Modify model parameters in Spark LLMs and zhipuai LLMs (#8078)

Co-authored-by: Charlie.Wei <luowei@cvte.com>

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

@@ -19,27 +19,25 @@ class SparkLLMClient:
         endpoint = 'chat'
         if api_domain:
             domain = api_domain
-            if model == 'spark-v3':
-                endpoint = 'multimodal'
 
         model_api_configs = {
-            'spark-1.5': {
+            'spark-lite': {
                 'version': 'v1.1',
                 'chat_domain': 'general'
             },
-            'spark-2': {
-                'version': 'v2.1',
-                'chat_domain': 'generalv2'
-            },
-            'spark-3': {
+            'spark-pro': {
                 'version': 'v3.1',
                 'chat_domain': 'generalv3'
             },
-            'spark-3.5': {
+            'spark-pro-128k': {
+                'version': 'pro-128k',
+                'chat_domain': 'pro-128k'
+            },
+            'spark-max': {
                 'version': 'v3.5',
                 'chat_domain': 'generalv3.5'
             },
-            'spark-4': {
+            'spark-4.0-ultra': {
                 'version': 'v4.0',
                 'chat_domain': '4.0Ultra'
             }
@@ -48,7 +46,12 @@ class SparkLLMClient:
         api_version = model_api_configs[model]['version']
 
         self.chat_domain = model_api_configs[model]['chat_domain']
-        self.api_base = f"wss://{domain}/{api_version}/{endpoint}"
+
+        if model == 'spark-pro-128k':
+            self.api_base = f"wss://{domain}/{endpoint}/{api_version}"
+        else:
+            self.api_base = f"wss://{domain}/{api_version}/{endpoint}"
+
         self.app_id = app_id
         self.ws_url = self.create_url(
             urlparse(self.api_base).netloc,

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

@@ -1,3 +1,8 @@
+- spark-4.0-ultra
+- spark-max
+- spark-pro-128k
+- spark-pro
+- spark-lite
 - spark-4
 - spark-3.5
 - spark-3

api/core/model_runtime/model_providers/spark/llm/spark-1.5.yaml

@@ -1,4 +1,5 @@
 model: spark-1.5
+deprecated: true
 label:
   en_US: Spark V1.5
 model_type: llm

api/core/model_runtime/model_providers/spark/llm/spark-3.5.yaml

@@ -1,4 +1,5 @@
 model: spark-3.5
+deprecated: true
 label:
   en_US: Spark V3.5
 model_type: llm

api/core/model_runtime/model_providers/spark/llm/spark-3.yaml

@@ -1,4 +1,5 @@
 model: spark-3
+deprecated: true
 label:
   en_US: Spark V3.0
 model_type: llm

api/core/model_runtime/model_providers/spark/llm/spark-4.0-ultra.yaml

@@ -0,0 +1,42 @@
+model: spark-4.0-ultra
+label:
+  en_US: Spark 4.0 Ultra
+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
+  - name: show_ref_label
+    label:
+      zh_Hans: 联网检索
+      en_US: web search
+    type: boolean
+    default: false
+    help:
+      zh_Hans: 该参数仅4.0 Ultra版本支持，当设置为true时，如果输入内容触发联网检索插件，会先返回检索信源列表，然后再返回星火回复结果，否则仅返回星火回复结果
+      en_US: The parameter is only supported in the 4.0 Ultra version. When set to true, if the input triggers the online search plugin, it will first return a list of search sources and then return the Spark response. Otherwise, it will only return the Spark response.

api/core/model_runtime/model_providers/spark/llm/spark-4.yaml

@@ -1,4 +1,5 @@
 model: spark-4
+deprecated: true
 label:
   en_US: Spark V4.0
 model_type: llm

api/core/model_runtime/model_providers/spark/llm/spark-lite.yaml

@@ -0,0 +1,33 @@
+model: spark-lite
+label:
+  en_US: Spark Lite
+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: 4096
+    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/spark/llm/spark-max.yaml

@@ -0,0 +1,33 @@
+model: spark-max
+label:
+  en_US: Spark Max
+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/spark/llm/spark-pro-128k.yaml

@@ -0,0 +1,33 @@
+model: spark-pro-128k
+label:
+  en_US: Spark Pro-128K
+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: 4096
+    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/spark/llm/spark-pro.yaml

@@ -0,0 +1,33 @@
+model: spark-pro
+label:
+  en_US: Spark Pro
+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