feat: add models for gitee.ai (langgenius#9490)

api/core/model_runtime/model_providers/gitee_ai/_common.py

@@ -0,0 +1,47 @@
+from dashscope.common.error import (
+    AuthenticationError,
+    InvalidParameter,
+    RequestFailure,
+    ServiceUnavailableError,
+    UnsupportedHTTPMethod,
+    UnsupportedModel,
+)
+
+from core.model_runtime.errors.invoke import (
+    InvokeAuthorizationError,
+    InvokeBadRequestError,
+    InvokeConnectionError,
+    InvokeError,
+    InvokeRateLimitError,
+    InvokeServerUnavailableError,
+)
+
+
+class _CommonGiteeAI:
+    @property
+    def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
+        """
+        Map model invoke error to unified error
+        The key is the error type thrown to the caller
+        The value is the error type thrown by the model,
+        which needs to be converted into a unified error type for the caller.
+
+        :return: Invoke error mapping
+        """
+        return {
+            InvokeConnectionError: [
+                RequestFailure,
+            ],
+            InvokeServerUnavailableError: [
+                ServiceUnavailableError,
+            ],
+            InvokeRateLimitError: [],
+            InvokeAuthorizationError: [
+                AuthenticationError,
+            ],
+            InvokeBadRequestError: [
+                InvalidParameter,
+                UnsupportedModel,
+                UnsupportedHTTPMethod,
+            ],
+        }

api/core/model_runtime/model_providers/gitee_ai/gitee_ai.py

@@ -0,0 +1,25 @@
+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 GiteeAIProvider(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="Qwen2-7B-Instruct", 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/gitee_ai/gitee_ai.yaml

@@ -0,0 +1,35 @@
+provider: gitee_ai
+label:
+  en_US: Gitee AI
+  zh_Hans: Gitee AI
+description:
+  en_US: 快速体验大模型，领先探索 AI 开源世界
+  zh_Hans: 快速体验大模型，领先探索 AI 开源世界
+icon_small:
+  en_US: Gitee-AI-Logo.svg
+icon_large:
+  en_US: Gitee-AI-Logo-full.svg
+help:
+  title:
+    en_US: Get your token from Gitee AI
+    zh_Hans: 从 Gitee AI 获取 token
+  url:
+    en_US: https://ai.gitee.com/dashboard/settings/tokens
+supported_model_types:
+  - llm
+  - text-embedding
+  - rerank
+  - speech2text
+  - tts
+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/gitee_ai/llm/Qwen2-72B-Instruct.yaml

@@ -0,0 +1,105 @@
+model: Qwen2-72B-Instruct
+label:
+  zh_Hans: Qwen2-72B-Instruct
+  en_US: Qwen2-72B-Instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 6400
+parameter_rules:
+  - name: stream
+    use_template: boolean
+    label:
+      en_US: "Stream"
+      zh_Hans: "流式"
+    type: boolean
+    default: true
+    required: true
+    help:
+      en_US: "Whether to return the results in batches through streaming. If set to true, the generated text will be pushed to the user in real time during the generation process."
+      zh_Hans: "是否通过流式分批返回结果。如果设置为 true，生成过程中实时地向用户推送每一部分生成的文本。"
+
+  - name: max_tokens
+    use_template: max_tokens
+    label:
+      en_US: "Max Tokens"
+      zh_Hans: "最大Token数"
+    type: int
+    default: 512
+    min: 1
+    required: true
+    help:
+      en_US: "The maximum number of tokens that can be generated by the model varies depending on the model."
+      zh_Hans: "模型可生成的最大 token 个数，不同模型上限不同。"
+
+  - name: temperature
+    use_template: temperature
+    label:
+      en_US: "Temperature"
+      zh_Hans: "采样温度"
+    type: float
+    default: 0.7
+    min: 0.0
+    max: 1.0
+    precision: 1
+    required: true
+    help:
+      en_US: "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
+      zh_Hans: "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
+
+  - name: top_p
+    use_template: top_p
+    label:
+      en_US: "Top P"
+      zh_Hans: "Top P"
+    type: float
+    default: 0.7
+    min: 0.0
+    max: 1.0
+    precision: 1
+    required: true
+    help:
+      en_US: "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
+      zh_Hans: "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
+
+  - name: top_k
+    use_template: top_k
+    label:
+      en_US: "Top K"
+      zh_Hans: "Top K"
+    type: int
+    default: 50
+    min: 0
+    max: 100
+    required: true
+    help:
+      en_US: "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be."
+      zh_Hans: "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
+
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    label:
+      en_US: "Frequency Penalty"
+      zh_Hans: "频率惩罚"
+    type: float
+    default: 0
+    min: -1.0
+    max: 1.0
+    precision: 1
+    required: false
+    help:
+      en_US: "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation."
+      zh_Hans: "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
+
+  - name: user
+    use_template: text
+    label:
+      en_US: "User"
+      zh_Hans: "用户"
+    type: string
+    required: false
+    help:
+      en_US: "Used to track and differentiate conversation requests from different users."
+      zh_Hans: "用于追踪和区分不同用户的对话请求。"