Feat/add groq (#2733)

api/core/model_runtime/model_providers/_position.yaml

@@ -7,6 +7,7 @@
 - togetherai
 - ollama
 - mistralai
+- groq
 - replicate
 - huggingface_hub
 - zhipuai

api/core/model_runtime/model_providers/groq/groq.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 GroqProvider(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='llama2-70b-4096',
+                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/groq/groq.yaml

@@ -0,0 +1,32 @@
+provider: groq
+label:
+  zh_Hans: GroqCloud
+  en_US: GroqCloud
+description:
+  en_US: GroqCloud provides access to the Groq Cloud API, which hosts models like LLama2 and Mixtral.
+  zh_Hans: GroqCloud 提供对 Groq Cloud API 的访问，其中托管了 LLama2 和 Mixtral 等模型。
+icon_small:
+  en_US: icon_s_en.svg
+icon_large:
+  en_US: icon_l_en.svg
+background: "#F5F5F4"
+help:
+  title:
+    en_US: Get your API Key from GroqCloud
+    zh_Hans: 从 GroqCloud 获取 API Key
+  url:
+    en_US: https://console.groq.com/
+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

api/core/model_runtime/model_providers/groq/llm/llama2-70b-4096.yaml

@@ -0,0 +1,25 @@
+model: llama2-70b-4096
+label:
+  zh_Hans: Llama-2-70B-4096
+  en_US: Llama-2-70B-4096
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 4096
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: max_tokens
+    use_template: max_tokens
+    default: 512
+    min: 1
+    max: 4096
+pricing:
+  input: '0.7'
+  output: '0.8'
+  unit: '0.000001'
+  currency: USD

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

@@ -0,0 +1,26 @@
+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 GroqLargeLanguageModel(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)
+
+    @staticmethod
+    def _add_custom_parameters(credentials: dict) -> None:
+        credentials['mode'] = 'chat'
+        credentials['endpoint_url'] = 'https://api.groq.com/openai/v1'
+    

api/core/model_runtime/model_providers/groq/llm/mixtral-8x7b-instruct-v0.1.yaml

@@ -0,0 +1,25 @@
+model: mixtral-8x7b-32768
+label:
+  zh_Hans: Mixtral-8x7b-Instruct-v0.1
+  en_US: Mixtral-8x7b-Instruct-v0.1
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 32768
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: max_tokens
+    use_template: max_tokens
+    default: 512
+    min: 1
+    max: 20480
+pricing:
+  input: '0.27'
+  output: '0.27'
+  unit: '0.000001'
+  currency: USD