feat:support azure openai llm 0125 version (#2889)

api/core/model_runtime/model_providers/azure_openai/_constant.py

@@ -123,6 +123,65 @@ LLM_BASE_MODELS = [
             )
         )
     ),
+    AzureBaseModel(
+        base_model_name='gpt-35-turbo-0125',
+        entity=AIModelEntity(
+            model='fake-deployment-name',
+            label=I18nObject(
+                en_US='fake-deployment-name-label',
+            ),
+            model_type=ModelType.LLM,
+            features=[
+                ModelFeature.AGENT_THOUGHT,
+                ModelFeature.MULTI_TOOL_CALL,
+                ModelFeature.STREAM_TOOL_CALL,
+            ],
+            fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
+            model_properties={
+                ModelPropertyKey.MODE: LLMMode.CHAT.value,
+                ModelPropertyKey.CONTEXT_SIZE: 16385,
+            },
+            parameter_rules=[
+                ParameterRule(
+                    name='temperature',
+                    **PARAMETER_RULE_TEMPLATE[DefaultParameterName.TEMPERATURE],
+                ),
+                ParameterRule(
+                    name='top_p',
+                    **PARAMETER_RULE_TEMPLATE[DefaultParameterName.TOP_P],
+                ),
+                ParameterRule(
+                    name='presence_penalty',
+                    **PARAMETER_RULE_TEMPLATE[DefaultParameterName.PRESENCE_PENALTY],
+                ),
+                ParameterRule(
+                    name='frequency_penalty',
+                    **PARAMETER_RULE_TEMPLATE[DefaultParameterName.FREQUENCY_PENALTY],
+                ),
+                _get_max_tokens(default=512, min_val=1, max_val=4096),
+                ParameterRule(
+                    name='response_format',
+                    label=I18nObject(
+                        zh_Hans='回复格式',
+                        en_US='response_format'
+                    ),
+                    type='string',
+                    help=I18nObject(
+                        zh_Hans='指定模型必须输出的格式',
+                        en_US='specifying the format that the model must output'
+                    ),
+                    required=False,
+                    options=['text', 'json_object']
+                ),
+            ],
+            pricing=PriceConfig(
+                input=0.0005,
+                output=0.0015,
+                unit=0.001,
+                currency='USD',
+            )
+        )
+    ),
     AzureBaseModel(
         base_model_name='gpt-4',
         entity=AIModelEntity(
@@ -273,6 +332,81 @@ LLM_BASE_MODELS = [
             )
         )
     ),
+    AzureBaseModel(
+        base_model_name='gpt-4-0125-preview',
+        entity=AIModelEntity(
+            model='fake-deployment-name',
+            label=I18nObject(
+                en_US='fake-deployment-name-label',
+            ),
+            model_type=ModelType.LLM,
+            features=[
+                ModelFeature.AGENT_THOUGHT,
+                ModelFeature.MULTI_TOOL_CALL,
+                ModelFeature.STREAM_TOOL_CALL,
+            ],
+            fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
+            model_properties={
+                ModelPropertyKey.MODE: LLMMode.CHAT.value,
+                ModelPropertyKey.CONTEXT_SIZE: 128000,
+            },
+            parameter_rules=[
+                ParameterRule(
+                    name='temperature',
+                    **PARAMETER_RULE_TEMPLATE[DefaultParameterName.TEMPERATURE],
+                ),
+                ParameterRule(
+                    name='top_p',
+                    **PARAMETER_RULE_TEMPLATE[DefaultParameterName.TOP_P],
+                ),
+                ParameterRule(
+                    name='presence_penalty',
+                    **PARAMETER_RULE_TEMPLATE[DefaultParameterName.PRESENCE_PENALTY],
+                ),
+                ParameterRule(
+                    name='frequency_penalty',
+                    **PARAMETER_RULE_TEMPLATE[DefaultParameterName.FREQUENCY_PENALTY],
+                ),
+                _get_max_tokens(default=512, min_val=1, max_val=4096),
+                ParameterRule(
+                    name='seed',
+                    label=I18nObject(
+                        zh_Hans='种子',
+                        en_US='Seed'
+                    ),
+                    type='int',
+                    help=I18nObject(
+                        zh_Hans='如果指定，模型将尽最大努力进行确定性采样，使得重复的具有相同种子和参数的请求应该返回相同的结果。不能保证确定性，您应该参考 system_fingerprint 响应参数来监视变化。',
+                        en_US='If specified, model will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.'
+                    ),
+                    required=False,
+                    precision=2,
+                    min=0,
+                    max=1,
+                ),
+                ParameterRule(
+                    name='response_format',
+                    label=I18nObject(
+                        zh_Hans='回复格式',
+                        en_US='response_format'
+                    ),
+                    type='string',
+                    help=I18nObject(
+                        zh_Hans='指定模型必须输出的格式',
+                        en_US='specifying the format that the model must output'
+                    ),
+                    required=False,
+                    options=['text', 'json_object']
+                ),
+            ],
+            pricing=PriceConfig(
+                input=0.01,
+                output=0.03,
+                unit=0.001,
+                currency='USD',
+            )
+        )
+    ),
     AzureBaseModel(
         base_model_name='gpt-4-1106-preview',
         entity=AIModelEntity(

api/core/model_runtime/model_providers/azure_openai/azure_openai.yaml

@@ -75,6 +75,12 @@ model_credential_schema:
           show_on:
             - variable: __model_type
               value: llm
+        - label:
+            en_US: gpt-35-turbo-0125
+          value: gpt-35-turbo-0125
+          show_on:
+            - variable: __model_type
+              value: llm
         - label:
             en_US: gpt-35-turbo-16k
           value: gpt-35-turbo-16k
@@ -93,6 +99,12 @@ model_credential_schema:
           show_on:
             - variable: __model_type
               value: llm
+        - label:
+            en_US: gpt-4-0125-preview
+          value: gpt-4-0125-preview
+          show_on:
+            - variable: __model_type
+              value: llm
         - label:
             en_US: gpt-4-1106-preview
           value: gpt-4-1106-preview