update wenxin llm

api/core/model_runtime/model_providers/wenxin/llm/ernie-3.5-4k-0205.yaml

@@ -0,0 +1,37 @@
+model: ernie-3.5-8k
+label:
+  en_US: Ernie-3.5-8K
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 4096
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0.1
+    max: 1.0
+    default: 0.8
+  - name: top_p
+    use_template: top_p
+  - name: max_output_tokens
+    use_template: max_output_tokens
+    default: 1024
+    min: 2
+    max: 2048
+  - name: penalty_score
+    use_template: penalty_score
+  - name: frequency_penalty
+    use_template: frequency_penalty
+  - name: response_format
+    use_template: response_format
+  - name: disable_search
+    label:
+      zh_Hans: 禁用搜索
+      en_US: Disable Search
+    type: boolean
+    help:
+      zh_Hans: 禁用模型自行进行外部搜索。
+      en_US: Disable the model to perform external search.
+    required: false

api/core/model_runtime/model_providers/wenxin/llm/ernie-bot-8k.yaml → api/core/model_runtime/model_providers/wenxin/llm/ernie-3.5-8k-0205.yaml

@@ -1,12 +1,12 @@
-model: ernie-bot-8k
+model: ernie-3.5-8k-0205
 label:
-  en_US: Ernie Bot 8k
+  en_US: Ernie-3.5-8K-0205
 model_type: llm
 features:
   - agent-thought
 model_properties:
   mode: chat
-  context_size: 8000
+  context_size: 8192
 parameter_rules:
   - name: temperature
     use_template: temperature
@@ -15,14 +15,13 @@ parameter_rules:
     default: 0.8
   - name: top_p
     use_template: top_p
-  - name: max_tokens
-    use_template: max_tokens
-    required: true
+  - name: max_output_tokens
+    use_template: max_output_tokens
     default: 1024
     min: 1
     max: 8000
-  - name: presence_penalty
-    use_template: presence_penalty
+  - name: penalty_score
+    use_template: penalty_score
   - name: frequency_penalty
     use_template: frequency_penalty
   - name: response_format

api/core/model_runtime/model_providers/wenxin/llm/ernie-3.5-8k-1222.yaml

@@ -0,0 +1,37 @@
+model: ernie-3.5-8k-1222
+label:
+  en_US: Ernie-3.5-8K-1222
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0.1
+    max: 1.0
+    default: 0.8
+  - name: top_p
+    use_template: top_p
+  - name: max_output_tokens
+    use_template: max_output_tokens
+    default: 1024
+    min: 1
+    max: 8000
+  - name: penalty_score
+    use_template: penalty_score
+  - name: frequency_penalty
+    use_template: frequency_penalty
+  - name: response_format
+    use_template: response_format
+  - name: disable_search
+    label:
+      zh_Hans: 禁用搜索
+      en_US: Disable Search
+    type: boolean
+    help:
+      zh_Hans: 禁用模型自行进行外部搜索。
+      en_US: Disable the model to perform external search.
+    required: false

api/core/model_runtime/model_providers/wenxin/llm/ernie-bot-4.yaml → api/core/model_runtime/model_providers/wenxin/llm/ernie-3.5-8k.yaml

@@ -1,12 +1,12 @@
-model: ernie-bot-4
+model: ernie-3.5-8k
 label:
-  en_US: Ernie Bot 4
+  en_US: Ernie-3.5-8K
 model_type: llm
 features:
   - agent-thought
 model_properties:
   mode: chat
-  context_size: 4800
+  context_size: 8192
 parameter_rules:
   - name: temperature
     use_template: temperature
@@ -15,14 +15,13 @@ parameter_rules:
     default: 0.8
   - name: top_p
     use_template: top_p
-  - name: max_tokens
-    use_template: max_tokens
-    required: true
-    default: 256
+  - name: max_output_tokens
+    use_template: max_output_tokens
+    default: 1024
     min: 1
-    max: 4800
-  - name: presence_penalty
-    use_template: presence_penalty
+    max: 8000
+  - name: penalty_score
+    use_template: penalty_score
   - name: frequency_penalty
     use_template: frequency_penalty
   - name: response_format

api/core/model_runtime/model_providers/wenxin/llm/ernie-bot.yaml → api/core/model_runtime/model_providers/wenxin/llm/ernie-4.0-8k.yaml

@@ -1,12 +1,12 @@
-model: ernie-bot
+model: ernie-4.0-8k
 label:
-  en_US: Ernie Bot
+  en_US: Ernie-4.0-8K
 model_type: llm
 features:
   - agent-thought
 model_properties:
   mode: chat
-  context_size: 4800
+  context_size: 8192
 parameter_rules:
   - name: temperature
     use_template: temperature
@@ -15,16 +15,17 @@ parameter_rules:
     default: 0.8
   - name: top_p
     use_template: top_p
-  - name: max_tokens
-    use_template: max_tokens
-    required: true
+  - name: max_output_tokens
+    use_template: max_output_tokens
     default: 256
     min: 1
     max: 4800
-  - name: presence_penalty
-    use_template: presence_penalty
+  - name: penalty_score
+    use_template: penalty_score
   - name: frequency_penalty
     use_template: frequency_penalty
+  - name: response_format
+    use_template: response_format
   - name: disable_search
     label:
       zh_Hans: 禁用搜索
@@ -34,5 +35,3 @@ parameter_rules:
       zh_Hans: 禁用模型自行进行外部搜索。
       en_US: Disable the model to perform external search.
     required: false
-  - name: response_format
-    use_template: response_format

api/core/model_runtime/model_providers/wenxin/llm/ernie-lite-8k-0308.yaml

@@ -0,0 +1,27 @@
+model: ernie-lite-8k-0308
+label:
+  en_US: ERNIE-Lite-8K-0308
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0.1
+    max: 1.0
+    default: 0.95
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1.0
+    default: 0.7
+  - name: max_output_tokens
+    use_template: max_output_tokens
+  - name: penalty_score
+    use_template: penalty_score
+    default: 1.0
+    min: 1.0
+    max: 2.0

api/core/model_runtime/model_providers/wenxin/llm/ernie-lite-8k-0922.yaml

@@ -0,0 +1,28 @@
+model: ernie-lite-8k-0922
+label:
+  en_US: ERNIE-Lite-8K-0922
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0.1
+    max: 1.0
+    default: 0.95
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1.0
+    default: 0.7
+  - name: max_output_tokens
+    use_template: max_output_tokens
+  - name: penalty_score
+    use_template: penalty_score
+    default: 1.0
+    min: 1.0
+    max: 2.0
+

api/core/model_runtime/model_providers/wenxin/llm/ernie-speed-128k.yaml

@@ -0,0 +1,27 @@
+model: ernie-speed-128k
+label:
+  en_US: ERNIE-Speed-128K
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 11200
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0.1
+    max: 1.0
+    default: 0.95
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1.0
+    default: 0.7
+  - name: max_output_tokens
+    use_template: max_output_tokens
+  - name: penalty_score
+    use_template: penalty_score
+    default: 1.0
+    min: 1.0
+    max: 2.0

api/core/model_runtime/model_providers/wenxin/llm/ernie-speed-8k.yaml

@@ -0,0 +1,27 @@
+model: ernie-speed-8k
+label:
+  en_US: ERNIE-Speed-8K
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0.1
+    max: 1.0
+    default: 0.95
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1.0
+    default: 0.7
+  - name: max_output_tokens
+    use_template: max_output_tokens
+  - name: penalty_score
+    use_template: penalty_score
+    default: 1.0
+    min: 1.0
+    max: 2.0

api/core/model_runtime/model_providers/wenxin/llm/ernie-speed-appbuilder.yaml

@@ -0,0 +1,27 @@
+model: ernie-speed-appbuilder
+label:
+  en_US: ERNIE-Speed-AppBuilder
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0.1
+    max: 1.0
+    default: 0.95
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1.0
+    default: 0.7
+  - name: max_output_tokens
+    use_template: max_output_tokens
+  - name: penalty_score
+    use_template: penalty_score
+    default: 1.0
+    min: 1.0
+    max: 2.0

api/core/model_runtime/model_providers/wenxin/llm/ernie_bot.py

@@ -121,15 +121,23 @@ def __init__(self, content: str, role: str = 'user') -> None:
 
 class ErnieBotModel:
     api_bases = {
-        'ernie-bot': 'https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/completions',
-        'ernie-bot-4': 'https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/completions_pro',
-        'ernie-bot-8k': 'https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie_bot_8k',
-        'ernie-bot-turbo': 'https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/eb-instant',
+        'ernie-3.5-8k': 'https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/completions',
+        'ernie-3.5-8k-0205': 'https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie-3.5-8k-0205',
+        'ernie-3.5-8k-1222': 'https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie-3.5-8k-1222',
+        'ernie-3.5-4k-0205': 'https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie-3.5-4k-0205',
+        'ernie-4.0-8k': 'https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/completions_pro',
+        'ernie-speed-8k': 'https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie_speed',
+        'ernie-speed-128k': 'https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie-speed-128k',
+        'ernie-speed-appbuilder': 'https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ai_apaas',
+        'ernie-lite-8k-0922': 'https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/eb-instant',
+        'ernie-lite-8k-0308': 'https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie-lite-8k',
     }
 
     function_calling_supports = [
-        'ernie-bot',
-        'ernie-bot-8k',
+        'ernie-3.5-8k',
+        'ernie-3.5-8k-0205',
+        'ernie-3.5-8k-1222',
+        'ernie-3.5-4k-0205'
     ]
 
     api_key: str = ''