Merge branch 'langgenius:main' into main

Author: haike-1213

api/core/model_runtime/model_providers/spark/llm/_client.py

@@ -25,14 +25,15 @@ def __init__(self, model: str, app_id: str, api_key: str, api_secret: str, api_d
             "spark-pro": {"version": "v3.1", "chat_domain": "generalv3"},
             "spark-pro-128k": {"version": "pro-128k", "chat_domain": "pro-128k"},
             "spark-max": {"version": "v3.5", "chat_domain": "generalv3.5"},
+            "spark-max-32k": {"version": "max-32k", "chat_domain": "max-32k"},
             "spark-4.0-ultra": {"version": "v4.0", "chat_domain": "4.0Ultra"},
         }
 
         api_version = model_api_configs[model]["version"]
 
         self.chat_domain = model_api_configs[model]["chat_domain"]
 
-        if model == "spark-pro-128k":
+        if model in ["spark-pro-128k", "spark-max-32k"]:
             self.api_base = f"wss://{domain}/{endpoint}/{api_version}"
         else:
             self.api_base = f"wss://{domain}/{api_version}/{endpoint}"

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

@@ -1,3 +1,4 @@
+- spark-max-32k
 - spark-4.0-ultra
 - spark-max
 - spark-pro-128k

api/core/model_runtime/model_providers/spark/llm/spark-max-32k.yaml

@@ -0,0 +1,33 @@
+model: spark-max-32k
+label:
+  en_US: Spark Max-32K
+model_type: llm
+model_properties:
+  mode: chat
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    default: 0.5
+    help:
+      zh_Hans: 核采样阈值。用于决定结果随机性，取值越高随机性越强即相同的问题得到的不同答案的可能性越高。
+      en_US: Kernel sampling threshold. Used to determine the randomness of the results. The higher the value, the stronger the randomness, that is, the higher the possibility of getting different answers to the same question.
+  - name: max_tokens
+    use_template: max_tokens
+    default: 4096
+    min: 1
+    max: 8192
+    help:
+      zh_Hans: 模型回答的tokens的最大长度。
+      en_US: Maximum length of tokens for the model response.
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    default: 4
+    min: 1
+    max: 6
+    help:
+      zh_Hans: 从 k 个候选中随机选择一个（非等概率）。
+      en_US: Randomly select one from k candidates (non-equal probability).
+    required: false

api/core/model_runtime/model_providers/tongyi/llm/farui-plus.yaml

@@ -62,13 +62,17 @@ parameter_rules:
     type: float
     default: 1.1
     label:
+      zh_Hans: 重复惩罚
       en_US: Repetition penalty
     help:
       zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
       en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
   - name: enable_search
     type: boolean
     default: false
+    label:
+      zh_Hans: 联网搜索
+      en_US: Web Search
     help:
       zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
       en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

api/core/model_runtime/model_providers/tongyi/llm/qwen-coder-turbo-0919.yaml

@@ -60,13 +60,17 @@ parameter_rules:
     type: float
     default: 1.1
     label:
+      zh_Hans: 重复惩罚
       en_US: Repetition penalty
     help:
       zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
       en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
   - name: enable_search
     type: boolean
     default: false
+    label:
+      zh_Hans: 联网搜索
+      en_US: Web Search
     help:
       zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
       en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

api/core/model_runtime/model_providers/tongyi/llm/qwen-coder-turbo-latest.yaml

@@ -60,13 +60,17 @@ parameter_rules:
     type: float
     default: 1.1
     label:
+      zh_Hans: 重复惩罚
       en_US: Repetition penalty
     help:
       zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
       en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
   - name: enable_search
     type: boolean
     default: false
+    label:
+      zh_Hans: 联网搜索
+      en_US: Web Search
     help:
       zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
       en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

api/core/model_runtime/model_providers/tongyi/llm/qwen-coder-turbo.yaml

@@ -60,13 +60,17 @@ parameter_rules:
     type: float
     default: 1.1
     label:
+      zh_Hans: 重复惩罚
       en_US: Repetition penalty
     help:
       zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
       en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
   - name: enable_search
     type: boolean
     default: false
+    label:
+      zh_Hans: 联网搜索
+      en_US: Web Search
     help:
       zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
       en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

api/core/model_runtime/model_providers/tongyi/llm/qwen-long.yaml

@@ -63,13 +63,17 @@ parameter_rules:
     type: float
     default: 1.1
     label:
+      zh_Hans: 重复惩罚
       en_US: Repetition penalty
     help:
       zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
       en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
   - name: enable_search
     type: boolean
     default: false
+    label:
+      zh_Hans: 联网搜索
+      en_US: Web Search
     help:
       zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
       en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

api/core/model_runtime/model_providers/tongyi/llm/qwen-math-plus-0816.yaml

@@ -60,13 +60,17 @@ parameter_rules:
     type: float
     default: 1.1
     label:
+      zh_Hans: 重复惩罚
       en_US: Repetition penalty
     help:
       zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
       en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
   - name: enable_search
     type: boolean
     default: false
+    label:
+      zh_Hans: 联网搜索
+      en_US: Web Search
     help:
       zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
       en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

api/core/model_runtime/model_providers/tongyi/llm/qwen-math-plus-0919.yaml

@@ -60,13 +60,17 @@ parameter_rules:
     type: float
     default: 1.1
     label:
+      zh_Hans: 重复惩罚
       en_US: Repetition penalty
     help:
       zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
       en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
   - name: enable_search
     type: boolean
     default: false
+    label:
+      zh_Hans: 联网搜索
+      en_US: Web Search
     help:
       zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
       en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.