dashscope 1.24.4__py3-none-any.whl → 1.24.5__py3-none-any.whl

dashscope/__init__.py

@@ -24,7 +24,7 @@ from dashscope.embeddings.batch_text_embedding_response import \
     BatchTextEmbeddingResponse
 from dashscope.embeddings.multimodal_embedding import (
     MultiModalEmbedding, MultiModalEmbeddingItemAudio,
-    MultiModalEmbeddingItemImage, MultiModalEmbeddingItemText)
+    MultiModalEmbeddingItemImage, MultiModalEmbeddingItemText, AioMultiModalEmbedding)
 from dashscope.embeddings.text_embedding import TextEmbedding
 from dashscope.files import Files
 from dashscope.models import Models
@@ -55,6 +55,7 @@ __all__ = [
     Models,
     TextEmbedding,
     MultiModalEmbedding,
+    AioMultiModalEmbedding,
     MultiModalEmbeddingItemAudio,
     MultiModalEmbeddingItemImage,
     MultiModalEmbeddingItemText,

dashscope/aigc/__init__.py

@@ -1,18 +1,20 @@
 # Copyright (c) Alibaba, Inc. and its affiliates.
-
 from .conversation import Conversation, History, HistoryItem
-from .generation import Generation
-from .image_synthesis import ImageSynthesis
+from .generation import Generation, AioGeneration
+from .image_synthesis import ImageSynthesis, AioImageSynthesis
 from .multimodal_conversation import MultiModalConversation, AioMultiModalConversation
-from .video_synthesis import VideoSynthesis
+from .video_synthesis import VideoSynthesis, AioVideoSynthesis
 
 __all__ = [
     Generation,
+    AioGeneration,
     Conversation,
     HistoryItem,
     History,
     ImageSynthesis,
+    AioImageSynthesis,
     MultiModalConversation,
     AioMultiModalConversation,
     VideoSynthesis,
+    AioVideoSynthesis,
 ]

dashscope/aigc/multimodal_conversation.py

@@ -24,9 +24,10 @@ class MultiModalConversation(BaseApi):
     def call(
         cls,
         model: str,
-        messages: List,
+        messages: List = None,
         api_key: str = None,
         workspace: str = None,
+        text: str = None,
         **kwargs
     ) -> Union[MultiModalConversationResponse, Generator[
             MultiModalConversationResponse, None, None]]:
@@ -55,6 +56,7 @@ class MultiModalConversation(BaseApi):
                 if None, will retrieve by rule [1].
                 [1]: https://help.aliyun.com/zh/dashscope/developer-reference/api-key-settings. # noqa E501
             workspace (str): The dashscope workspace id.
+            text (str): The text to generate.
             **kwargs:
                 stream(bool, `optional`): Enable server-sent events
                     (ref: https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events)  # noqa E501
@@ -68,8 +70,11 @@ class MultiModalConversation(BaseApi):
                     tokens with top_p probability mass. So 0.1 means only
                     the tokens comprising the top 10% probability mass are
                     considered[qwen-turbo,bailian-v1].
+                voice(string, `optional`): The voice name of qwen tts, include 'Cherry'/'Ethan'/'Sunny'/'Dylan' and so on,
+                    you can get the total voice list : https://help.aliyun.com/zh/model-studio/qwen-tts.
                 top_k(float, `optional`):
 
+
         Raises:
             InvalidInput: The history and auto_history are mutually exclusive.
 
@@ -78,18 +83,24 @@ class MultiModalConversation(BaseApi):
                   Generator[MultiModalConversationResponse, None, None]]: If
             stream is True, return Generator, otherwise MultiModalConversationResponse.
         """
-        if (messages is None or not messages):
-            raise InputRequired('prompt or messages is required!')
         if model is None or not model:
             raise ModelRequired('Model is required!')
         task_group, _ = _get_task_group_and_task(__name__)
-        msg_copy = copy.deepcopy(messages)
-        has_upload = cls._preprocess_messages(model, msg_copy, api_key)
-        if has_upload:
-            headers = kwargs.pop('headers', {})
-            headers['X-DashScope-OssResourceResolve'] = 'enable'
-            kwargs['headers'] = headers
-        input = {'messages': msg_copy}
+        input = {}
+        msg_copy = None
+
+        if messages is not None and messages:
+            msg_copy = copy.deepcopy(messages)
+            has_upload = cls._preprocess_messages(model, msg_copy, api_key)
+            if has_upload:
+                headers = kwargs.pop('headers', {})
+                headers['X-DashScope-OssResourceResolve'] = 'enable'
+                kwargs['headers'] = headers
+
+        if text is not None and text:
+            input.update({'text': text})
+        if msg_copy is not None:
+            input.update({'messages': msg_copy})
         response = super().call(model=model,
                                 task_group=task_group,
                                 task=MultiModalConversation.task,
@@ -145,9 +156,10 @@ class AioMultiModalConversation(BaseAioApi):
     async def call(
         cls,
         model: str,
-        messages: List,
+        messages: List = None,
         api_key: str = None,
         workspace: str = None,
+        text: str = None,
         **kwargs
     ) -> Union[MultiModalConversationResponse, Generator[
             MultiModalConversationResponse, None, None]]:
@@ -176,6 +188,7 @@ class AioMultiModalConversation(BaseAioApi):
                 if None, will retrieve by rule [1].
                 [1]: https://help.aliyun.com/zh/dashscope/developer-reference/api-key-settings. # noqa E501
             workspace (str): The dashscope workspace id.
+            text (str): The text to generate.
             **kwargs:
                 stream(bool, `optional`): Enable server-sent events
                     (ref: https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events)  # noqa E501
@@ -189,6 +202,8 @@ class AioMultiModalConversation(BaseAioApi):
                     tokens with top_p probability mass. So 0.1 means only
                     the tokens comprising the top 10% probability mass are
                     considered[qwen-turbo,bailian-v1].
+                voice(string, `optional`): The voice name of qwen tts, include 'Cherry'/'Ethan'/'Sunny'/'Dylan' and so on,
+                    you can get the total voice list : https://help.aliyun.com/zh/model-studio/qwen-tts.
                 top_k(float, `optional`):
 
         Raises:
@@ -199,18 +214,24 @@ class AioMultiModalConversation(BaseAioApi):
                   Generator[MultiModalConversationResponse, None, None]]: If
             stream is True, return Generator, otherwise MultiModalConversationResponse.
         """
-        if (messages is None or not messages):
-            raise InputRequired('prompt or messages is required!')
         if model is None or not model:
             raise ModelRequired('Model is required!')
         task_group, _ = _get_task_group_and_task(__name__)
-        msg_copy = copy.deepcopy(messages)
-        has_upload = cls._preprocess_messages(model, msg_copy, api_key)
-        if has_upload:
-            headers = kwargs.pop('headers', {})
-            headers['X-DashScope-OssResourceResolve'] = 'enable'
-            kwargs['headers'] = headers
-        input = {'messages': msg_copy}
+        input = {}
+        msg_copy = None
+
+        if messages is not None and messages:
+            msg_copy = copy.deepcopy(messages)
+            has_upload = cls._preprocess_messages(model, msg_copy, api_key)
+            if has_upload:
+                headers = kwargs.pop('headers', {})
+                headers['X-DashScope-OssResourceResolve'] = 'enable'
+                kwargs['headers'] = headers
+
+        if text is not None and text:
+            input.update({'text': text})
+        if msg_copy is not None:
+            input.update({'messages': msg_copy})
         response = await super().call(model=model,
                                       task_group=task_group,
                                       task=AioMultiModalConversation.task,

dashscope/api_entities/dashscope_response.py

@@ -152,6 +152,26 @@ class Choice(DictMixin):
                          **kwargs)
 
 
+@dataclass(init=False)
+class Audio(DictMixin):
+    data: str
+    url: str
+    id: str
+    expires_at: int
+
+    def __init__(self,
+                 data: str = None,
+                 url: str = None,
+                 id: str = None,
+                 expires_at: int = None,
+                 **kwargs):
+        super().__init__(data=data,
+                         url=url,
+                         id=id,
+                         expires_at=expires_at,
+                         **kwargs)
+
+
 @dataclass(init=False)
 class GenerationOutput(DictMixin):
     text: str
@@ -217,20 +237,25 @@ class GenerationResponse(DashScopeAPIResponse):
 @dataclass(init=False)
 class MultiModalConversationOutput(DictMixin):
     choices: List[Choice]
+    audio: Audio
 
     def __init__(self,
                  text: str = None,
                  finish_reason: str = None,
                  choices: List[Choice] = None,
+                 audio: Audio = None,
                  **kwargs):
         chs = None
         if choices is not None:
             chs = []
             for choice in choices:
                 chs.append(Choice(**choice))
+        if audio is not None:
+            audio = Audio(**audio)
         super().__init__(text=text,
                          finish_reason=finish_reason,
                          choices=chs,
+                         audio=audio,
                          **kwargs)
 
 
@@ -238,15 +263,18 @@ class MultiModalConversationOutput(DictMixin):
 class MultiModalConversationUsage(DictMixin):
     input_tokens: int
     output_tokens: int
+    characters: int
 
     # TODO add image usage info.
 
     def __init__(self,
                  input_tokens: int = 0,
                  output_tokens: int = 0,
+                 characters: int = 0,
                  **kwargs):
         super().__init__(input_tokens=input_tokens,
                          output_tokens=output_tokens,
+                         characters=characters,
                          **kwargs)
 
 
@@ -378,7 +406,7 @@ class RecognitionResponse(DashScopeAPIResponse):
         """
         result = False
         if sentence is not None and 'end_time' in sentence and sentence[
-                'end_time'] is not None:
+            'end_time'] is not None:
             result = True
         return result
 
@@ -445,8 +473,8 @@ class ImageSynthesisOutput(DictMixin):
     results: List[ImageSynthesisResult]
 
     def __init__(self,
-                 task_id: str =  None,
-                 task_status: str =  None,
+                 task_id: str = None,
+                 task_status: str = None,
                  results: List[ImageSynthesisResult] = [],
                  **kwargs):
         res = []

dashscope/embeddings/multimodal_embedding.py

@@ -5,7 +5,7 @@ from typing import List
 
 from dashscope.api_entities.dashscope_response import (DashScopeAPIResponse,
                                                        DictMixin)
-from dashscope.client.base_api import BaseApi
+from dashscope.client.base_api import BaseApi, BaseAioApi
 from dashscope.common.error import InputRequired, ModelRequired
 from dashscope.common.utils import _get_task_group_and_task
 from dashscope.utils.oss_utils import preprocess_message_element
@@ -111,3 +111,72 @@ class MultiModalEmbedding(BaseApi):
                 if is_upload and not has_upload:
                     has_upload = True
         return has_upload
+
+
+class AioMultiModalEmbedding(BaseAioApi):
+    task = 'multimodal-embedding'
+
+    class Models:
+        multimodal_embedding_one_peace_v1 = 'multimodal-embedding-one-peace-v1'
+
+    @classmethod
+    async def call(cls,
+         model: str,
+         input: List[MultiModalEmbeddingItemBase],
+         api_key: str = None,
+         workspace: str = None,
+         **kwargs) -> DashScopeAPIResponse:
+        """Get embedding multimodal contents..
+
+        Args:
+            model (str): The embedding model name.
+            input (List[MultiModalEmbeddingElement]): The embedding elements,
+                every element include data, modal, factor field.
+            workspace (str): The dashscope workspace id.
+            **kwargs:
+                auto_truncation(bool, `optional`): Automatically truncate
+                audio longer than 15 seconds or text longer than 70 words.
+                Default to false(Too long input will result in failure).
+
+        Returns:
+            DashScopeAPIResponse: The embedding result.
+        """
+        if input is None or not input:
+            raise InputRequired('prompt is required!')
+        if model is None or not model:
+            raise ModelRequired('Model is required!')
+        embedding_input = {}
+        has_upload = cls._preprocess_message_inputs(model, input, api_key)
+        if has_upload:
+            headers = kwargs.pop('headers', {})
+            headers['X-DashScope-OssResourceResolve'] = 'enable'
+            kwargs['headers'] = headers
+        embedding_input['contents'] = input
+        kwargs.pop('stream', False)  # not support streaming output.
+        task_group, function = _get_task_group_and_task(__name__)
+        response = await super().call(
+            model=model,
+            input=embedding_input,
+            task_group=task_group,
+            task=MultiModalEmbedding.task,
+            function=function,
+            api_key=api_key,
+            workspace=workspace,
+            **kwargs)
+        return response
+
+    @classmethod
+    def _preprocess_message_inputs(cls, model: str, input: List[dict],
+                                   api_key: str):
+        """preprocess following inputs
+        input = [{'factor': 1, 'text': 'hello'},
+                {'factor': 2, 'audio': ''},
+                {'factor': 3, 'image': ''}]
+        """
+        has_upload = False
+        for elem in input:
+            if not isinstance(elem, (int, float, bool, str, bytes, bytearray)):
+                is_upload = preprocess_message_element(model, elem, api_key)
+                if is_upload and not has_upload:
+                    has_upload = True
+        return has_upload

dashscope/version.py

@@ -1,3 +1,3 @@
 # Copyright (c) Alibaba, Inc. and its affiliates.
 
-__version__ = '1.24.4'
+__version__ = '1.24.5'

{dashscope-1.24.4.dist-info → dashscope-1.24.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dashscope
-Version: 1.24.4
+Version: 1.24.5
 Summary: dashscope client sdk library
 Home-page: https://dashscope.aliyun.com/
 Author: Alibaba Cloud

{dashscope-1.24.4.dist-info → dashscope-1.24.5.dist-info}/RECORD

@@ -1,16 +1,16 @@
-dashscope/__init__.py,sha256=MJI4PJmnevfQA_GA30_L3hmsq49hooZpg25k6w39dts,3120
+dashscope/__init__.py,sha256=96J137Im9Ii9uxfVOOYkZDJNZXF1sEbcH4-QXFr4xEw,3172
 dashscope/cli.py,sha256=64oGkevgX0RHPPmMg0sevXDgaFLQNA_0vdtjQ7Z2pHM,26492
 dashscope/files.py,sha256=vRDQygm3lOqBZR73o7KNHs1iTBVuvLncuwJNxIYjzAU,3981
 dashscope/model.py,sha256=B5v_BtYLPqj6raClejBgdKg6WTGwhH_f-20pvsQqmsk,1491
 dashscope/models.py,sha256=dE4mzXkl85G343qVylSGpURPRdA5pZSqXlx6PcxqC_Q,1275
-dashscope/version.py,sha256=-rY4TVBLCGXmd6f3VVXw5GRs4Fvfu8nGa-Yu2KG4ReM,74
-dashscope/aigc/__init__.py,sha256=m51CHEKL3WPq-s14OF-G1Uk3rLj6B6KrU55bbCKU-Ak,500
+dashscope/version.py,sha256=2fvqw7bZLyWOIDvUb8DEkdi6y_VgyljhOeYdITEksWM,74
+dashscope/aigc/__init__.py,sha256=kYvYEoRK-NUHyMWpBDNQBz4fVA__uOhHRK2kDTBaWgk,617
 dashscope/aigc/chat_completion.py,sha256=ONlyyssIbfaKKcFo7cEKhHx5OCF2XX810HFzIExW1ho,14813
 dashscope/aigc/code_generation.py,sha256=p_mxDKJLQMW0IjFD46JRlZuEZCRESSVKEfLlAevBtqw,10936
 dashscope/aigc/conversation.py,sha256=95xEEY4ThZJysj5zy3aMw7ql9KLJVfD_1iHv9QZ17Ew,14282
 dashscope/aigc/generation.py,sha256=xMcMu16rICTdjZiD_sPqYV_Ltdp4ewGzzfC7JD9VApY,17948
 dashscope/aigc/image_synthesis.py,sha256=Itx9h5brEwC-d3Mj_ntDHGd4qaitqDg9DeGHMJouhMk,28178
-dashscope/aigc/multimodal_conversation.py,sha256=Kjg8Gtfhl_Ok8WVwD-AeT-VBN9hh6E74TfkCxkL5wbY,10821
+dashscope/aigc/multimodal_conversation.py,sha256=BXpUthyGxJHQs18-m_ZzAw6MI5nSM4_NVMUfTDSC1-k,11682
 dashscope/aigc/video_synthesis.py,sha256=RSPjar5-YiF9xclRmf9H7-5QbRxLcsNXO4zS7oTKi2I,24137
 dashscope/api_entities/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 dashscope/api_entities/aiohttp_request.py,sha256=1L7XdIJ9L65cQmX8x9JCR4t5hNIMDrbiWADfKKp9yfo,10280
@@ -18,7 +18,7 @@ dashscope/api_entities/api_request_data.py,sha256=04rpYPNK1HkT3iTPJmZpquH621xcBb
 dashscope/api_entities/api_request_factory.py,sha256=ynpbFmxSne4dJkv5m40Vlwt4hJSxQPprAuUgMSQIQDg,5639
 dashscope/api_entities/base_request.py,sha256=W2SzrSAGFS6V8DErfSrayQtSL0T4iO7BrC8flr7nt1w,977
 dashscope/api_entities/chat_completion_types.py,sha256=1WMWPszhM3HaJBVz-ZXx-El4D8-RfVUL3ym65xsDRLk,11435
-dashscope/api_entities/dashscope_response.py,sha256=slc7o9jNS5yzv2giEPzz9CDOW6X797nkAocgZ1r84aU,22089
+dashscope/api_entities/dashscope_response.py,sha256=31guU41ePkLyFsVVN-1WODXdOHiURzRyxxhrUmX9dGM,22835
 dashscope/api_entities/encryption.py,sha256=rUCZx3wwVvS5oyKXEeWgyWPxM8Y5d4AaVdgxLhizBqA,5517
 dashscope/api_entities/http_request.py,sha256=MTxYsbkK8oYWDp8ZPjrkdY9YbnQ9SEIy87riyJidMXo,16484
 dashscope/api_entities/websocket_request.py,sha256=PS0FU854-HjTbKa68f4GHa7-noFRMzKySJGfPkrrBjw,16146
@@ -65,7 +65,7 @@ dashscope/customize/finetunes.py,sha256=AL_kGTJXMvM2ej-EKsLLd1dUphPQdVTefFVCSVH-
 dashscope/embeddings/__init__.py,sha256=XQ7vKr8oZM2CmdOduE53BWy6_Qpn9xUPkma64yw8Gws,291
 dashscope/embeddings/batch_text_embedding.py,sha256=lVhvTS8McYfXuqt_8CmmhA6bPqD0nrGv965kjYG_j0E,8842
 dashscope/embeddings/batch_text_embedding_response.py,sha256=ZfkJMUq8GRsFA6XUTsiAsIySqGJH-VPi2P9Ba1KTU-s,2056
-dashscope/embeddings/multimodal_embedding.py,sha256=NwjQsdkKgUz51ozGjqFDzVlLcZjY0m1JNdH1EyAY0a4,4109
+dashscope/embeddings/multimodal_embedding.py,sha256=PEF7DmtE5cbrXw4k3WQcfmsBKaAY3CTIoei3SyhOl34,6774
 dashscope/embeddings/text_embedding.py,sha256=2MPEyMB99xueDbvFg9kKAe8bgHMDEaFLaFa6GzDWDHg,2108
 dashscope/io/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 dashscope/io/input_output.py,sha256=0aXrRJFo1ZqYm_AJWR_w88O4-Btn9np2zUhrrUdBdfw,3992
@@ -100,9 +100,9 @@ dashscope/tokenizers/tokenizer.py,sha256=3FQVDvMNkCW9ccYeJdjrd_PIMMD3Xv7aNZkaYOE
 dashscope/tokenizers/tokenizer_base.py,sha256=5EJIFuizMWESEmLmbd38yJnfeHmPnzZPwsO4aOGjpl4,707
 dashscope/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 dashscope/utils/oss_utils.py,sha256=aZIHlMN2JOfVw6kp0SVrMw_N1MfoTcR_-wiRbJ7DgHw,7501
-dashscope-1.24.4.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-dashscope-1.24.4.dist-info/METADATA,sha256=uGVIdzKXASvLK5vUwMAFzIOS_qCj1RIGo_XCqvrjloQ,7146
-dashscope-1.24.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dashscope-1.24.4.dist-info/entry_points.txt,sha256=e9C3sOf9zDYL0O5ROEGX6FT8w-QK_kaGRWmPZDHAFys,49
-dashscope-1.24.4.dist-info/top_level.txt,sha256=woqavFJK9zas5xTqynmALqOtlafghjsk63Xk86powTU,10
-dashscope-1.24.4.dist-info/RECORD,,
+dashscope-1.24.5.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+dashscope-1.24.5.dist-info/METADATA,sha256=eRxoK1TphMD4hn-vUM3aPMtaCsvCzstnDe-QPH9A4Q0,7146
+dashscope-1.24.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dashscope-1.24.5.dist-info/entry_points.txt,sha256=e9C3sOf9zDYL0O5ROEGX6FT8w-QK_kaGRWmPZDHAFys,49
+dashscope-1.24.5.dist-info/top_level.txt,sha256=woqavFJK9zas5xTqynmALqOtlafghjsk63Xk86powTU,10
+dashscope-1.24.5.dist-info/RECORD,,