feat: add qwen3 series models llm config

README.md

@@ -29,19 +29,19 @@ More patterns are coming soon...
 
 The LLM model integration can be accomplished with simple configuration, currently agentUniverse supported models include:
 
-||Vendors|Models|
+|-|Vendors|                                                       Models                                                       |
-|:-----:|:--------:|:------:|
+|:-----:|:--------:|:------------------------------------------------------------------------------------------------------------------:|
-|<img src="https://github.com/user-attachments/assets/b7b0f2ce-3250-4008-b6d7-4712a983deb9" height="25">|Qwen|qwen2.5-72b-instruct、qwq-32b-preview、qwen-max、…|
+|<img src="https://github.com/user-attachments/assets/b7b0f2ce-3250-4008-b6d7-4712a983deb9" height="25">|  Qwen  | [✨**new**] **qwen3 Series**（qwen3-235b-a22b、qwen3-32b、qwen3-30b-a3b, etc.）、qwen2.5-72b-instruct、qwq-32b-preview、qwen-max、… |
-|<img src="https://github.com/user-attachments/assets/5a997feb-bef4-4e53-ac3e-d38221e5399c" height="25">|Deepseek|deepseek-r1、deepseek-v3、deepseek-r1-distill-qwen-32b、…|
+|<img src="https://github.com/user-attachments/assets/5a997feb-bef4-4e53-ac3e-d38221e5399c" height="25">|Deepseek|                               deepseek-r1、deepseek-v3、deepseek-r1-distill-qwen-32b、…                               |
-|<img src="https://github.com/user-attachments/assets/0b50e555-65e8-49b2-b725-f3f71ee7daed" height="25">|OpenAI|GPT-4o、GPT-4o mini、OpenAI o1、OpenAI o3-mini、…|
+|<img src="https://github.com/user-attachments/assets/0b50e555-65e8-49b2-b725-f3f71ee7daed" height="25">| OpenAI |                                   GPT-4o、GPT-4o mini、OpenAI o1、OpenAI o3-mini、…                                    |
-|<img src="https://github.com/user-attachments/assets/60fe0a70-0b47-4ac7-9bc9-8e860732ace9" height="25">|Claude|Claude 3.5 Sonnet、Claude 3 Opus、…|
+|<img src="https://github.com/user-attachments/assets/60fe0a70-0b47-4ac7-9bc9-8e860732ace9" height="25">| Claude |                                         Claude 3.5 Sonnet、Claude 3 Opus、…                                          |
-|<img src="https://github.com/user-attachments/assets/334c7f09-7eae-4a65-a70f-2e6531964224" height="25">|Gemini|Gemini 2.0 Flash、Gemini 2.0 Flash Thinking、Gemini 1.5 Pro、…|
+|<img src="https://github.com/user-attachments/assets/334c7f09-7eae-4a65-a70f-2e6531964224" height="25">| Gemini |                            Gemini 2.0 Flash、Gemini 2.0 Flash Thinking、Gemini 1.5 Pro、…                             |
-|<img src="https://github.com/user-attachments/assets/8e41c73f-3103-4305-ad1f-56116ea55523" height="25">|Llama|llama3.3-70b-instruct、llama3.2-3b-instruct、llama3.2-1b-instruct、…|
+|<img src="https://github.com/user-attachments/assets/8e41c73f-3103-4305-ad1f-56116ea55523" height="25">| Llama  |                         llama3.3-70b-instruct、llama3.2-3b-instruct、llama3.2-1b-instruct、…                          |
-|<img src="https://github.com/user-attachments/assets/19d264c6-e499-4913-9d6d-314d392f2246" height="25">|KIMI|moonshot-v1-128k、moonshot-v1-32k、moonshot-v1-8k、…|
+|<img src="https://github.com/user-attachments/assets/19d264c6-e499-4913-9d6d-314d392f2246" height="25">|  KIMI  |                                 moonshot-v1-128k、moonshot-v1-32k、moonshot-v1-8k、…                                  |
-|<img src="https://github.com/user-attachments/assets/79572d9a-29d5-4c0e-a336-ce3f8018fb05" height="25">|WenXin|ERNIE 4.0、ERNIE 4.0 Turbo、ERNIE 3.5、…|
+|<img src="https://github.com/user-attachments/assets/79572d9a-29d5-4c0e-a336-ce3f8018fb05" height="25">| WenXin |                                       ERNIE 4.0、ERNIE 4.0 Turbo、ERNIE 3.5、…                                        |
-|<img src="https://github.com/user-attachments/assets/abb5311e-4d70-4e9c-8fca-e5129ae912fc" height="25">|chatglm|chatglm3-6b、chatglm-6b-v2、…|
+|<img src="https://github.com/user-attachments/assets/abb5311e-4d70-4e9c-8fca-e5129ae912fc" height="25">|chatglm |                                            chatglm3-6b、chatglm-6b-v2、…                                             |
-|<img src="https://github.com/user-attachments/assets/fe265f24-4ea6-4ff2-9b50-58ab6706a5f5" height="25">|BaiChuan|baichuan2-turbo、baichuan2-13b-chat-v1、…|
+|<img src="https://github.com/user-attachments/assets/fe265f24-4ea6-4ff2-9b50-58ab6706a5f5" height="25">|BaiChuan|                                      baichuan2-turbo、baichuan2-13b-chat-v1、…                                       |
-|<img src="https://github.com/user-attachments/assets/41ffe268-392f-4ab9-b42d-e30dbd70d66b" height="25">|Doubao|Doubao-pro-128k、Doubao-pro-32k、Doubao-lite-128k、…|
+|<img src="https://github.com/user-attachments/assets/41ffe268-392f-4ab9-b42d-e30dbd70d66b" height="25">| Doubao |                                 Doubao-pro-128k、Doubao-pro-32k、Doubao-lite-128k、…                                  |
 
 For example, to use deepseek model, you can simply set DEEPSEEK_API_KEY value in the custom_key.toml file, and set the llm_model name in the agent configuration file to 'default_deepseek_llm' and you're all set. For more information about llm configuration, please refer to [switch-the-llm](https://github.com/agentuniverse-ai/agentUniverse/blob/master/docs/guidebook/en/Get_Start/2.Run_Your_First_Tutorial_Example.md#switch-the-llm).
 

README_zh.md

@@ -24,6 +24,22 @@
 
 更多模式组件持续推出中...
 
+The LLM model integration can be accomplished with simple configuration, currently agentUniverse supported models include:
+
+|-|供应商|                                                            模型                                                            |
+|:-----:|:--------:|:------------------------------------------------------------------------------------------------------------------------:|
+|<img src="https://github.com/user-attachments/assets/b7b0f2ce-3250-4008-b6d7-4712a983deb9" height="25">|Qwen|  [✨**new**] **qwen3 Series**（qwen3-235b-a22b、qwen3-32b、qwen3-30b-a3b, etc.） 、qwen2.5-72b-instruct、qwq-32b-preview、qwen-max、… |
+|<img src="https://github.com/user-attachments/assets/5a997feb-bef4-4e53-ac3e-d38221e5399c" height="25">|Deepseek|                                  deepseek-r1、deepseek-v3、deepseek-r1-distill-qwen-32b、…                                  |
+|<img src="https://github.com/user-attachments/assets/0b50e555-65e8-49b2-b725-f3f71ee7daed" height="25">|OpenAI|                                      GPT-4o、GPT-4o mini、OpenAI o1、OpenAI o3-mini、…                                       |
+|<img src="https://github.com/user-attachments/assets/60fe0a70-0b47-4ac7-9bc9-8e860732ace9" height="25">|Claude|                                            Claude 3.5 Sonnet、Claude 3 Opus、…                                             |
+|<img src="https://github.com/user-attachments/assets/334c7f09-7eae-4a65-a70f-2e6531964224" height="25">|Gemini|                               Gemini 2.0 Flash、Gemini 2.0 Flash Thinking、Gemini 1.5 Pro、…                                |
+|<img src="https://github.com/user-attachments/assets/8e41c73f-3103-4305-ad1f-56116ea55523" height="25">|Llama|                            llama3.3-70b-instruct、llama3.2-3b-instruct、llama3.2-1b-instruct、…                             |
+|<img src="https://github.com/user-attachments/assets/19d264c6-e499-4913-9d6d-314d392f2246" height="25">|KIMI|                                    moonshot-v1-128k、moonshot-v1-32k、moonshot-v1-8k、…                                     |
+|<img src="https://github.com/user-attachments/assets/79572d9a-29d5-4c0e-a336-ce3f8018fb05" height="25">|WenXin|                                          ERNIE 4.0、ERNIE 4.0 Turbo、ERNIE 3.5、…                                           |
+|<img src="https://github.com/user-attachments/assets/abb5311e-4d70-4e9c-8fca-e5129ae912fc" height="25">|chatglm|                                               chatglm3-6b、chatglm-6b-v2、…                                                |
+|<img src="https://github.com/user-attachments/assets/fe265f24-4ea6-4ff2-9b50-58ab6706a5f5" height="25">|BaiChuan|                                         baichuan2-turbo、baichuan2-13b-chat-v1、…                                          |
+|<img src="https://github.com/user-attachments/assets/41ffe268-392f-4ab9-b42d-e30dbd70d66b" height="25">|Doubao|                                    Doubao-pro-128k、Doubao-pro-32k、Doubao-lite-128k、…                                     |
+
 ****************************************
 
 ## 目录

examples/sample_standard_app/intelligence/agentic/agent/agent_instance/demo_agent.yaml

@@ -35,7 +35,7 @@ profile:
   #
   # Note: The current configuration uses Way 1, as shown below
   llm_model:
-    name: 'deepseek-chat'
+    name: 'qwen3-32b'
 action:
   # Please select the tools and knowledge base.
   tool:

examples/sample_standard_app/intelligence/agentic/llm/buildin/qwen/channel/qwen3/qwen3_0_6b_official_channel.yaml

@@ -0,0 +1,8 @@
+channel_name: 'qwen3-0.6b-official'
+channel_api_key: '${DASHSCOPE_API_KEY}'
+channel_api_base: 'https://dashscope.aliyuncs.com/compatible-mode/v1'
+channel_model_name: 'qwen3-0.6b'
+model_support_stream: True
+model_support_max_context_length: 32768
+model_is_openai_protocol_compatible: True
+meta_class: 'agentuniverse.llm.llm_channel.dashscope_llm_channel.DashscopeLLMChannel'

examples/sample_standard_app/intelligence/agentic/llm/buildin/qwen/channel/qwen3/qwen3_14b_official_channel.yaml

@@ -0,0 +1,8 @@
+channel_name: 'qwen3-14b-official'
+channel_api_key: '${DASHSCOPE_API_KEY}'
+channel_api_base: 'https://dashscope.aliyuncs.com/compatible-mode/v1'
+channel_model_name: 'qwen3-14b'
+model_support_stream: True
+model_support_max_context_length: 131072
+model_is_openai_protocol_compatible: True
+meta_class: 'agentuniverse.llm.llm_channel.dashscope_llm_channel.DashscopeLLMChannel'

examples/sample_standard_app/intelligence/agentic/llm/buildin/qwen/channel/qwen3/qwen3_1_7b_official_channel.yaml

@@ -0,0 +1,8 @@
+channel_name: 'qwen3-1.7b-official'
+channel_api_key: '${DASHSCOPE_API_KEY}'
+channel_api_base: 'https://dashscope.aliyuncs.com/compatible-mode/v1'
+channel_model_name: 'qwen3-1.7b'
+model_support_stream: True
+model_support_max_context_length: 32768
+model_is_openai_protocol_compatible: True
+meta_class: 'agentuniverse.llm.llm_channel.dashscope_llm_channel.DashscopeLLMChannel'

examples/sample_standard_app/intelligence/agentic/llm/buildin/qwen/channel/qwen3/qwen3_235b_a22b_official_channel.yaml

@@ -0,0 +1,8 @@
+channel_name: 'qwen3-235b-a22b'
+channel_api_key: '${DASHSCOPE_API_KEY}'
+channel_api_base: 'https://dashscope.aliyuncs.com/compatible-mode/v1'
+channel_model_name: 'qwen3-235b-a22b'
+model_support_stream: True
+model_support_max_context_length: 131072
+model_is_openai_protocol_compatible: True
+meta_class: 'agentuniverse.llm.llm_channel.dashscope_llm_channel.DashscopeLLMChannel'

examples/sample_standard_app/intelligence/agentic/llm/buildin/qwen/channel/qwen3/qwen3_30b_a3b_official_channel.yaml

@@ -0,0 +1,8 @@
+channel_name: 'qwen3-30b-a3b-official'
+channel_api_key: '${DASHSCOPE_API_KEY}'
+channel_api_base: 'https://dashscope.aliyuncs.com/compatible-mode/v1'
+channel_model_name: 'qwen3-30b-a3b'
+model_support_stream: True
+model_support_max_context_length: 131072
+model_is_openai_protocol_compatible: True
+meta_class: 'agentuniverse.llm.llm_channel.dashscope_llm_channel.DashscopeLLMChannel'

examples/sample_standard_app/intelligence/agentic/llm/buildin/qwen/channel/qwen3/qwen3_32b_official_channel.yaml

@@ -0,0 +1,8 @@
+channel_name: 'qwen3-32b-official'
+channel_api_key: '${DASHSCOPE_API_KEY}'
+channel_api_base: 'https://dashscope.aliyuncs.com/compatible-mode/v1'
+channel_model_name: 'qwen3-32b'
+model_support_stream: True
+model_support_max_context_length: 131072
+model_is_openai_protocol_compatible: True
+meta_class: 'agentuniverse.llm.llm_channel.dashscope_llm_channel.DashscopeLLMChannel'

examples/sample_standard_app/intelligence/agentic/llm/buildin/qwen/channel/qwen3/qwen3_4b_official_channel.yaml

@@ -0,0 +1,8 @@
+channel_name: 'qwen3-4b-official'
+channel_api_key: '${DASHSCOPE_API_KEY}'
+channel_api_base: 'https://dashscope.aliyuncs.com/compatible-mode/v1'
+channel_model_name: 'qwen3-4b'
+model_support_stream: True
+model_support_max_context_length: 131072
+model_is_openai_protocol_compatible: True
+meta_class: 'agentuniverse.llm.llm_channel.dashscope_llm_channel.DashscopeLLMChannel'

examples/sample_standard_app/intelligence/agentic/llm/buildin/qwen/channel/qwen3/qwen3_8b_official_channel.yaml

@@ -0,0 +1,8 @@
+channel_name: 'qwen3-8b-official'
+channel_api_key: '${DASHSCOPE_API_KEY}'
+channel_api_base: 'https://dashscope.aliyuncs.com/compatible-mode/v1'
+channel_model_name: 'qwen3-8b'
+model_support_stream: True
+model_support_max_context_length: 131072
+model_is_openai_protocol_compatible: True
+meta_class: 'agentuniverse.llm.llm_channel.dashscope_llm_channel.DashscopeLLMChannel'

examples/sample_standard_app/intelligence/agentic/llm/buildin/qwen/qwen3/qwen3_0_6b.yaml

@@ -0,0 +1,9 @@
+name: 'qwen3-0.6b'
+description: 'qwen3-0.6b'
+model_name: 'qwen3-0.6b'
+temperature: 0.5
+max_tokens: 8192
+max_context_length: 32768
+streaming: True
+channel: qwen3-0.6b-official
+meta_class: 'agentuniverse.llm.default.qwen_openai_style_llm.QWenOpenAIStyleLLM'

examples/sample_standard_app/intelligence/agentic/llm/buildin/qwen/qwen3/qwen3_14b.yaml

@@ -0,0 +1,9 @@
+name: 'qwen3-14b'
+description: 'qwen3-14b'
+model_name: 'qwen3-14b'
+temperature: 0.5
+max_tokens: 8192
+max_context_length: 131072
+streaming: True
+channel: qwen3-14b-official
+meta_class: 'agentuniverse.llm.default.qwen_openai_style_llm.QWenOpenAIStyleLLM'

examples/sample_standard_app/intelligence/agentic/llm/buildin/qwen/qwen3/qwen3_1_7b.yaml

@@ -0,0 +1,9 @@
+name: 'qwen3-1.7b'
+description: 'qwen3-1.7b'
+model_name: 'qwen3-1.7b'
+temperature: 0.5
+max_tokens: 8192
+max_context_length: 32768
+streaming: True
+channel: qwen3-1.7b-official
+meta_class: 'agentuniverse.llm.default.qwen_openai_style_llm.QWenOpenAIStyleLLM'

examples/sample_standard_app/intelligence/agentic/llm/buildin/qwen/qwen3/qwen3_235b_a22b.yaml

@@ -0,0 +1,9 @@
+name: 'qwen3-235b-a22b'
+description: 'qwen3-235b-a22b'
+model_name: 'qwen3-235b-a22b'
+temperature: 0.5
+max_tokens: 8192
+max_context_length: 131072
+streaming: True
+channel: qwen3-235b-a22b-official
+meta_class: 'agentuniverse.llm.default.qwen_openai_style_llm.QWenOpenAIStyleLLM'

examples/sample_standard_app/intelligence/agentic/llm/buildin/qwen/qwen3/qwen3_30b_a3b.yaml

@@ -0,0 +1,9 @@
+name: 'qwen3-30b-a3b'
+description: 'qwen3-30b-a3b'
+model_name: 'qwen3-30b-a3b'
+temperature: 0.5
+max_tokens: 8192
+max_context_length: 131072
+streaming: True
+channel: qwen3-30b-a3b-official
+meta_class: 'agentuniverse.llm.default.qwen_openai_style_llm.QWenOpenAIStyleLLM'

examples/sample_standard_app/intelligence/agentic/llm/buildin/qwen/qwen3/qwen3_32b.yaml

@@ -0,0 +1,9 @@
+name: 'qwen3-32b'
+description: 'qwen3-32b'
+model_name: 'qwen3-32b'
+temperature: 0.5
+max_tokens: 8192
+max_context_length: 131072
+streaming: True
+channel: qwen3-32b-official
+meta_class: 'agentuniverse.llm.default.qwen_openai_style_llm.QWenOpenAIStyleLLM'

examples/sample_standard_app/intelligence/agentic/llm/buildin/qwen/qwen3/qwen3_4b.yaml

@@ -0,0 +1,9 @@
+name: 'qwen3-4b'
+description: 'qwen3-4b'
+model_name: 'qwen3-4b'
+temperature: 0.5
+max_tokens: 8192
+max_context_length: 131072
+streaming: True
+channel: qwen3-4b-official
+meta_class: 'agentuniverse.llm.default.qwen_openai_style_llm.QWenOpenAIStyleLLM'

examples/sample_standard_app/intelligence/agentic/llm/buildin/qwen/qwen3/qwen3_8b.yaml

@@ -0,0 +1,9 @@
+name: 'qwen3-8b'
+description: 'qwen3-8b'
+model_name: 'qwen3-8b'
+temperature: 0.5
+max_tokens: 8192
+max_context_length: 131072
+streaming: True
+channel: qwen3-8b-official
+meta_class: 'agentuniverse.llm.default.qwen_openai_style_llm.QWenOpenAIStyleLLM'