livekit-plugins-aws 1.0.0.dev5__py3-none-any.whl → 1.0.0rc1__py3-none-any.whl

livekit/plugins/aws/llm.py

@@ -80,16 +80,16 @@ class LLM(llm.LLM):
             top_p (float, optional): The nucleus sampling probability for response generation. Defaults to None.
             tool_choice (ToolChoice or Literal["auto", "required", "none"], optional): Specifies whether to use tools during response generation. Defaults to "auto".
             additional_request_fields (dict[str, Any], optional): Additional request fields to send to the AWS Bedrock Converse API. Defaults to None.
-        """
+        """  # noqa: E501
         super().__init__()
         self._api_key, self._api_secret, self._region = get_aws_credentials(
             api_key, api_secret, region
         )
 
-        model = model or os.environ.get("BEDROCK_INFERENCE_PROFILE_ARN")
-        if not is_given(model):
+        model = model if is_given(model) else os.environ.get("BEDROCK_INFERENCE_PROFILE_ARN")
+        if not model:
             raise ValueError(
-                "model or inference profile arn must be set using the argument or by setting the BEDROCK_INFERENCE_PROFILE_ARN environment variable."
+                "model or inference profile arn must be set using the argument or by setting the BEDROCK_INFERENCE_PROFILE_ARN environment variable."  # noqa: E501
             )
         self._opts = _LLMOptions(
             model=model,

livekit/plugins/aws/stt.py

@@ -20,6 +20,8 @@ from amazon_transcribe.model import Result, TranscriptEvent
 
 from livekit import rtc
 from livekit.agents import DEFAULT_API_CONNECT_OPTIONS, APIConnectOptions, stt, utils
+from livekit.agents.types import NOT_GIVEN, NotGivenOr
+from livekit.agents.utils import is_given
 
 from .log import logger
 from .utils import get_aws_credentials
@@ -31,16 +33,16 @@ class STTOptions:
     sample_rate: int
     language: str
     encoding: str
-    vocabulary_name: str | None
-    session_id: str | None
-    vocab_filter_method: str | None
-    vocab_filter_name: str | None
-    show_speaker_label: bool | None
-    enable_channel_identification: bool | None
-    number_of_channels: int | None
-    enable_partial_results_stabilization: bool | None
-    partial_results_stability: str | None
-    language_model_name: str | None
+    vocabulary_name: NotGivenOr[str]
+    session_id: NotGivenOr[str]
+    vocab_filter_method: NotGivenOr[str]
+    vocab_filter_name: NotGivenOr[str]
+    show_speaker_label: NotGivenOr[bool]
+    enable_channel_identification: NotGivenOr[bool]
+    number_of_channels: NotGivenOr[int]
+    enable_partial_results_stabilization: NotGivenOr[bool]
+    partial_results_stability: NotGivenOr[str]
+    language_model_name: NotGivenOr[str]
 
 
 class STT(stt.STT):
@@ -48,21 +50,21 @@ class STT(stt.STT):
         self,
         *,
         speech_region: str = "us-east-1",
-        api_key: str | None = None,
-        api_secret: str | None = None,
+        api_key: NotGivenOr[str] = NOT_GIVEN,
+        api_secret: NotGivenOr[str] = NOT_GIVEN,
         sample_rate: int = 48000,
         language: str = "en-US",
         encoding: str = "pcm",
-        vocabulary_name: str | None = None,
-        session_id: str | None = None,
-        vocab_filter_method: str | None = None,
-        vocab_filter_name: str | None = None,
-        show_speaker_label: bool | None = None,
-        enable_channel_identification: bool | None = None,
-        number_of_channels: int | None = None,
-        enable_partial_results_stabilization: bool | None = None,
-        partial_results_stability: str | None = None,
-        language_model_name: str | None = None,
+        vocabulary_name: NotGivenOr[str] = NOT_GIVEN,
+        session_id: NotGivenOr[str] = NOT_GIVEN,
+        vocab_filter_method: NotGivenOr[str] = NOT_GIVEN,
+        vocab_filter_name: NotGivenOr[str] = NOT_GIVEN,
+        show_speaker_label: NotGivenOr[bool] = NOT_GIVEN,
+        enable_channel_identification: NotGivenOr[bool] = NOT_GIVEN,
+        number_of_channels: NotGivenOr[int] = NOT_GIVEN,
+        enable_partial_results_stabilization: NotGivenOr[bool] = NOT_GIVEN,
+        partial_results_stability: NotGivenOr[str] = NOT_GIVEN,
+        language_model_name: NotGivenOr[str] = NOT_GIVEN,
     ):
         super().__init__(capabilities=stt.STTCapabilities(streaming=True, interim_results=True))
 
@@ -90,7 +92,7 @@ class STT(stt.STT):
         self,
         buffer: utils.AudioBuffer,
         *,
-        language: str | None,
+        language: NotGivenOr[str] = NOT_GIVEN,
         conn_options: APIConnectOptions,
     ) -> stt.SpeechEvent:
         raise NotImplementedError("Amazon Transcribe does not support single frame recognition")
@@ -98,7 +100,7 @@ class STT(stt.STT):
     def stream(
         self,
         *,
-        language: str | None = None,
+        language: NotGivenOr[str] = NOT_GIVEN,
         conn_options: APIConnectOptions = DEFAULT_API_CONNECT_OPTIONS,
     ) -> SpeechStream:
         return SpeechStream(
@@ -120,21 +122,23 @@ class SpeechStream(stt.SpeechStream):
         self._client = TranscribeStreamingClient(region=self._opts.speech_region)
 
     async def _run(self) -> None:
-        stream = await self._client.start_stream_transcription(
-            language_code=self._opts.language,
-            media_sample_rate_hz=self._opts.sample_rate,
-            media_encoding=self._opts.encoding,
-            vocabulary_name=self._opts.vocabulary_name,
-            session_id=self._opts.session_id,
-            vocab_filter_method=self._opts.vocab_filter_method,
-            vocab_filter_name=self._opts.vocab_filter_name,
-            show_speaker_label=self._opts.show_speaker_label,
-            enable_channel_identification=self._opts.enable_channel_identification,
-            number_of_channels=self._opts.number_of_channels,
-            enable_partial_results_stabilization=self._opts.enable_partial_results_stabilization,
-            partial_results_stability=self._opts.partial_results_stability,
-            language_model_name=self._opts.language_model_name,
-        )
+        live_config = {
+            "language_code": self._opts.language,
+            "media_sample_rate_hz": self._opts.sample_rate,
+            "media_encoding": self._opts.encoding,
+            "vocabulary_name": self._opts.vocabulary_name,
+            "session_id": self._opts.session_id,
+            "vocab_filter_method": self._opts.vocab_filter_method,
+            "vocab_filter_name": self._opts.vocab_filter_name,
+            "show_speaker_label": self._opts.show_speaker_label,
+            "enable_channel_identification": self._opts.enable_channel_identification,
+            "number_of_channels": self._opts.number_of_channels,
+            "enable_partial_results_stabilization": self._opts.enable_partial_results_stabilization,
+            "partial_results_stability": self._opts.partial_results_stability,
+            "language_model_name": self._opts.language_model_name,
+        }
+        filtered_config = {k: v for k, v in live_config.items() if is_given(v)}
+        stream = await self._client.start_stream_transcription(**filtered_config)
 
         @utils.log_exceptions(logger=logger)
         async def input_generator():

livekit/plugins/aws/tts.py

@@ -27,9 +27,15 @@ from livekit.agents import (
     tts,
     utils,
 )
+from livekit.agents.types import (
+    DEFAULT_API_CONNECT_OPTIONS,
+    NOT_GIVEN,
+    NotGivenOr,
+)
+from livekit.agents.utils import is_given
 
 from .models import TTS_LANGUAGE, TTS_SPEECH_ENGINE
-from .utils import get_aws_credentials
+from .utils import _strip_nones, get_aws_credentials
 
 TTS_NUM_CHANNELS: int = 1
 DEFAULT_SPEECH_ENGINE: TTS_SPEECH_ENGINE = "generative"
@@ -41,24 +47,24 @@ DEFAULT_SAMPLE_RATE = 16000
 @dataclass
 class _TTSOptions:
     # https://docs.aws.amazon.com/polly/latest/dg/API_SynthesizeSpeech.html
-    voice: str | None
-    speech_engine: TTS_SPEECH_ENGINE
+    voice: NotGivenOr[str]
+    speech_engine: NotGivenOr[TTS_SPEECH_ENGINE]
     speech_region: str
     sample_rate: int
-    language: TTS_LANGUAGE | str | None
+    language: NotGivenOr[TTS_LANGUAGE | str]
 
 
 class TTS(tts.TTS):
     def __init__(
         self,
         *,
-        voice: str | None = DEFAULT_VOICE,
-        language: TTS_LANGUAGE | str | None = None,
-        speech_engine: TTS_SPEECH_ENGINE = DEFAULT_SPEECH_ENGINE,
+        voice: NotGivenOr[str] = NOT_GIVEN,
+        language: NotGivenOr[TTS_LANGUAGE | str] = NOT_GIVEN,
+        speech_engine: NotGivenOr[TTS_SPEECH_ENGINE] = NOT_GIVEN,
         sample_rate: int = DEFAULT_SAMPLE_RATE,
-        speech_region: str = DEFAULT_SPEECH_REGION,
-        api_key: str | None = None,
-        api_secret: str | None = None,
+        speech_region: NotGivenOr[str] = DEFAULT_SPEECH_REGION,
+        api_key: NotGivenOr[str] = NOT_GIVEN,
+        api_secret: NotGivenOr[str] = NOT_GIVEN,
         session: AioSession | None = None,
     ) -> None:
         """
@@ -77,7 +83,7 @@ class TTS(tts.TTS):
             speech_region(str, optional): The region to use for the synthesis. Defaults to "us-east-1".
             api_key(str, optional): AWS access key id.
             api_secret(str, optional): AWS secret access key.
-        """
+        """  # noqa: E501
         super().__init__(
             capabilities=tts.TTSCapabilities(
                 streaming=False,
@@ -111,7 +117,7 @@ class TTS(tts.TTS):
         self,
         text: str,
         *,
-        conn_options: APIConnectOptions | None = None,
+        conn_options: APIConnectOptions = DEFAULT_API_CONNECT_OPTIONS,
     ) -> ChunkedStream:
         return ChunkedStream(
             tts=self,
@@ -128,7 +134,7 @@ class ChunkedStream(tts.ChunkedStream):
         *,
         tts: TTS,
         text: str,
-        conn_options: APIConnectOptions | None = None,
+        conn_options: APIConnectOptions = DEFAULT_API_CONNECT_OPTIONS,
         opts: _TTSOptions,
         get_client: Callable[[], Any],
     ) -> None:
@@ -145,11 +151,13 @@ class ChunkedStream(tts.ChunkedStream):
                 params = {
                     "Text": self._input_text,
                     "OutputFormat": "mp3",
-                    "Engine": self._opts.speech_engine,
-                    "VoiceId": self._opts.voice,
+                    "Engine": self._opts.speech_engine
+                    if is_given(self._opts.speech_engine)
+                    else DEFAULT_SPEECH_ENGINE,
+                    "VoiceId": self._opts.voice if is_given(self._opts.voice) else DEFAULT_VOICE,
                     "TextType": "text",
                     "SampleRate": str(self._opts.sample_rate),
-                    "LanguageCode": self._opts.language,
+                    "LanguageCode": self._opts.language if is_given(self._opts.language) else None,
                 }
                 response = await client.synthesize_speech(**_strip_nones(params))
                 if "AudioStream" in response:
@@ -195,7 +203,3 @@ class ChunkedStream(tts.ChunkedStream):
             ) from e
         except Exception as e:
             raise APIConnectionError() from e
-
-
-def _strip_nones(d: dict[str, Any]) -> dict[str, Any]:
-    return {k: v for k, v in d.items() if v is not None}

livekit/plugins/aws/utils.py

@@ -8,25 +8,31 @@ import boto3
 
 from livekit.agents import llm
 from livekit.agents.llm import ChatContext, FunctionTool, ImageContent, utils
+from livekit.agents.types import NotGivenOr
+from livekit.agents.utils import is_given
 
 __all__ = ["to_fnc_ctx", "to_chat_ctx", "get_aws_credentials"]
 
 
-def get_aws_credentials(api_key: str | None, api_secret: str | None, region: str | None):
-    region = region or os.environ.get("AWS_DEFAULT_REGION")
-    if not region:
+def get_aws_credentials(
+    api_key: NotGivenOr[str],
+    api_secret: NotGivenOr[str],
+    region: NotGivenOr[str],
+):
+    aws_region = region if is_given(region) else os.environ.get("AWS_DEFAULT_REGION")
+    if not aws_region:
         raise ValueError(
-            "AWS_DEFAULT_REGION must be set via argument or the AWS_DEFAULT_REGION environment variable."
+            "AWS_DEFAULT_REGION must be set via argument or the AWS_DEFAULT_REGION environment variable."  # noqa: E501
         )
 
-    if api_key and api_secret:
+    if is_given(api_key) and is_given(api_secret):
         session = boto3.Session(
             aws_access_key_id=api_key,
             aws_secret_access_key=api_secret,
-            region_name=region,
+            region_name=aws_region,
         )
     else:
-        session = boto3.Session(region_name=region)
+        session = boto3.Session(region_name=aws_region)
 
     credentials = session.get_credentials()
     if not credentials or not credentials.access_key or not credentials.secret_key:

livekit/plugins/aws/version.py

@@ -12,4 +12,4 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = "1.0.0.dev5"
+__version__ = '1.0.0.rc1'

{livekit_plugins_aws-1.0.0.dev5.dist-info → livekit_plugins_aws-1.0.0rc1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: livekit-plugins-aws
-Version: 1.0.0.dev5
+Version: 1.0.0rc1
 Summary: LiveKit Agents Plugin for services from AWS
 Project-URL: Documentation, https://docs.livekit.io
 Project-URL: Website, https://livekit.io/
@@ -21,7 +21,7 @@ Requires-Python: >=3.9.0
 Requires-Dist: aiobotocore==2.19.0
 Requires-Dist: amazon-transcribe>=0.6.2
 Requires-Dist: boto3==1.36.3
-Requires-Dist: livekit-agents>=1.0.0.dev5
+Requires-Dist: livekit-agents>=1.0.0.rc1
 Description-Content-Type: text/markdown
 
 # LiveKit Plugins AWS

livekit_plugins_aws-1.0.0rc1.dist-info/RECORD

@@ -0,0 +1,12 @@
+livekit/plugins/aws/__init__.py,sha256=Ea-hK7QdutnwdZvvs9K2fiR8RWJqz2JcONxXnV1kXF0,977
+livekit/plugins/aws/llm.py,sha256=2wdIZhjume5ukSkNHe3L1QLhBN6MyrtNuxHefEUM104,11050
+livekit/plugins/aws/log.py,sha256=jFief0Xhv0n_F6sp6UFu9VKxs2bXNVGAfYGmEYfR_2Q,66
+livekit/plugins/aws/models.py,sha256=Nf8RFmDulW7h03dG2lERTog3mgDK0TbLvW0eGOncuEE,704
+livekit/plugins/aws/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+livekit/plugins/aws/stt.py,sha256=j2vEsoixFcsyTbCNhW5EWea5CEv3K-DzL9wmweebf3o,8030
+livekit/plugins/aws/tts.py,sha256=4EOI4VabvhjCcDyp_QoDhlXOdrMrKpnmNIDTeoJ8kcU,7601
+livekit/plugins/aws/utils.py,sha256=AiLzvztT635oF_DW4LQiKAL5wq_2nwBL6zBnyvdKB90,4978
+livekit/plugins/aws/version.py,sha256=pF0lh6G9GYL7Mj7EnfhjFifzlzdWx6u3RvB0Itch4UE,604
+livekit_plugins_aws-1.0.0rc1.dist-info/METADATA,sha256=BK464NnvrztaIc7bJFOwxGRjhBZec7BMFIhbL6y-6B8,1485
+livekit_plugins_aws-1.0.0rc1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+livekit_plugins_aws-1.0.0rc1.dist-info/RECORD,,

livekit_plugins_aws-1.0.0.dev5.dist-info/RECORD

@@ -1,12 +0,0 @@
-livekit/plugins/aws/__init__.py,sha256=Ea-hK7QdutnwdZvvs9K2fiR8RWJqz2JcONxXnV1kXF0,977
-livekit/plugins/aws/llm.py,sha256=Mc910AREP7-FX1yEV1k_rViue_30Gy8qmp42VDAptSE,11011
-livekit/plugins/aws/log.py,sha256=jFief0Xhv0n_F6sp6UFu9VKxs2bXNVGAfYGmEYfR_2Q,66
-livekit/plugins/aws/models.py,sha256=Nf8RFmDulW7h03dG2lERTog3mgDK0TbLvW0eGOncuEE,704
-livekit/plugins/aws/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-livekit/plugins/aws/stt.py,sha256=hRulbbMXtYqYPuqo359ARWE0fYDy1PzMdpT-h2m1UsY,7575
-livekit/plugins/aws/tts.py,sha256=WA-KtEVF8dq4GZEbPWdY3azdHZRiHFyptesx7kh6Tio,7250
-livekit/plugins/aws/utils.py,sha256=Q62NpoJs3bLerMBlhW22L9xiZHgmtxK3-js7KbL0bkQ,4790
-livekit/plugins/aws/version.py,sha256=pXgCpV03nQI-5Kk-74NFyAdw1htj2cx6unwQHipEcfE,605
-livekit_plugins_aws-1.0.0.dev5.dist-info/METADATA,sha256=P10ho20uMHMcEW2xywzbYwXvPqego-Yv3EvpWLXsSCs,1488
-livekit_plugins_aws-1.0.0.dev5.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-livekit_plugins_aws-1.0.0.dev5.dist-info/RECORD,,