refactor: add is_cache_model method to various model classes to standardize cache behavior

apps/models_provider/impl/aliyun_bai_lian_model_provider/model/image.py

@@ -8,6 +8,10 @@ from models_provider.impl.base_chat_open_ai import BaseChatOpenAI
 
 class QwenVLChatModel(MaxKBBaseModel, BaseChatOpenAI):
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = MaxKBBaseModel.filter_optional_params(model_kwargs)

apps/models_provider/impl/aliyun_bai_lian_model_provider/model/stt.py

@@ -19,6 +19,10 @@ class AliyunBaiLianSpeechToText(MaxKBBaseModel, BaseSpeechToText):
         self.api_key = kwargs.get('api_key')
         self.model = kwargs.get('model')
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = {}

apps/models_provider/impl/aliyun_bai_lian_model_provider/model/tti.py

@@ -13,7 +13,6 @@ from models_provider.base_model_provider import MaxKBBaseModel
 from models_provider.impl.base_tti import BaseTextToImage
 
 
-
 class QwenTextToImageModel(MaxKBBaseModel, BaseTextToImage):
     api_key: str
     model_name: str
@@ -25,6 +24,10 @@ class QwenTextToImageModel(MaxKBBaseModel, BaseTextToImage):
         self.model_name = kwargs.get('model_name')
         self.params = kwargs.get('params')
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = {'params': {'size': '1024*1024', 'style': '<auto>', 'n': 1}}

apps/models_provider/impl/aliyun_bai_lian_model_provider/model/tts.py

@@ -20,6 +20,10 @@ class AliyunBaiLianTextToSpeech(MaxKBBaseModel, BaseTextToSpeech):
         self.model = kwargs.get('model')
         self.params = kwargs.get('params')
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = {'params': {'voice': 'longxiaochun', 'speech_rate': 1.0}}
@@ -52,5 +56,3 @@ class AliyunBaiLianTextToSpeech(MaxKBBaseModel, BaseTextToSpeech):
             raise Exception(audio)
         return audio
 
-    def is_cache_model(self):
-        return False

apps/models_provider/impl/anthropic_model_provider/model/image.py

@@ -13,6 +13,10 @@ def custom_get_token_ids(text: str):
 
 class AnthropicImage(MaxKBBaseModel, ChatAnthropic):
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = MaxKBBaseModel.filter_optional_params(model_kwargs)

apps/models_provider/impl/azure_model_provider/model/image.py

@@ -14,6 +14,10 @@ def custom_get_token_ids(text: str):
 
 class AzureOpenAIImage(MaxKBBaseModel, AzureChatOpenAI):
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = MaxKBBaseModel.filter_optional_params(model_kwargs)

apps/models_provider/impl/azure_model_provider/model/stt.py

@@ -25,6 +25,10 @@ class AzureOpenAISpeechToText(MaxKBBaseModel, BaseSpeechToText):
         self.api_base = kwargs.get('api_base')
         self.api_version = kwargs.get('api_version')
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = {}

apps/models_provider/impl/azure_model_provider/model/tti.py

@@ -27,6 +27,10 @@ class AzureOpenAITextToImage(MaxKBBaseModel, BaseTextToImage):
         self.model = kwargs.get('model')
         self.params = kwargs.get('params')
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = {'params': {'size': '1024x1024', 'quality': 'standard', 'n': 1}}

apps/models_provider/impl/azure_model_provider/model/tts.py

@@ -28,6 +28,10 @@ class AzureOpenAITextToSpeech(MaxKBBaseModel, BaseTextToSpeech):
         self.model = kwargs.get('model')
         self.params = kwargs.get('params')
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = {'params': {'voice': 'alloy'}}

apps/models_provider/impl/gemini_model_provider/model/image.py

@@ -13,6 +13,10 @@ def custom_get_token_ids(text: str):
 
 class GeminiImage(MaxKBBaseModel, ChatGoogleGenerativeAI):
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = MaxKBBaseModel.filter_optional_params(model_kwargs)

apps/models_provider/impl/gemini_model_provider/model/stt.py

@@ -22,6 +22,10 @@ class GeminiSpeechToText(MaxKBBaseModel, BaseSpeechToText):
         super().__init__(**kwargs)
         self.api_key = kwargs.get('api_key')
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = {}

apps/models_provider/impl/ollama_model_provider/model/image.py

@@ -15,6 +15,10 @@ def get_base_url(url: str):
 
 class OllamaImage(MaxKBBaseModel, BaseChatOpenAI):
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         api_base = model_credential.get('api_base', '')

apps/models_provider/impl/openai_model_provider/model/image.py

@@ -6,6 +6,10 @@ from models_provider.impl.base_chat_open_ai import BaseChatOpenAI
 
 class OpenAIImage(MaxKBBaseModel, BaseChatOpenAI):
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = MaxKBBaseModel.filter_optional_params(model_kwargs)

apps/models_provider/impl/openai_model_provider/model/stt.py

@@ -19,6 +19,10 @@ class OpenAISpeechToText(MaxKBBaseModel, BaseSpeechToText):
     api_key: str
     model: str
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
         self.api_key = kwargs.get('api_key')

apps/models_provider/impl/openai_model_provider/model/tti.py

@@ -25,6 +25,10 @@ class OpenAITextToImage(MaxKBBaseModel, BaseTextToImage):
         self.model = kwargs.get('model')
         self.params = kwargs.get('params')
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = {'params': {'size': '1024x1024', 'quality': 'standard', 'n': 1}}

apps/models_provider/impl/openai_model_provider/model/tts.py

@@ -26,6 +26,10 @@ class OpenAITextToSpeech(MaxKBBaseModel, BaseTextToSpeech):
         self.model = kwargs.get('model')
         self.params = kwargs.get('params')
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = {'params': {'voice': 'alloy'}}

apps/models_provider/impl/regolo_model_provider/model/image.py

@@ -6,6 +6,10 @@ from models_provider.impl.base_chat_open_ai import BaseChatOpenAI
 
 class RegoloImage(MaxKBBaseModel, BaseChatOpenAI):
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = MaxKBBaseModel.filter_optional_params(model_kwargs)

apps/models_provider/impl/regolo_model_provider/model/tti.py

@@ -25,6 +25,10 @@ class RegoloTextToImage(MaxKBBaseModel, BaseTextToImage):
         self.model = kwargs.get('model')
         self.params = kwargs.get('params')
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = {'params': {'size': '1024x1024', 'quality': 'standard', 'n': 1}}
@@ -38,9 +42,6 @@ class RegoloTextToImage(MaxKBBaseModel, BaseTextToImage):
             **optional_params,
         )
 
-    def is_cache_model(self):
-        return False
-
     def check_auth(self):
         chat = OpenAI(api_key=self.api_key, base_url=self.api_base)
         response_list = chat.models.with_raw_response.list()

apps/models_provider/impl/siliconCloud_model_provider/model/image.py

@@ -6,6 +6,10 @@ from models_provider.impl.base_chat_open_ai import BaseChatOpenAI
 
 class SiliconCloudImage(MaxKBBaseModel, BaseChatOpenAI):
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = MaxKBBaseModel.filter_optional_params(model_kwargs)

apps/models_provider/impl/siliconCloud_model_provider/model/stt.py

@@ -38,6 +38,10 @@ class SiliconCloudSpeechToText(MaxKBBaseModel, BaseSpeechToText):
             **optional_params,
         )
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     def check_auth(self):
         client = OpenAI(
             base_url=self.api_base,
@@ -56,4 +60,3 @@ class SiliconCloudSpeechToText(MaxKBBaseModel, BaseSpeechToText):
         buffer.name = "file.mp3"  # this is the important line
         res = client.audio.transcriptions.create(model=self.model, language="zh", file=buffer)
         return res.text
-

apps/models_provider/impl/siliconCloud_model_provider/model/tti.py

@@ -25,6 +25,10 @@ class SiliconCloudTextToImage(MaxKBBaseModel, BaseTextToImage):
         self.model = kwargs.get('model')
         self.params = kwargs.get('params')
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = {'params': {'size': '1024x1024', 'quality': 'standard', 'n': 1}}
@@ -38,9 +42,6 @@ class SiliconCloudTextToImage(MaxKBBaseModel, BaseTextToImage):
             **optional_params,
         )
 
-    def is_cache_model(self):
-        return False
-
     def check_auth(self):
         chat = OpenAI(api_key=self.api_key, base_url=self.api_base)
         response_list = chat.models.with_raw_response.list()

apps/models_provider/impl/tencent_model_provider/model/image.py

@@ -18,3 +18,7 @@ class TencentVision(MaxKBBaseModel, BaseChatOpenAI):
             stream_usage=True,
             extra_body=optional_params
         )
+
+    @staticmethod
+    def is_cache_model():
+        return False

apps/models_provider/impl/volcanic_engine_model_provider/model/image.py

@@ -18,3 +18,7 @@ class VolcanicEngineImage(MaxKBBaseModel, BaseChatOpenAI):
             stream_usage=True,
             extra_body=optional_params
         )
+
+    @staticmethod
+    def is_cache_model():
+        return False

apps/models_provider/impl/volcanic_engine_model_provider/model/stt.py

@@ -200,6 +200,10 @@ class VolcanicEngineSpeechToText(MaxKBBaseModel, BaseSpeechToText):
         self.volcanic_app_id = kwargs.get('volcanic_app_id')
         self.volcanic_cluster = kwargs.get('volcanic_cluster')
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = {}

apps/models_provider/impl/volcanic_engine_model_provider/model/tti.py

@@ -37,7 +37,6 @@ req_key_dict = {
 }
 
 
-
 def sign(key, msg):
     return hmac.new(key, msg.encode('utf-8'), hashlib.sha256).digest()
 
@@ -127,6 +126,10 @@ class VolcanicEngineTextToImage(MaxKBBaseModel, BaseTextToImage):
         self.model_version = kwargs.get('model_version')
         self.params = kwargs.get('params')
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = {'params': {}}

apps/models_provider/impl/xf_model_provider/model/image.py

@@ -94,3 +94,7 @@ class XFSparkImage(MaxKBBaseModel, ChatSparkLLM):
             if run_manager:
                 run_manager.on_llm_new_token(str(chunk.content), chunk=cg_chunk)
             yield cg_chunk
+
+    @staticmethod
+    def is_cache_model():
+        return False

apps/models_provider/impl/xf_model_provider/model/stt.py

@@ -29,7 +29,6 @@ ssl_context.check_hostname = False
 ssl_context.verify_mode = ssl.CERT_NONE
 
 
-
 class XFSparkSpeechToText(MaxKBBaseModel, BaseSpeechToText):
     spark_app_id: str
     spark_api_key: str
@@ -43,6 +42,10 @@ class XFSparkSpeechToText(MaxKBBaseModel, BaseSpeechToText):
         self.spark_api_key = kwargs.get('spark_api_key')
         self.spark_api_secret = kwargs.get('spark_api_secret')
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = {}

apps/models_provider/impl/xf_model_provider/model/tts.py

@@ -23,7 +23,6 @@ from common.utils.common import _remove_empty_lines
 from models_provider.base_model_provider import MaxKBBaseModel
 from models_provider.impl.base_tts import BaseTextToSpeech
 
-
 STATUS_FIRST_FRAME = 0  # 第一帧的标识
 STATUS_CONTINUE_FRAME = 1  # 中间帧标识
 STATUS_LAST_FRAME = 2  # 最后一帧的标识
@@ -48,6 +47,10 @@ class XFSparkTextToSpeech(MaxKBBaseModel, BaseTextToSpeech):
         self.spark_api_secret = kwargs.get('spark_api_secret')
         self.params = kwargs.get('params')
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = {'params': {'vcn': 'xiaoyan', 'speed': 50}}

apps/models_provider/impl/xinference_model_provider/model/image.py

@@ -9,6 +9,10 @@ from models_provider.impl.base_chat_open_ai import BaseChatOpenAI
 
 class XinferenceImage(MaxKBBaseModel, BaseChatOpenAI):
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = MaxKBBaseModel.filter_optional_params(model_kwargs)

apps/models_provider/impl/xinference_model_provider/model/stt.py

@@ -23,6 +23,10 @@ class XInferenceSpeechToText(MaxKBBaseModel, BaseSpeechToText):
         self.api_key = kwargs.get('api_key')
         self.api_base = kwargs.get('api_base')
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = {}

apps/models_provider/impl/xinference_model_provider/model/tti.py

@@ -28,6 +28,10 @@ class XinferenceTextToImage(MaxKBBaseModel, BaseTextToImage):
         self.model = kwargs.get('model')
         self.params = kwargs.get('params')
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = {'params': {'size': '1024x1024', 'quality': 'standard', 'n': 1}}

apps/models_provider/impl/xinference_model_provider/model/tts.py

@@ -27,6 +27,10 @@ class XInferenceTextToSpeech(MaxKBBaseModel, BaseTextToSpeech):
         self.model = kwargs.get('model')
         self.params = kwargs.get('params')
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = {'params': {'voice': '中文女'}}

apps/models_provider/impl/zhipu_model_provider/model/image.py

@@ -6,6 +6,10 @@ from models_provider.impl.base_chat_open_ai import BaseChatOpenAI
 
 class ZhiPuImage(MaxKBBaseModel, BaseChatOpenAI):
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = MaxKBBaseModel.filter_optional_params(model_kwargs)

apps/models_provider/impl/zhipu_model_provider/model/tti.py

@@ -26,6 +26,10 @@ class ZhiPuTextToImage(MaxKBBaseModel, BaseTextToImage):
         self.model = kwargs.get('model')
         self.params = kwargs.get('params')
 
+    @staticmethod
+    def is_cache_model():
+        return False
+
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = {'params': {'size': '1024x1024'}}