diff --git a/api/core/model_runtime/model_providers/leptonai/_assets/icon_l_en.png b/api/core/model_runtime/model_providers/leptonai/_assets/icon_l_en.png new file mode 100644 index 0000000000..719122b284 Binary files /dev/null and b/api/core/model_runtime/model_providers/leptonai/_assets/icon_l_en.png differ diff --git a/api/core/model_runtime/model_providers/leptonai/_assets/icon_s_en.png b/api/core/model_runtime/model_providers/leptonai/_assets/icon_s_en.png new file mode 100644 index 0000000000..3f652d96e1 Binary files /dev/null and b/api/core/model_runtime/model_providers/leptonai/_assets/icon_s_en.png differ diff --git a/api/core/model_runtime/model_providers/leptonai/leptonai.py b/api/core/model_runtime/model_providers/leptonai/leptonai.py new file mode 100644 index 0000000000..b035c31ac5 --- /dev/null +++ b/api/core/model_runtime/model_providers/leptonai/leptonai.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 LeptonAIProvider(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='llama2-7b', + 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 diff --git a/api/core/model_runtime/model_providers/leptonai/leptonai.yaml b/api/core/model_runtime/model_providers/leptonai/leptonai.yaml new file mode 100644 index 0000000000..a246ff5356 --- /dev/null +++ b/api/core/model_runtime/model_providers/leptonai/leptonai.yaml @@ -0,0 +1,29 @@ +provider: leptonai +label: + zh_Hans: Lepton AI + en_US: Lepton AI +icon_small: + en_US: icon_s_en.png +icon_large: + en_US: icon_l_en.png +background: "#F5F5F4" +help: + title: + en_US: Get your API Key from Lepton AI + zh_Hans: 从 Lepton AI 获取 API Key + url: + en_US: https://dashboard.lepton.ai +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 diff --git a/api/core/model_runtime/model_providers/leptonai/llm/_position.yaml b/api/core/model_runtime/model_providers/leptonai/llm/_position.yaml new file mode 100644 index 0000000000..a85e8e65ba --- /dev/null +++ b/api/core/model_runtime/model_providers/leptonai/llm/_position.yaml @@ -0,0 +1,6 @@ +- gemma-7b +- mistral-7b +- mixtral-8x7b +- llama2-7b +- llama2-13b +- llama3-70b diff --git a/api/core/model_runtime/model_providers/leptonai/llm/gemma-7b.yaml b/api/core/model_runtime/model_providers/leptonai/llm/gemma-7b.yaml new file mode 100644 index 0000000000..2d69067a23 --- /dev/null +++ b/api/core/model_runtime/model_providers/leptonai/llm/gemma-7b.yaml @@ -0,0 +1,20 @@ +model: gemma-7b +label: + zh_Hans: gemma-7b + en_US: gemma-7b +model_type: llm +features: + - agent-thought +model_properties: + mode: chat + context_size: 8192 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: max_tokens + use_template: max_tokens + default: 1024 + min: 1 + max: 1024 diff --git a/api/core/model_runtime/model_providers/leptonai/llm/llama2-13b.yaml b/api/core/model_runtime/model_providers/leptonai/llm/llama2-13b.yaml new file mode 100644 index 0000000000..307f1ea88f --- /dev/null +++ b/api/core/model_runtime/model_providers/leptonai/llm/llama2-13b.yaml @@ -0,0 +1,20 @@ +model: llama2-13b +label: + zh_Hans: llama2-13b + en_US: llama2-13b +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: 1024 + min: 1 + max: 1024 diff --git a/api/core/model_runtime/model_providers/leptonai/llm/llama2-7b.yaml b/api/core/model_runtime/model_providers/leptonai/llm/llama2-7b.yaml new file mode 100644 index 0000000000..bd471e59cd --- /dev/null +++ b/api/core/model_runtime/model_providers/leptonai/llm/llama2-7b.yaml @@ -0,0 +1,20 @@ +model: llama2-7b +label: + zh_Hans: llama2-7b + en_US: llama2-7b +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: 1024 + min: 1 + max: 1024 diff --git a/api/core/model_runtime/model_providers/leptonai/llm/llama3-70b.yaml b/api/core/model_runtime/model_providers/leptonai/llm/llama3-70b.yaml new file mode 100644 index 0000000000..9c20eb6cdb --- /dev/null +++ b/api/core/model_runtime/model_providers/leptonai/llm/llama3-70b.yaml @@ -0,0 +1,20 @@ +model: llama3-70b +label: + zh_Hans: llama3-70b + en_US: llama3-70b +model_type: llm +features: + - agent-thought +model_properties: + mode: chat + context_size: 8192 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: max_tokens + use_template: max_tokens + default: 1024 + min: 1 + max: 1024 diff --git a/api/core/model_runtime/model_providers/leptonai/llm/llm.py b/api/core/model_runtime/model_providers/leptonai/llm/llm.py new file mode 100644 index 0000000000..523309bac5 --- /dev/null +++ b/api/core/model_runtime/model_providers/leptonai/llm/llm.py @@ -0,0 +1,34 @@ +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 LeptonAILargeLanguageModel(OAIAPICompatLargeLanguageModel): + MODEL_PREFIX_MAP = { + 'llama2-7b': 'llama2-7b', + 'gemma-7b': 'gemma-7b', + 'mistral-7b': 'mistral-7b', + 'mixtral-8x7b': 'mixtral-8x7b', + 'llama3-70b': 'llama3-70b', + 'llama2-13b': 'llama2-13b', + } + 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, model) + 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, model) + super().validate_credentials(model, credentials) + + @classmethod + def _add_custom_parameters(cls, credentials: dict, model: str) -> None: + credentials['mode'] = 'chat' + credentials['endpoint_url'] = f'https://{cls.MODEL_PREFIX_MAP[model]}.lepton.run/api/v1' + \ No newline at end of file diff --git a/api/core/model_runtime/model_providers/leptonai/llm/mistral-7b.yaml b/api/core/model_runtime/model_providers/leptonai/llm/mistral-7b.yaml new file mode 100644 index 0000000000..f2b46ff917 --- /dev/null +++ b/api/core/model_runtime/model_providers/leptonai/llm/mistral-7b.yaml @@ -0,0 +1,20 @@ +model: mistral-7b +label: + zh_Hans: mistral-7b + en_US: mistral-7b +model_type: llm +features: + - agent-thought +model_properties: + mode: chat + context_size: 8192 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: max_tokens + use_template: max_tokens + default: 1024 + min: 1 + max: 1024 diff --git a/api/core/model_runtime/model_providers/leptonai/llm/mixtral-8x7b.yaml b/api/core/model_runtime/model_providers/leptonai/llm/mixtral-8x7b.yaml new file mode 100644 index 0000000000..de788ac256 --- /dev/null +++ b/api/core/model_runtime/model_providers/leptonai/llm/mixtral-8x7b.yaml @@ -0,0 +1,20 @@ +model: mixtral-8x7b +label: + zh_Hans: mixtral-8x7b + en_US: mixtral-8x7b +model_type: llm +features: + - agent-thought +model_properties: + mode: chat + context_size: 32000 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: max_tokens + use_template: max_tokens + default: 1024 + min: 1 + max: 1024