feat: support siliconflow (#5129)

api/core/model_runtime/model_providers/_position.yaml

@@ -32,3 +32,4 @@
 - openai_api_compatible
 - deepseek
 - hunyuan
+- siliconflow

api/core/model_runtime/model_providers/siliconflow/llm/_position.yaml

@@ -0,0 +1,8 @@
+- deepseek-v2-chat
+- qwen2-72b-instruct
+- qwen2-57b-a14b-instruct
+- qwen2-7b-instruct
+- yi-1.5-34b-chat
+- yi-1.5-9b-chat
+- yi-1.5-6b-chat
+- glm4-9B-chat

api/core/model_runtime/model_providers/siliconflow/llm/deepseek-v2-chat.yaml

@@ -0,0 +1,32 @@
+model: deepseek-ai/deepseek-v2-chat
+label:
+  en_US: deepseek-ai/deepseek-v2-chat
+model_type: llm
+features:
+  - multi-tool-call
+  - agent-thought
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 32768
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 512
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
+      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
+  - name: top_p
+    use_template: top_p
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: '1.33'
+  output: '1.33'
+  unit: '0.000001'
+  currency: RMB

api/core/model_runtime/model_providers/siliconflow/llm/glm4-9b-chat.yaml

@@ -0,0 +1,32 @@
+model: zhipuai/glm4-9B-chat
+label:
+  en_US: zhipuai/glm4-9B-chat
+model_type: llm
+features:
+  - multi-tool-call
+  - agent-thought
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 32768
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 512
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
+      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
+  - name: top_p
+    use_template: top_p
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: '0.6'
+  output: '0.6'
+  unit: '0.000001'
+  currency: RMB

api/core/model_runtime/model_providers/siliconflow/llm/llm.py

@@ -0,0 +1,25 @@
+from collections.abc import Generator
+from typing import Optional, Union
+
+from core.model_runtime.entities.llm_entities import LLMResult
+from core.model_runtime.entities.message_entities import PromptMessage, PromptMessageTool
+from core.model_runtime.model_providers.openai_api_compatible.llm.llm import OAIAPICompatLargeLanguageModel
+
+
+class SiliconflowLargeLanguageModel(OAIAPICompatLargeLanguageModel):
+    def _invoke(self, model: str, credentials: dict,
+                prompt_messages: list[PromptMessage], model_parameters: dict,
+                tools: Optional[list[PromptMessageTool]] = None, stop: Optional[list[str]] = None,
+                stream: bool = True, user: Optional[str] = None) \
+            -> Union[LLMResult, Generator]:
+        self._add_custom_parameters(credentials)
+        return super()._invoke(model, credentials, prompt_messages, model_parameters, tools, stop, stream)
+
+    def validate_credentials(self, model: str, credentials: dict) -> None:
+        self._add_custom_parameters(credentials)
+        super().validate_credentials(model, credentials)
+
+    @classmethod
+    def _add_custom_parameters(cls, credentials: dict) -> None:
+        credentials['mode'] = 'chat'
+        credentials['endpoint_url'] = 'https://api.siliconflow.cn/v1'

api/core/model_runtime/model_providers/siliconflow/llm/qwen2-57b-a14b-instruct.yaml

@@ -0,0 +1,32 @@
+model: alibaba/Qwen2-57B-A14B-Instruct
+label:
+  en_US: alibaba/Qwen2-57B-A14B-Instruct
+model_type: llm
+features:
+  - multi-tool-call
+  - agent-thought
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 32768
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 512
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
+      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
+  - name: top_p
+    use_template: top_p
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: '1.26'
+  output: '1.26'
+  unit: '0.000001'
+  currency: RMB

api/core/model_runtime/model_providers/siliconflow/llm/qwen2-72b-instruct.yaml

@@ -0,0 +1,32 @@
+model: alibaba/Qwen2-72B-Instruct
+label:
+  en_US: alibaba/Qwen2-72B-Instruct
+model_type: llm
+features:
+  - multi-tool-call
+  - agent-thought
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 32768
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 512
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
+      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
+  - name: top_p
+    use_template: top_p
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: '4.13'
+  output: '4.13'
+  unit: '0.000001'
+  currency: RMB

api/core/model_runtime/model_providers/siliconflow/llm/qwen2-7b-instruct.yaml

@@ -0,0 +1,32 @@
+model: alibaba/Qwen2-7B-Instruct
+label:
+  en_US: alibaba/Qwen2-7B-Instruct
+model_type: llm
+features:
+  - multi-tool-call
+  - agent-thought
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 32768
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 512
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
+      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
+  - name: top_p
+    use_template: top_p
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: '0.35'
+  output: '0.35'
+  unit: '0.000001'
+  currency: RMB

api/core/model_runtime/model_providers/siliconflow/llm/yi-1.5-34b-chat.yaml

@@ -0,0 +1,32 @@
+model: 01-ai/Yi-1.5-34B-Chat
+label:
+  en_US: 01-ai/Yi-1.5-34B-Chat
+model_type: llm
+features:
+  - multi-tool-call
+  - agent-thought
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 16384
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 512
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
+      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
+  - name: top_p
+    use_template: top_p
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: '1.26'
+  output: '1.26'
+  unit: '0.000001'
+  currency: RMB

api/core/model_runtime/model_providers/siliconflow/llm/yi-1.5-6b-chat.yaml

@@ -0,0 +1,32 @@
+model: 01-ai/Yi-1.5-6B-Chat
+label:
+  en_US: 01-ai/Yi-1.5-6B-Chat
+model_type: llm
+features:
+  - multi-tool-call
+  - agent-thought
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 4096
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 512
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
+      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
+  - name: top_p
+    use_template: top_p
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: '0.35'
+  output: '0.35'
+  unit: '0.000001'
+  currency: RMB

api/core/model_runtime/model_providers/siliconflow/llm/yi-1.5-9b-chat.yaml

@@ -0,0 +1,32 @@
+model: 01-ai/Yi-1.5-9B-Chat
+label:
+  en_US: 01-ai/Yi-1.5-9B-Chat
+model_type: llm
+features:
+  - multi-tool-call
+  - agent-thought
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 16384
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 512
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
+      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
+  - name: top_p
+    use_template: top_p
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: '0.42'
+  output: '0.42'
+  unit: '0.000001'
+  currency: RMB

api/core/model_runtime/model_providers/siliconflow/siliconflow.py

@@ -0,0 +1,29 @@
+import logging
+
+from core.model_runtime.entities.model_entities import ModelType
+from core.model_runtime.errors.validate import CredentialsValidateFailedError
+from core.model_runtime.model_providers.__base.model_provider import ModelProvider
+
+logger = logging.getLogger(__name__)
+
+class SiliconflowProvider(ModelProvider):
+
+    def validate_provider_credentials(self, credentials: dict) -> None:
+        """
+        Validate provider credentials
+        if validate failed, raise exception
+
+        :param credentials: provider credentials, credentials form defined in `provider_credential_schema`.
+        """
+        try:
+            model_instance = self.get_model_instance(ModelType.LLM)
+
+            model_instance.validate_credentials(
+                model='deepseek-ai/deepseek-v2-chat',
+                credentials=credentials
+            )
+        except CredentialsValidateFailedError as ex:
+            raise ex
+        except Exception as ex:
+            logger.exception(f'{self.get_provider_schema().provider} credentials validate failed')
+            raise ex

api/core/model_runtime/model_providers/siliconflow/siliconflow.yaml

@@ -0,0 +1,29 @@
+provider: siliconflow
+label:
+  zh_Hans: 硅基流动
+  en_US: SiliconFlow
+icon_small:
+  en_US: siliconflow_square.svg
+icon_large:
+  en_US: siliconflow.svg
+background: "#ffecff"
+help:
+  title:
+    en_US: Get your API Key from SiliconFlow
+    zh_Hans: 从 SiliconFlow 获取 API Key
+  url:
+    en_US: https://cloud.siliconflow.cn/keys
+supported_model_types:
+  - llm
+configurate_methods:
+  - predefined-model
+provider_credential_schema:
+  credential_form_schemas:
+    - variable: api_key
+      label:
+        en_US: API Key
+      type: secret-input
+      required: true
+      placeholder:
+        zh_Hans: 在此输入您的 API Key
+        en_US: Enter your API Key