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

llama_cloud/types/metadata_filters_param.py

@@ -0,0 +1,58 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, Union, Iterable, Optional
+from typing_extensions import Literal, Required, TypeAlias, TypedDict, TypeAliasType
+
+from .._types import SequenceNotStr
+from .._compat import PYDANTIC_V1
+
+__all__ = ["MetadataFiltersParam", "Filter", "FilterMetadataFilter"]
+
+
+class FilterMetadataFilter(TypedDict, total=False):
+    """Comprehensive metadata filter for vector stores to support more operators.
+
+    Value uses Strict types, as int, float and str are compatible types and were all
+    converted to string before.
+
+    See: https://docs.pydantic.dev/latest/usage/types/#strict-types
+    """
+
+    key: Required[str]
+
+    value: Required[Union[float, str, SequenceNotStr[str], Iterable[float], Iterable[int], None]]
+
+    operator: Literal[
+        "==",
+        ">",
+        "<",
+        "!=",
+        ">=",
+        "<=",
+        "in",
+        "nin",
+        "any",
+        "all",
+        "text_match",
+        "text_match_insensitive",
+        "contains",
+        "is_empty",
+    ]
+    """Vector store filter operator."""
+
+
+if TYPE_CHECKING or not PYDANTIC_V1:
+    Filter = TypeAliasType("Filter", Union[FilterMetadataFilter, "MetadataFiltersParam"])
+else:
+    Filter: TypeAlias = Union[FilterMetadataFilter, "MetadataFiltersParam"]
+
+
+class MetadataFiltersParam(TypedDict, total=False):
+    """Metadata filters for vector stores."""
+
+    filters: Required[Iterable[Filter]]
+
+    condition: Optional[Literal["and", "or", "not"]]
+    """Vector store filter conditions to combine different filters."""

llama_cloud/types/openai_embedding.py

@@ -0,0 +1,56 @@
+# 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__ = ["OpenAIEmbedding"]
+
+
+class OpenAIEmbedding(BaseModel):
+    additional_kwargs: Optional[Dict[str, object]] = None
+    """Additional kwargs for the OpenAI API."""
+
+    api_base: Optional[str] = None
+    """The base URL for OpenAI API."""
+
+    api_key: Optional[str] = None
+    """The OpenAI API key."""
+
+    api_version: Optional[str] = None
+    """The version for OpenAI API."""
+
+    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/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 .openai_embedding import OpenAIEmbedding
+
+__all__ = ["OpenAIEmbeddingConfig"]
+
+
+class OpenAIEmbeddingConfig(BaseModel):
+    component: Optional[OpenAIEmbedding] = None
+    """Configuration for the OpenAI embedding model."""
+
+    type: Optional[Literal["OPENAI_EMBEDDING"]] = None
+    """Type of the embedding model."""

llama_cloud/types/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 .openai_embedding_param import OpenAIEmbeddingParam
+
+__all__ = ["OpenAIEmbeddingConfigParam"]
+
+
+class OpenAIEmbeddingConfigParam(TypedDict, total=False):
+    component: OpenAIEmbeddingParam
+    """Configuration for the OpenAI embedding model."""
+
+    type: Literal["OPENAI_EMBEDDING"]
+    """Type of the embedding model."""

llama_cloud/types/openai_embedding_param.py

@@ -0,0 +1,55 @@
+# 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__ = ["OpenAIEmbeddingParam"]
+
+
+class OpenAIEmbeddingParam(TypedDict, total=False):
+    additional_kwargs: Dict[str, object]
+    """Additional kwargs for the OpenAI API."""
+
+    api_base: Optional[str]
+    """The base URL for OpenAI API."""
+
+    api_key: Optional[str]
+    """The OpenAI API key."""
+
+    api_version: Optional[str]
+    """The version for OpenAI API."""
+
+    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/page_figure_node_with_score.py

@@ -1,38 +1,41 @@
-# 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 ..core.datetime_utils import serialize_datetime
-from .page_figure_metadata import PageFigureMetadata
+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__ = ["PageFigureNodeWithScore", "Node"]
 
 
-class PageFigureNodeWithScore(pydantic.BaseModel):
-    """
-    Page figure metadata with score
-    """
+class Node(BaseModel):
+    confidence: float
+    """The confidence of the figure"""
 
-    node: PageFigureMetadata
-    score: float = pydantic.Field(description="The score of the figure node")
-    class_name: typing.Optional[str]
+    figure_name: str
+    """The name of the figure"""
 
-    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)
+    figure_size: int
+    """The size of the figure in bytes"""
 
-    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)
+    file_id: str
+    """The ID of the file that the figure was taken from"""
 
-    class Config:
-        frozen = True
-        smart_union = True
-        json_encoders = {dt.datetime: serialize_datetime}
+    page_index: int
+    """The index of the page for which the figure is taken (0-indexed)"""
+
+    is_likely_noise: Optional[bool] = None
+    """Whether the figure is likely to be noise"""
+
+    metadata: Optional[Dict[str, object]] = None
+    """Metadata for the figure"""
+
+
+class PageFigureNodeWithScore(BaseModel):
+    """Page figure metadata with score"""
+
+    node: Node
+
+    score: float
+    """The score of the figure node"""
+
+    class_name: Optional[str] = None

llama_cloud/types/page_screenshot_node_with_score.py

@@ -1,38 +1,32 @@
-# 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 ..core.datetime_utils import serialize_datetime
-from .page_screenshot_metadata import PageScreenshotMetadata
+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__ = ["PageScreenshotNodeWithScore", "Node"]
 
 
-class PageScreenshotNodeWithScore(pydantic.BaseModel):
-    """
-    Page screenshot metadata with score
-    """
+class Node(BaseModel):
+    file_id: str
+    """The ID of the file that the page screenshot was taken from"""
 
-    node: PageScreenshotMetadata
-    score: float = pydantic.Field(description="The score of the screenshot node")
-    class_name: typing.Optional[str]
+    image_size: int
+    """The size of the image in bytes"""
 
-    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)
+    page_index: int
+    """The index of the page for which the screenshot is taken (0-indexed)"""
 
-    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)
+    metadata: Optional[Dict[str, object]] = None
+    """Metadata for the screenshot"""
 
-    class Config:
-        frozen = True
-        smart_union = True
-        json_encoders = {dt.datetime: serialize_datetime}
+
+class PageScreenshotNodeWithScore(BaseModel):
+    """Page screenshot metadata with score"""
+
+    node: Node
+
+    score: float
+    """The score of the screenshot node"""
+
+    class_name: Optional[str] = None