antfly-sdk 0.0.2.dev2__py3-none-any.whl

antfly/client_generated/models/inference_tool_call_delta.py

@@ -0,0 +1,110 @@
+from __future__ import annotations
+
+from collections.abc import Mapping
+from typing import TYPE_CHECKING, Any, TypeVar
+
+from attrs import define as _attrs_define
+from attrs import field as _attrs_field
+
+from ..models.inference_tool_call_delta_type import InferenceToolCallDeltaType
+from ..types import UNSET, Unset
+
+if TYPE_CHECKING:
+    from ..models.inference_tool_call_function_delta import InferenceToolCallFunctionDelta
+
+
+T = TypeVar("T", bound="InferenceToolCallDelta")
+
+
+@_attrs_define
+class InferenceToolCallDelta:
+    """Incremental tool call data for streaming
+
+    Attributes:
+        index (int | Unset): Index of the tool call in the array
+        id (str | Unset): Unique identifier (only in first delta for this index)
+        type_ (InferenceToolCallDeltaType | Unset): The type of tool call (only in first delta)
+        function (InferenceToolCallFunctionDelta | Unset): Incremental function call data for streaming
+    """
+
+    index: int | Unset = UNSET
+    id: str | Unset = UNSET
+    type_: InferenceToolCallDeltaType | Unset = UNSET
+    function: InferenceToolCallFunctionDelta | Unset = UNSET
+    additional_properties: dict[str, Any] = _attrs_field(init=False, factory=dict)
+
+    def to_dict(self) -> dict[str, Any]:
+        index = self.index
+
+        id = self.id
+
+        type_: str | Unset = UNSET
+        if not isinstance(self.type_, Unset):
+            type_ = self.type_.value
+
+        function: dict[str, Any] | Unset = UNSET
+        if not isinstance(self.function, Unset):
+            function = self.function.to_dict()
+
+        field_dict: dict[str, Any] = {}
+        field_dict.update(self.additional_properties)
+        field_dict.update({})
+        if index is not UNSET:
+            field_dict["index"] = index
+        if id is not UNSET:
+            field_dict["id"] = id
+        if type_ is not UNSET:
+            field_dict["type"] = type_
+        if function is not UNSET:
+            field_dict["function"] = function
+
+        return field_dict
+
+    @classmethod
+    def from_dict(cls: type[T], src_dict: Mapping[str, Any]) -> T:
+        from ..models.inference_tool_call_function_delta import InferenceToolCallFunctionDelta
+
+        d = dict(src_dict)
+        index = d.pop("index", UNSET)
+
+        id = d.pop("id", UNSET)
+
+        _type_ = d.pop("type", UNSET)
+        type_: InferenceToolCallDeltaType | Unset
+        if isinstance(_type_, Unset):
+            type_ = UNSET
+        else:
+            type_ = InferenceToolCallDeltaType(_type_)
+
+        _function = d.pop("function", UNSET)
+        function: InferenceToolCallFunctionDelta | Unset
+        if isinstance(_function, Unset):
+            function = UNSET
+        else:
+            function = InferenceToolCallFunctionDelta.from_dict(_function)
+
+        inference_tool_call_delta = cls(
+            index=index,
+            id=id,
+            type_=type_,
+            function=function,
+        )
+
+        inference_tool_call_delta.additional_properties = d
+        return inference_tool_call_delta
+
+    @property
+    def additional_keys(self) -> list[str]:
+        return list(self.additional_properties.keys())
+
+    def __getitem__(self, key: str) -> Any:
+        return self.additional_properties[key]
+
+    def __setitem__(self, key: str, value: Any) -> None:
+        self.additional_properties[key] = value
+
+    def __delitem__(self, key: str) -> None:
+        del self.additional_properties[key]
+
+    def __contains__(self, key: str) -> bool:
+        return key in self.additional_properties

antfly/client_generated/models/inference_tool_call_delta_type.py

@@ -0,0 +1,8 @@
+from enum import Enum
+
+
+class InferenceToolCallDeltaType(str, Enum):
+    FUNCTION = "function"
+
+    def __str__(self) -> str:
+        return str(self.value)

antfly/client_generated/models/inference_tool_call_function_delta.py

@@ -0,0 +1,71 @@
+from __future__ import annotations
+
+from collections.abc import Mapping
+from typing import Any, TypeVar
+
+from attrs import define as _attrs_define
+from attrs import field as _attrs_field
+
+from ..types import UNSET, Unset
+
+T = TypeVar("T", bound="InferenceToolCallFunctionDelta")
+
+
+@_attrs_define
+class InferenceToolCallFunctionDelta:
+    """Incremental function call data for streaming
+
+    Attributes:
+        name (str | Unset): Function name (only in first delta)
+        arguments (str | Unset): Incremental arguments JSON string
+    """
+
+    name: str | Unset = UNSET
+    arguments: str | Unset = UNSET
+    additional_properties: dict[str, Any] = _attrs_field(init=False, factory=dict)
+
+    def to_dict(self) -> dict[str, Any]:
+        name = self.name
+
+        arguments = self.arguments
+
+        field_dict: dict[str, Any] = {}
+        field_dict.update(self.additional_properties)
+        field_dict.update({})
+        if name is not UNSET:
+            field_dict["name"] = name
+        if arguments is not UNSET:
+            field_dict["arguments"] = arguments
+
+        return field_dict
+
+    @classmethod
+    def from_dict(cls: type[T], src_dict: Mapping[str, Any]) -> T:
+        d = dict(src_dict)
+        name = d.pop("name", UNSET)
+
+        arguments = d.pop("arguments", UNSET)
+
+        inference_tool_call_function_delta = cls(
+            name=name,
+            arguments=arguments,
+        )
+
+        inference_tool_call_function_delta.additional_properties = d
+        return inference_tool_call_function_delta
+
+    @property
+    def additional_keys(self) -> list[str]:
+        return list(self.additional_properties.keys())
+
+    def __getitem__(self, key: str) -> Any:
+        return self.additional_properties[key]
+
+    def __setitem__(self, key: str, value: Any) -> None:
+        self.additional_properties[key] = value
+
+    def __delitem__(self, key: str) -> None:
+        del self.additional_properties[key]
+
+    def __contains__(self, key: str) -> bool:
+        return key in self.additional_properties

antfly/client_generated/models/inference_tool_choice_type_0.py

@@ -0,0 +1,10 @@
+from enum import Enum
+
+
+class InferenceToolChoiceType0(str, Enum):
+    AUTO = "auto"
+    NONE = "none"
+    REQUIRED = "required"
+
+    def __str__(self) -> str:
+        return str(self.value)

antfly/client_generated/models/inference_tool_choice_type_1_function.py

@@ -0,0 +1,61 @@
+from __future__ import annotations
+
+from collections.abc import Mapping
+from typing import Any, TypeVar
+
+from attrs import define as _attrs_define
+from attrs import field as _attrs_field
+
+T = TypeVar("T", bound="InferenceToolChoiceType1Function")
+
+
+@_attrs_define
+class InferenceToolChoiceType1Function:
+    """
+    Attributes:
+        name (str): The name of the function to call
+    """
+
+    name: str
+    additional_properties: dict[str, Any] = _attrs_field(init=False, factory=dict)
+
+    def to_dict(self) -> dict[str, Any]:
+        name = self.name
+
+        field_dict: dict[str, Any] = {}
+        field_dict.update(self.additional_properties)
+        field_dict.update(
+            {
+                "name": name,
+            }
+        )
+
+        return field_dict
+
+    @classmethod
+    def from_dict(cls: type[T], src_dict: Mapping[str, Any]) -> T:
+        d = dict(src_dict)
+        name = d.pop("name")
+
+        inference_tool_choice_type_1_function = cls(
+            name=name,
+        )
+
+        inference_tool_choice_type_1_function.additional_properties = d
+        return inference_tool_choice_type_1_function
+
+    @property
+    def additional_keys(self) -> list[str]:
+        return list(self.additional_properties.keys())
+
+    def __getitem__(self, key: str) -> Any:
+        return self.additional_properties[key]
+
+    def __setitem__(self, key: str, value: Any) -> None:
+        self.additional_properties[key] = value
+
+    def __delitem__(self, key: str) -> None:
+        del self.additional_properties[key]
+
+    def __contains__(self, key: str) -> bool:
+        return key in self.additional_properties

antfly/client_generated/models/inference_tool_choice_type_1_type.py

@@ -0,0 +1,8 @@
+from enum import Enum
+
+
+class InferenceToolChoiceType1Type(str, Enum):
+    FUNCTION = "function"
+
+    def __str__(self) -> str:
+        return str(self.value)

antfly/client_generated/models/inference_tool_type.py

@@ -0,0 +1,8 @@
+from enum import Enum
+
+
+class InferenceToolType(str, Enum):
+    FUNCTION = "function"
+
+    def __str__(self) -> str:
+        return str(self.value)

antfly/client_generated/models/inference_transcribe_object.py

@@ -0,0 +1,89 @@
+from __future__ import annotations
+
+from collections.abc import Mapping
+from typing import Any, TypeVar
+
+from attrs import define as _attrs_define
+from attrs import field as _attrs_field
+
+from ..models.inference_transcribe_object_object import InferenceTranscribeObjectObject
+from ..types import UNSET, Unset
+
+T = TypeVar("T", bound="InferenceTranscribeObject")
+
+
+@_attrs_define
+class InferenceTranscribeObject:
+    """
+    Attributes:
+        object_ (InferenceTranscribeObjectObject):
+        index (int): Input audio index.
+        text (str): Transcribed text from the audio Example: Hello, how are you today?.
+        language (str | Unset): Detected or forced language Example: en.
+    """
+
+    object_: InferenceTranscribeObjectObject
+    index: int
+    text: str
+    language: str | Unset = UNSET
+    additional_properties: dict[str, Any] = _attrs_field(init=False, factory=dict)
+
+    def to_dict(self) -> dict[str, Any]:
+        object_ = self.object_.value
+
+        index = self.index
+
+        text = self.text
+
+        language = self.language
+
+        field_dict: dict[str, Any] = {}
+        field_dict.update(self.additional_properties)
+        field_dict.update(
+            {
+                "object": object_,
+                "index": index,
+                "text": text,
+            }
+        )
+        if language is not UNSET:
+            field_dict["language"] = language
+
+        return field_dict
+
+    @classmethod
+    def from_dict(cls: type[T], src_dict: Mapping[str, Any]) -> T:
+        d = dict(src_dict)
+        object_ = InferenceTranscribeObjectObject(d.pop("object"))
+
+        index = d.pop("index")
+
+        text = d.pop("text")
+
+        language = d.pop("language", UNSET)
+
+        inference_transcribe_object = cls(
+            object_=object_,
+            index=index,
+            text=text,
+            language=language,
+        )
+
+        inference_transcribe_object.additional_properties = d
+        return inference_transcribe_object
+
+    @property
+    def additional_keys(self) -> list[str]:
+        return list(self.additional_properties.keys())
+
+    def __getitem__(self, key: str) -> Any:
+        return self.additional_properties[key]
+
+    def __setitem__(self, key: str, value: Any) -> None:
+        self.additional_properties[key] = value
+
+    def __delitem__(self, key: str) -> None:
+        del self.additional_properties[key]
+
+    def __contains__(self, key: str) -> bool:
+        return key in self.additional_properties

antfly/client_generated/models/inference_transcribe_object_object.py

@@ -0,0 +1,8 @@
+from enum import Enum
+
+
+class InferenceTranscribeObjectObject(str, Enum):
+    TRANSCRIPTION = "transcription"
+
+    def __str__(self) -> str:
+        return str(self.value)

antfly/client_generated/models/inference_transcribe_request.py

@@ -0,0 +1,81 @@
+from __future__ import annotations
+
+from collections.abc import Mapping
+from typing import Any, TypeVar
+
+from attrs import define as _attrs_define
+from attrs import field as _attrs_field
+
+from ..types import UNSET, Unset
+
+T = TypeVar("T", bound="InferenceTranscribeRequest")
+
+
+@_attrs_define
+class InferenceTranscribeRequest:
+    """
+    Attributes:
+        audio (str): Base64-encoded audio data (WAV, MP3, FLAC, etc.)
+        model (str | Unset): Name of transcriber model from models_dir/transcribers/ Example: openai/whisper-tiny.
+        language (str | Unset): Force specific language for transcription (optional, model-dependent) Example: en.
+    """
+
+    audio: str
+    model: str | Unset = UNSET
+    language: str | Unset = UNSET
+    additional_properties: dict[str, Any] = _attrs_field(init=False, factory=dict)
+
+    def to_dict(self) -> dict[str, Any]:
+        audio = self.audio
+
+        model = self.model
+
+        language = self.language
+
+        field_dict: dict[str, Any] = {}
+        field_dict.update(self.additional_properties)
+        field_dict.update(
+            {
+                "audio": audio,
+            }
+        )
+        if model is not UNSET:
+            field_dict["model"] = model
+        if language is not UNSET:
+            field_dict["language"] = language
+
+        return field_dict
+
+    @classmethod
+    def from_dict(cls: type[T], src_dict: Mapping[str, Any]) -> T:
+        d = dict(src_dict)
+        audio = d.pop("audio")
+
+        model = d.pop("model", UNSET)
+
+        language = d.pop("language", UNSET)
+
+        inference_transcribe_request = cls(
+            audio=audio,
+            model=model,
+            language=language,
+        )
+
+        inference_transcribe_request.additional_properties = d
+        return inference_transcribe_request
+
+    @property
+    def additional_keys(self) -> list[str]:
+        return list(self.additional_properties.keys())
+
+    def __getitem__(self, key: str) -> Any:
+        return self.additional_properties[key]
+
+    def __setitem__(self, key: str, value: Any) -> None:
+        self.additional_properties[key] = value
+
+    def __delitem__(self, key: str) -> None:
+        del self.additional_properties[key]
+
+    def __contains__(self, key: str) -> bool:
+        return key in self.additional_properties

antfly/client_generated/models/inference_transcribe_response.py

@@ -0,0 +1,103 @@
+from __future__ import annotations
+
+from collections.abc import Mapping
+from typing import TYPE_CHECKING, Any, TypeVar
+
+from attrs import define as _attrs_define
+from attrs import field as _attrs_field
+
+from ..models.inference_transcribe_response_object import InferenceTranscribeResponseObject
+
+if TYPE_CHECKING:
+    from ..models.inference_generate_usage import InferenceGenerateUsage
+    from ..models.inference_transcribe_object import InferenceTranscribeObject
+
+
+T = TypeVar("T", bound="InferenceTranscribeResponse")
+
+
+@_attrs_define
+class InferenceTranscribeResponse:
+    """
+    Attributes:
+        object_ (InferenceTranscribeResponseObject): Object type, always "list"
+        data (list[InferenceTranscribeObject]): Transcription result objects.
+        model (str): Name of model used for transcription
+        usage (InferenceGenerateUsage):
+    """
+
+    object_: InferenceTranscribeResponseObject
+    data: list[InferenceTranscribeObject]
+    model: str
+    usage: InferenceGenerateUsage
+    additional_properties: dict[str, Any] = _attrs_field(init=False, factory=dict)
+
+    def to_dict(self) -> dict[str, Any]:
+        object_ = self.object_.value
+
+        data = []
+        for data_item_data in self.data:
+            data_item = data_item_data.to_dict()
+            data.append(data_item)
+
+        model = self.model
+
+        usage = self.usage.to_dict()
+
+        field_dict: dict[str, Any] = {}
+        field_dict.update(self.additional_properties)
+        field_dict.update(
+            {
+                "object": object_,
+                "data": data,
+                "model": model,
+                "usage": usage,
+            }
+        )
+
+        return field_dict
+
+    @classmethod
+    def from_dict(cls: type[T], src_dict: Mapping[str, Any]) -> T:
+        from ..models.inference_generate_usage import InferenceGenerateUsage
+        from ..models.inference_transcribe_object import InferenceTranscribeObject
+
+        d = dict(src_dict)
+        object_ = InferenceTranscribeResponseObject(d.pop("object"))
+
+        data = []
+        _data = d.pop("data")
+        for data_item_data in _data:
+            data_item = InferenceTranscribeObject.from_dict(data_item_data)
+
+            data.append(data_item)
+
+        model = d.pop("model")
+
+        usage = InferenceGenerateUsage.from_dict(d.pop("usage"))
+
+        inference_transcribe_response = cls(
+            object_=object_,
+            data=data,
+            model=model,
+            usage=usage,
+        )
+
+        inference_transcribe_response.additional_properties = d
+        return inference_transcribe_response
+
+    @property
+    def additional_keys(self) -> list[str]:
+        return list(self.additional_properties.keys())
+
+    def __getitem__(self, key: str) -> Any:
+        return self.additional_properties[key]
+
+    def __setitem__(self, key: str, value: Any) -> None:
+        self.additional_properties[key] = value
+
+    def __delitem__(self, key: str) -> None:
+        del self.additional_properties[key]
+
+    def __contains__(self, key: str) -> bool:
+        return key in self.additional_properties

antfly/client_generated/models/inference_transcribe_response_object.py

@@ -0,0 +1,8 @@
+from enum import Enum
+
+
+class InferenceTranscribeResponseObject(str, Enum):
+    LIST = "list"
+
+    def __str__(self) -> str:
+        return str(self.value)

antfly/client_generated/models/inference_vad_options.py

@@ -0,0 +1,92 @@
+from __future__ import annotations
+
+from collections.abc import Mapping
+from typing import Any, TypeVar
+
+from attrs import define as _attrs_define
+from attrs import field as _attrs_field
+
+from ..types import UNSET, Unset
+
+T = TypeVar("T", bound="InferenceVADOptions")
+
+
+@_attrs_define
+class InferenceVADOptions:
+    """Options for Voice Activity Detection (VAD) based audio segmentation. inference-specific.
+
+    Attributes:
+        min_silence_duration_ms (int | Unset): Minimum silence duration (ms) to split speech segments. Gaps shorter than
+            this are merged. Higher values produce longer, fewer segments. Default: 300.
+        min_speech_duration_ms (int | Unset): Minimum speech duration (ms) for a segment to be kept. Shorter segments
+            are discarded. Default: 250.
+        speech_pad_ms (int | Unset): Padding (ms) added before and after detected speech. Default: 30.
+        max_segment_duration_ms (int | Unset): Maximum segment duration (ms). Segments longer than this are split.
+            Useful for Whisper-compatible chunking. Default: 30000.
+    """
+
+    min_silence_duration_ms: int | Unset = UNSET
+    min_speech_duration_ms: int | Unset = UNSET
+    speech_pad_ms: int | Unset = UNSET
+    max_segment_duration_ms: int | Unset = UNSET
+    additional_properties: dict[str, Any] = _attrs_field(init=False, factory=dict)
+
+    def to_dict(self) -> dict[str, Any]:
+        min_silence_duration_ms = self.min_silence_duration_ms
+
+        min_speech_duration_ms = self.min_speech_duration_ms
+
+        speech_pad_ms = self.speech_pad_ms
+
+        max_segment_duration_ms = self.max_segment_duration_ms
+
+        field_dict: dict[str, Any] = {}
+        field_dict.update(self.additional_properties)
+        field_dict.update({})
+        if min_silence_duration_ms is not UNSET:
+            field_dict["min_silence_duration_ms"] = min_silence_duration_ms
+        if min_speech_duration_ms is not UNSET:
+            field_dict["min_speech_duration_ms"] = min_speech_duration_ms
+        if speech_pad_ms is not UNSET:
+            field_dict["speech_pad_ms"] = speech_pad_ms
+        if max_segment_duration_ms is not UNSET:
+            field_dict["max_segment_duration_ms"] = max_segment_duration_ms
+
+        return field_dict
+
+    @classmethod
+    def from_dict(cls: type[T], src_dict: Mapping[str, Any]) -> T:
+        d = dict(src_dict)
+        min_silence_duration_ms = d.pop("min_silence_duration_ms", UNSET)
+
+        min_speech_duration_ms = d.pop("min_speech_duration_ms", UNSET)
+
+        speech_pad_ms = d.pop("speech_pad_ms", UNSET)
+
+        max_segment_duration_ms = d.pop("max_segment_duration_ms", UNSET)
+
+        inference_vad_options = cls(
+            min_silence_duration_ms=min_silence_duration_ms,
+            min_speech_duration_ms=min_speech_duration_ms,
+            speech_pad_ms=speech_pad_ms,
+            max_segment_duration_ms=max_segment_duration_ms,
+        )
+
+        inference_vad_options.additional_properties = d
+        return inference_vad_options
+
+    @property
+    def additional_keys(self) -> list[str]:
+        return list(self.additional_properties.keys())
+
+    def __getitem__(self, key: str) -> Any:
+        return self.additional_properties[key]
+
+    def __setitem__(self, key: str, value: Any) -> None:
+        self.additional_properties[key] = value
+
+    def __delitem__(self, key: str) -> None:
+        del self.additional_properties[key]
+
+    def __contains__(self, key: str) -> bool:
+        return key in self.additional_properties