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

llama_cloud/types/advanced_mode_transform_config.py

@@ -1,38 +1,102 @@
-# 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 .advanced_mode_transform_config_chunking_config import AdvancedModeTransformConfigChunkingConfig
-from .advanced_mode_transform_config_segmentation_config import AdvancedModeTransformConfigSegmentationConfig
-
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
-
-
-class AdvancedModeTransformConfig(pydantic.BaseModel):
-    segmentation_config: typing.Optional[AdvancedModeTransformConfigSegmentationConfig] = pydantic.Field(
-        description="Configuration for the segmentation."
-    )
-    chunking_config: typing.Optional[AdvancedModeTransformConfigChunkingConfig] = pydantic.Field(
-        description="Configuration for the chunking."
-    )
-
-    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 Union, Optional
+from typing_extensions import Literal, TypeAlias
+
+from .._models import BaseModel
+
+__all__ = [
+    "AdvancedModeTransformConfig",
+    "ChunkingConfig",
+    "ChunkingConfigNoneChunkingConfig",
+    "ChunkingConfigCharacterChunkingConfig",
+    "ChunkingConfigTokenChunkingConfig",
+    "ChunkingConfigSentenceChunkingConfig",
+    "ChunkingConfigSemanticChunkingConfig",
+    "SegmentationConfig",
+    "SegmentationConfigNoneSegmentationConfig",
+    "SegmentationConfigPageSegmentationConfig",
+    "SegmentationConfigElementSegmentationConfig",
+]
+
+
+class ChunkingConfigNoneChunkingConfig(BaseModel):
+    mode: Optional[Literal["none"]] = None
+
+
+class ChunkingConfigCharacterChunkingConfig(BaseModel):
+    chunk_overlap: Optional[int] = None
+
+    chunk_size: Optional[int] = None
+
+    mode: Optional[Literal["character"]] = None
+
+
+class ChunkingConfigTokenChunkingConfig(BaseModel):
+    chunk_overlap: Optional[int] = None
+
+    chunk_size: Optional[int] = None
+
+    mode: Optional[Literal["token"]] = None
+
+    separator: Optional[str] = None
+
+
+class ChunkingConfigSentenceChunkingConfig(BaseModel):
+    chunk_overlap: Optional[int] = None
+
+    chunk_size: Optional[int] = None
+
+    mode: Optional[Literal["sentence"]] = None
+
+    paragraph_separator: Optional[str] = None
+
+    separator: Optional[str] = None
+
+
+class ChunkingConfigSemanticChunkingConfig(BaseModel):
+    breakpoint_percentile_threshold: Optional[int] = None
+
+    buffer_size: Optional[int] = None
+
+    mode: Optional[Literal["semantic"]] = None
+
+
+ChunkingConfig: TypeAlias = Union[
+    ChunkingConfigNoneChunkingConfig,
+    ChunkingConfigCharacterChunkingConfig,
+    ChunkingConfigTokenChunkingConfig,
+    ChunkingConfigSentenceChunkingConfig,
+    ChunkingConfigSemanticChunkingConfig,
+]
+
+
+class SegmentationConfigNoneSegmentationConfig(BaseModel):
+    mode: Optional[Literal["none"]] = None
+
+
+class SegmentationConfigPageSegmentationConfig(BaseModel):
+    mode: Optional[Literal["page"]] = None
+
+    page_separator: Optional[str] = None
+
+
+class SegmentationConfigElementSegmentationConfig(BaseModel):
+    mode: Optional[Literal["element"]] = None
+
+
+SegmentationConfig: TypeAlias = Union[
+    SegmentationConfigNoneSegmentationConfig,
+    SegmentationConfigPageSegmentationConfig,
+    SegmentationConfigElementSegmentationConfig,
+]
+
+
+class AdvancedModeTransformConfig(BaseModel):
+    chunking_config: Optional[ChunkingConfig] = None
+    """Configuration for the chunking."""
+
+    mode: Optional[Literal["advanced"]] = None
+
+    segmentation_config: Optional[SegmentationConfig] = None
+    """Configuration for the segmentation."""

llama_cloud/types/advanced_mode_transform_config_param.py

@@ -0,0 +1,102 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Union
+from typing_extensions import Literal, TypeAlias, TypedDict
+
+__all__ = [
+    "AdvancedModeTransformConfigParam",
+    "ChunkingConfig",
+    "ChunkingConfigNoneChunkingConfig",
+    "ChunkingConfigCharacterChunkingConfig",
+    "ChunkingConfigTokenChunkingConfig",
+    "ChunkingConfigSentenceChunkingConfig",
+    "ChunkingConfigSemanticChunkingConfig",
+    "SegmentationConfig",
+    "SegmentationConfigNoneSegmentationConfig",
+    "SegmentationConfigPageSegmentationConfig",
+    "SegmentationConfigElementSegmentationConfig",
+]
+
+
+class ChunkingConfigNoneChunkingConfig(TypedDict, total=False):
+    mode: Literal["none"]
+
+
+class ChunkingConfigCharacterChunkingConfig(TypedDict, total=False):
+    chunk_overlap: int
+
+    chunk_size: int
+
+    mode: Literal["character"]
+
+
+class ChunkingConfigTokenChunkingConfig(TypedDict, total=False):
+    chunk_overlap: int
+
+    chunk_size: int
+
+    mode: Literal["token"]
+
+    separator: str
+
+
+class ChunkingConfigSentenceChunkingConfig(TypedDict, total=False):
+    chunk_overlap: int
+
+    chunk_size: int
+
+    mode: Literal["sentence"]
+
+    paragraph_separator: str
+
+    separator: str
+
+
+class ChunkingConfigSemanticChunkingConfig(TypedDict, total=False):
+    breakpoint_percentile_threshold: int
+
+    buffer_size: int
+
+    mode: Literal["semantic"]
+
+
+ChunkingConfig: TypeAlias = Union[
+    ChunkingConfigNoneChunkingConfig,
+    ChunkingConfigCharacterChunkingConfig,
+    ChunkingConfigTokenChunkingConfig,
+    ChunkingConfigSentenceChunkingConfig,
+    ChunkingConfigSemanticChunkingConfig,
+]
+
+
+class SegmentationConfigNoneSegmentationConfig(TypedDict, total=False):
+    mode: Literal["none"]
+
+
+class SegmentationConfigPageSegmentationConfig(TypedDict, total=False):
+    mode: Literal["page"]
+
+    page_separator: str
+
+
+class SegmentationConfigElementSegmentationConfig(TypedDict, total=False):
+    mode: Literal["element"]
+
+
+SegmentationConfig: TypeAlias = Union[
+    SegmentationConfigNoneSegmentationConfig,
+    SegmentationConfigPageSegmentationConfig,
+    SegmentationConfigElementSegmentationConfig,
+]
+
+
+class AdvancedModeTransformConfigParam(TypedDict, total=False):
+    chunking_config: ChunkingConfig
+    """Configuration for the chunking."""
+
+    mode: Literal["advanced"]
+
+    segmentation_config: SegmentationConfig
+    """Configuration for the segmentation."""

llama_cloud/types/auto_transform_config.py

@@ -1,32 +1,18 @@
-# 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
 
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
+__all__ = ["AutoTransformConfig"]
 
 
-class AutoTransformConfig(pydantic.BaseModel):
-    chunk_size: typing.Optional[int] = pydantic.Field(description="Chunk size for the transformation.")
-    chunk_overlap: typing.Optional[int] = pydantic.Field(description="Chunk overlap for the transformation.")
+class AutoTransformConfig(BaseModel):
+    chunk_overlap: Optional[int] = None
+    """Chunk overlap for the transformation."""
 
-    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)
+    chunk_size: Optional[int] = None
+    """Chunk size for the transformation."""
 
-    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}
+    mode: Optional[Literal["auto"]] = None

llama_cloud/types/auto_transform_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
+
+__all__ = ["AutoTransformConfigParam"]
+
+
+class AutoTransformConfigParam(TypedDict, total=False):
+    chunk_overlap: int
+    """Chunk overlap for the transformation."""
+
+    chunk_size: int
+    """Chunk size for the transformation."""
+
+    mode: Literal["auto"]

llama_cloud/types/azure_openai_embedding.py

@@ -0,0 +1,62 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Dict, Optional
+
+from pydantic import Field as FieldInfo
+
+from .._models import BaseModel
+
+__all__ = ["AzureOpenAIEmbedding"]
+
+
+class AzureOpenAIEmbedding(BaseModel):
+    additional_kwargs: Optional[Dict[str, object]] = None
+    """Additional kwargs for the OpenAI API."""
+
+    api_base: Optional[str] = None
+    """The base URL for Azure deployment."""
+
+    api_key: Optional[str] = None
+    """The OpenAI API key."""
+
+    api_version: Optional[str] = None
+    """The version for Azure OpenAI API."""
+
+    azure_deployment: Optional[str] = None
+    """The Azure deployment to use."""
+
+    azure_endpoint: Optional[str] = None
+    """The Azure endpoint to use."""
+
+    class_name: Optional[str] = None
+
+    default_headers: Optional[Dict[str, str]] = None
+    """The default headers for API requests."""
+
+    dimensions: Optional[int] = None
+    """The number of dimensions on the output embedding vectors.
+
+    Works only with v3 embedding models.
+    """
+
+    embed_batch_size: Optional[int] = None
+    """The batch size for embedding calls."""
+
+    max_retries: Optional[int] = None
+    """Maximum number of retries."""
+
+    api_model_name: Optional[str] = FieldInfo(alias="model_name", default=None)
+    """The name of the OpenAI embedding model."""
+
+    num_workers: Optional[int] = None
+    """The number of workers to use for async embedding calls."""
+
+    reuse_client: Optional[bool] = None
+    """Reuse the OpenAI client between requests.
+
+    When doing anything with large volumes of async API calls, setting this to false
+    can improve stability.
+    """
+
+    timeout: Optional[float] = None
+    """Timeout for each request."""

llama_cloud/types/azure_openai_embedding_config.py

@@ -0,0 +1,17 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Optional
+from typing_extensions import Literal
+
+from .._models import BaseModel
+from .azure_openai_embedding import AzureOpenAIEmbedding
+
+__all__ = ["AzureOpenAIEmbeddingConfig"]
+
+
+class AzureOpenAIEmbeddingConfig(BaseModel):
+    component: Optional[AzureOpenAIEmbedding] = None
+    """Configuration for the Azure OpenAI embedding model."""
+
+    type: Optional[Literal["AZURE_EMBEDDING"]] = None
+    """Type of the embedding model."""

llama_cloud/types/azure_openai_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 .azure_openai_embedding_param import AzureOpenAIEmbeddingParam
+
+__all__ = ["AzureOpenAIEmbeddingConfigParam"]
+
+
+class AzureOpenAIEmbeddingConfigParam(TypedDict, total=False):
+    component: AzureOpenAIEmbeddingParam
+    """Configuration for the Azure OpenAI embedding model."""
+
+    type: Literal["AZURE_EMBEDDING"]
+    """Type of the embedding model."""

llama_cloud/types/azure_openai_embedding_param.py

@@ -0,0 +1,61 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict, Optional
+from typing_extensions import TypedDict
+
+__all__ = ["AzureOpenAIEmbeddingParam"]
+
+
+class AzureOpenAIEmbeddingParam(TypedDict, total=False):
+    additional_kwargs: Dict[str, object]
+    """Additional kwargs for the OpenAI API."""
+
+    api_base: str
+    """The base URL for Azure deployment."""
+
+    api_key: Optional[str]
+    """The OpenAI API key."""
+
+    api_version: str
+    """The version for Azure OpenAI API."""
+
+    azure_deployment: Optional[str]
+    """The Azure deployment to use."""
+
+    azure_endpoint: Optional[str]
+    """The Azure endpoint to use."""
+
+    class_name: str
+
+    default_headers: Optional[Dict[str, str]]
+    """The default headers for API requests."""
+
+    dimensions: Optional[int]
+    """The number of dimensions on the output embedding vectors.
+
+    Works only with v3 embedding models.
+    """
+
+    embed_batch_size: int
+    """The batch size for embedding calls."""
+
+    max_retries: int
+    """Maximum number of retries."""
+
+    model_name: str
+    """The name of the OpenAI embedding model."""
+
+    num_workers: Optional[int]
+    """The number of workers to use for async embedding calls."""
+
+    reuse_client: bool
+    """Reuse the OpenAI client between requests.
+
+    When doing anything with large volumes of async API calls, setting this to false
+    can improve stability.
+    """
+
+    timeout: float
+    """Timeout for each request."""

llama_cloud/types/b_box.py

@@ -0,0 +1,37 @@
+# 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__ = ["BBox"]
+
+
+class BBox(BaseModel):
+    """Bounding box with coordinates and optional metadata."""
+
+    h: float
+    """Height of the bounding box"""
+
+    w: float
+    """Width of the bounding box"""
+
+    x: float
+    """X coordinate of the bounding box"""
+
+    y: float
+    """Y coordinate of the bounding box"""
+
+    confidence: Optional[float] = None
+    """Confidence score"""
+
+    end_index: Optional[int] = FieldInfo(alias="endIndex", default=None)
+    """End index in the text"""
+
+    label: Optional[str] = None
+    """Label for the bounding box"""
+
+    start_index: Optional[int] = FieldInfo(alias="startIndex", default=None)
+    """Start index in the text"""

llama_cloud/types/bedrock_embedding.py

@@ -1,46 +1,49 @@
-# 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 BedrockEmbedding(pydantic.BaseModel):
-    model_name: typing.Optional[str] = pydantic.Field(description="The modelId of the Bedrock model to use.")
-    embed_batch_size: typing.Optional[int] = pydantic.Field(description="The batch size for embedding calls.")
-    num_workers: typing.Optional[int]
-    profile_name: typing.Optional[str]
-    aws_access_key_id: typing.Optional[str]
-    aws_secret_access_key: typing.Optional[str]
-    aws_session_token: typing.Optional[str]
-    region_name: typing.Optional[str]
-    max_retries: typing.Optional[int] = pydantic.Field(description="The maximum number of API retries.")
-    timeout: typing.Optional[float] = pydantic.Field(
-        description="The timeout for the Bedrock API request in seconds. It will be used for both connect and read timeouts."
-    )
-    additional_kwargs: typing.Optional[typing.Dict[str, typing.Any]] = pydantic.Field(
-        description="Additional kwargs for the bedrock client."
-    )
-    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, Optional
+
+from pydantic import Field as FieldInfo
+
+from .._models import BaseModel
+
+__all__ = ["BedrockEmbedding"]
+
+
+class BedrockEmbedding(BaseModel):
+    additional_kwargs: Optional[Dict[str, object]] = None
+    """Additional kwargs for the bedrock client."""
+
+    aws_access_key_id: Optional[str] = None
+    """AWS Access Key ID to use"""
+
+    aws_secret_access_key: Optional[str] = None
+    """AWS Secret Access Key to use"""
+
+    aws_session_token: Optional[str] = None
+    """AWS Session Token to use"""
+
+    class_name: Optional[str] = None
+
+    embed_batch_size: Optional[int] = None
+    """The batch size for embedding calls."""
+
+    max_retries: Optional[int] = None
+    """The maximum number of API retries."""
+
+    api_model_name: Optional[str] = FieldInfo(alias="model_name", default=None)
+    """The modelId of the Bedrock model to use."""
+
+    num_workers: Optional[int] = None
+    """The number of workers to use for async embedding calls."""
+
+    profile_name: Optional[str] = None
+    """The name of aws profile to use. If not given, then the default profile is used."""
+
+    region_name: Optional[str] = None
+    """AWS region name to use. Uses region configured in AWS CLI if not passed"""
+
+    timeout: Optional[float] = None
+    """The timeout for the Bedrock API request in seconds.
+
+    It will be used for both connect and read timeouts.
+    """

llama_cloud/types/bedrock_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 .bedrock_embedding import BedrockEmbedding
 
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
+__all__ = ["BedrockEmbeddingConfig"]
 
 
-class BedrockEmbeddingConfig(pydantic.BaseModel):
-    component: typing.Optional[BedrockEmbedding] = pydantic.Field(
-        description="Configuration for the Bedrock embedding model."
-    )
+class BedrockEmbeddingConfig(BaseModel):
+    component: Optional[BedrockEmbedding] = None
+    """Configuration for the Bedrock 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["BEDROCK_EMBEDDING"]] = None
+    """Type of the embedding model."""

llama_cloud/types/bedrock_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 .bedrock_embedding_param import BedrockEmbeddingParam
+
+__all__ = ["BedrockEmbeddingConfigParam"]
+
+
+class BedrockEmbeddingConfigParam(TypedDict, total=False):
+    component: BedrockEmbeddingParam
+    """Configuration for the Bedrock embedding model."""
+
+    type: Literal["BEDROCK_EMBEDDING"]
+    """Type of the embedding model."""