type: Optional[str]
+    """The task for embedding model."""
+
+    title: Optional[str]
+    """
+    Title is only applicable for retrieval_document tasks, and is used to represent
+    a document title. For other tasks, title is invalid.
+    """
+
+    transport: Optional[str]
+    """Transport to access the model. Defaults to None."""

llama_cloud/types/hugging_face_inference_api_embedding.py

@@ -1,46 +1,62 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import datetime as dt
-import typing
-
-from ..core.datetime_utils import serialize_datetime
-from .hugging_face_inference_api_embedding_token import HuggingFaceInferenceApiEmbeddingToken
-from .pooling import Pooling
-
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
-
-
-class HuggingFaceInferenceApiEmbedding(pydantic.BaseModel):
-    model_name: typing.Optional[str]
-    embed_batch_size: typing.Optional[int] = pydantic.Field(description="The batch size for embedding calls.")
-    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]
-    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:
-        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}
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Dict, Union, Optional
+from typing_extensions import Literal
+
+from pydantic import Field as FieldInfo
+
+from .._models import BaseModel
+
+__all__ = ["HuggingFaceInferenceAPIEmbedding"]
+
+
+class HuggingFaceInferenceAPIEmbedding(BaseModel):
+    token: Union[str, bool, None] = None
+    """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.
+    """
+
+    class_name: Optional[str] = None
+
+    cookies: Optional[Dict[str, str]] = None
+    """Additional cookies to send to the server."""
+
+    embed_batch_size: Optional[int] = None
+    """The batch size for embedding calls."""
+
+    headers: Optional[Dict[str, str]] = None
+    """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.
+    """
+
+    api_model_name: Optional[str] = FieldInfo(alias="model_name", default=None)
+    """Hugging Face model name. If None, the task will be used."""
+
+    num_workers: Optional[int] = None
+    """The number of workers to use for async embedding calls."""
+
+    pooling: Optional[Literal["cls", "mean", "last"]] = None
+    """Enum of possible pooling choices with pooling behaviors."""
+
+    query_instruction: Optional[str] = None
+    """Instruction to prepend during query embedding."""
+
+    task: Optional[str] = None
+    """
+    Optional task to pick Hugging Face's recommended model, used when model_name is
+    left as default of None.
+    """
+
+    text_instruction: Optional[str] = None
+    """Instruction to prepend during text embedding."""
+
+    timeout: Optional[float] = None
+    """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.
+    """

llama_cloud/types/hugging_face_inference_api_embedding_config.py

@@ -1,34 +1,17 @@
-# 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 typing_extensions import Literal
 
-from ..core.datetime_utils import serialize_datetime
-from .hugging_face_inference_api_embedding import HuggingFaceInferenceApiEmbedding
+from .._models import BaseModel
+from .hugging_face_inference_api_embedding import HuggingFaceInferenceAPIEmbedding
 
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
+__all__ = ["HuggingFaceInferenceAPIEmbeddingConfig"]
 
 
-class HuggingFaceInferenceApiEmbeddingConfig(pydantic.BaseModel):
-    component: typing.Optional[HuggingFaceInferenceApiEmbedding] = pydantic.Field(
-        description="Configuration for the HuggingFace Inference API embedding model."
-    )
+class HuggingFaceInferenceAPIEmbeddingConfig(BaseModel):
+    component: Optional[HuggingFaceInferenceAPIEmbedding] = None
+    """Configuration for the HuggingFace Inference API embedding model."""
 
-    def json(self, **kwargs: typing.Any) -> str:
-        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
-        return super().json(**kwargs_with_defaults)
-
-    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
-        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
-        return super().dict(**kwargs_with_defaults)
-
-    class Config:
-        frozen = True
-        smart_union = True
-        json_encoders = {dt.datetime: serialize_datetime}
+    type: Optional[Literal["HUGGINGFACE_API_EMBEDDING"]] = None
+    """Type of the embedding model."""

llama_cloud/types/hugging_face_inference_api_embedding_config_param.py

@@ -0,0 +1,17 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing_extensions import Literal, TypedDict
+
+from .hugging_face_inference_api_embedding_param import HuggingFaceInferenceAPIEmbeddingParam
+
+__all__ = ["HuggingFaceInferenceAPIEmbeddingConfigParam"]
+
+
+class HuggingFaceInferenceAPIEmbeddingConfigParam(TypedDict, total=False):
+    component: HuggingFaceInferenceAPIEmbeddingParam
+    """Configuration for the HuggingFace Inference API embedding model."""
+
+    type: Literal["HUGGINGFACE_API_EMBEDDING"]
+    """Type of the embedding model."""

llama_cloud/types/hugging_face_inference_api_embedding_param.py

@@ -0,0 +1,60 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict, Union, Optional
+from typing_extensions import Literal, TypedDict
+
+__all__ = ["HuggingFaceInferenceAPIEmbeddingParam"]
+
+
+class HuggingFaceInferenceAPIEmbeddingParam(TypedDict, total=False):
+    token: Union[str, bool, None]
+    """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.
+    """
+
+    class_name: str
+
+    cookies: Optional[Dict[str, str]]
+    """Additional cookies to send to the server."""
+
+    embed_batch_size: int
+    """The batch size for embedding calls."""
+
+    headers: Optional[Dict[str, str]]
+    """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.
+    """
+
+    model_name: Optional[str]
+    """Hugging Face model name. If None, the task will be used."""
+
+    num_workers: Optional[int]
+    """The number of workers to use for async embedding calls."""
+
+    pooling: Optional[Literal["cls", "mean", "last"]]
+    """Enum of possible pooling choices with pooling behaviors."""
+
+    query_instruction: Optional[str]
+    """Instruction to prepend during query embedding."""
+
+    task: Optional[str]
+    """
+    Optional task to pick Hugging Face's recommended model, used when model_name is
+    left as default of None.
+    """
+
+    text_instruction: Optional[str]
+    """Instruction to prepend during text embedding."""
+
+    timeout: Optional[float]
+    """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.
+    """

llama_cloud/types/list_item.py

@@ -0,0 +1,48 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, List, Union, Optional
+from typing_extensions import Literal, TypeAlias, TypeAliasType
+
+from pydantic import Field as FieldInfo
+
+from .b_box import BBox
+from .._compat import PYDANTIC_V1
+from .._models import BaseModel
+
+__all__ = ["ListItem", "Item", "ItemTextItem"]
+
+
+class ItemTextItem(BaseModel):
+    md: str
+    """Markdown representation preserving formatting"""
+
+    value: str
+    """Text content"""
+
+    b_box: Optional[List[BBox]] = FieldInfo(alias="bBox", default=None)
+    """List of bounding boxes"""
+
+    type: Optional[Literal["text"]] = None
+    """Text item type"""
+
+
+if TYPE_CHECKING or not PYDANTIC_V1:
+    Item = TypeAliasType("Item", Union[ItemTextItem, "ListItem"])
+else:
+    Item: TypeAlias = Union[ItemTextItem, "ListItem"]
+
+
+class ListItem(BaseModel):
+    items: List[Item]
+    """List of nested text or list items"""
+
+    ordered: bool
+    """Whether the list is ordered or unordered"""
+
+    b_box: Optional[List[BBox]] = FieldInfo(alias="bBox", default=None)
+    """List of bounding boxes"""
+
+    type: Optional[Literal["list"]] = None
+    """List item type"""