wangtinghu/agentUniverse
1
0
Fork 0
mirror of https://github.com/agentuniverse-ai/agentUniverse.git synced 2026-02-09 01:59:19 +08:00
Code Issues Packages Projects Releases Wiki Activity

support 4.5

Browse Source
This commit is contained in:
fangfangssj
2025-07-12 23:47:32 +08:00
parent 45ded8f467
commit b6ad038c83
10 changed files with 225 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@@ -38,7 +38,7 @@ The LLM model integration can be accomplished with simple configuration, current
|<img src="https://github.com/user-attachments/assets/334c7f09-7eae-4a65-a70f-2e6531964224" height="25">|Gemini| Gemini 2.5 Pro、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/79572d9a-29d5-4c0e-a336-ce3f8018fb05" height="25">|WenXin| ERNIE 4.5 Turbo、ERNIE 4.5、ERNIE 4.0 Turbo、ERNIE 4.0、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、… |

2
README_zh.md
View File

@@ -35,7 +35,7 @@ The LLM model integration can be accomplished with simple configuration, current
|<img src="https://github.com/user-attachments/assets/334c7f09-7eae-4a65-a70f-2e6531964224" height="25">|Gemini| Gemini 2.5 Pro、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/79572d9a-29d5-4c0e-a336-ce3f8018fb05" height="25">|WenXin| ERNIE 4.5 Turbo、ERNIE 4.5、ERNIE 4.0 Turbo、ERNIE 4.0、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、… |

4
agentuniverse/llm/default/wenxin_llm.py
View File

@@ -21,7 +21,9 @@ from agentuniverse.llm.llm_output import LLMOutput
from agentuniverse.llm.wenxin_langchain_instance import WenXinLangChainInstance
TokenModelList = [
'Ernie-4.0-8k',
'ernie-4.5-turbo-32k'
'ernie-4.5-8k-preview'
'ernie-4.0-8k',
'ernie-3.5-8k',
'ernie-speed-8k',
'ernie-speed-128k',

6
agentuniverse_product/base/constant/llm_constant.py
View File

@@ -17,10 +17,12 @@ LLM_MODEL_NAME = {
'qwen2.5-72b-instruct', 'qwen2.5-32b-instruct', 'qwen2.5-14b-instruct', 'qwen2.5-7b-instruct'],
'wenxin_llm': ['ERNIE-Speed-AppBuilder-8K-0516', 'ERNIE-Lite-8K-0725', 'ERNIE-Speed-128K', 'ERNIE-3.5-128K',
'ERNIE-3.5-8K-0701', 'ERNIE-4.0-8K-0613', 'ERNIE-4.0-8K-Preview', 'ERNIE-3.5-8K-Preview',
'ERNIE-Tiny-8K', 'ERNIE-4.0-8K-Latest', 'ERNIE-4.0-Turbo-8K'],
'ERNIE-Tiny-8K', 'ERNIE-4.0-8K-Latest', 'ERNIE-4.0-Turbo-8K','ERNIE-4.5-8K-Preview',
'ERNIE-4.5-Turbo-32K', 'ERNIE-4.5-Turbo-128K'],
'default_wenxin_llm': ['ERNIE-Speed-AppBuilder-8K-0516', 'ERNIE-Lite-8K-0725', 'ERNIE-Speed-128K', 'ERNIE-3.5-128K',
'ERNIE-3.5-8K-0701', 'ERNIE-4.0-8K-0613', 'ERNIE-4.0-8K-Preview', 'ERNIE-3.5-8K-Preview',
'ERNIE-Tiny-8K', 'ERNIE-4.0-8K-Latest', 'ERNIE-4.0-Turbo-8K'],
'ERNIE-Tiny-8K', 'ERNIE-4.0-8K-Latest', 'ERNIE-4.0-Turbo-8K','ERNIE-4.5-8K-Preview',
'ERNIE-4.5-Turbo-32K', 'ERNIE-4.5-Turbo-128K'],
'kimi_llm': ['moonshot-v1-8k', 'moonshot-v1-32k', 'moonshot-v1-128k'],
'default_kimi_llm': ['moonshot-v1-8k', 'moonshot-v1-32k', 'moonshot-v1-128k'],
'deepseek_llm': ['deepseek-chat', 'deepseek-coder', 'deepseek-reasoner', 'deepseek-v3', 'deepseek-r1',

36
examples/sample_apps/toolkit_demo_app/intelligence/agentic/llm/buildin/wenxin/ernie_4_5_8k_preview.yaml Normal file
View File

@@ -0,0 +1,36 @@
name: 'ERNIE-4.5-8K-Preview'
description: 'Baidu ERNIE-4.5-8K-Preview model'
model_name: 'ERNIE-4.5-8K-Preview'
max_tokens: 1000
streaming: true
#
# There are three ways to configure the api_key:
#
# 1. Direct String Value:
# Directly input the API key as a string.
# Example: api_key: 'sk-xxxxxxxxxxxxxxxx'
#
# 2. Environment Variable Placeholder:
# Use ${VARIABLE_NAME} syntax to load from environment variables. When agentUniverse starts,
# it will automatically read the value from environment variables during YAML configuration parsing.
# Example: api_key: '${QIANFAN_AK}'
#
# 3. Custom Function Loading:
# Use @FUNC annotation to dynamically load the API key at runtime through a custom function.
# Example: api_key: '@FUNC(load_api_key(model_name="wenxin"))'
# The function should be defined in the YamlFuncExtension class within yaml_func_extension.py
# When agentUniverse loads this configuration, it will:
# - Parse the @FUNC annotation
# - Execute the load_api_key function with the given argument
# - Replace the annotation with the function's return value
#
# The same configuration methods apply to other parameters below (api_base, organization, proxy)
#
# Note: Current configuration uses the second method (Environment Variable Placeholder)
#
api_key: '${QIANFAN_AK}'
secret_key: '${QIANFAN_SK}'
metadata:
type: 'LLM'
module: 'agentuniverse.llm.default.wenxin_llm'
class: 'WenXinLLM'

36
examples/sample_apps/toolkit_demo_app/intelligence/agentic/llm/buildin/wenxin/ernie_4_5_turbo_128k.yaml Normal file
View File

@@ -0,0 +1,36 @@
name: 'Ernie-4.5-turbo-128k'
description: 'Baidu Ernie-4.5-turbo-128k model'
model_name: 'Ernie-4.5-turbo-128k'
max_tokens: 1000
streaming: true
#
# There are three ways to configure the api_key:
#
# 1. Direct String Value:
# Directly input the API key as a string.
# Example: api_key: 'sk-xxxxxxxxxxxxxxxx'
#
# 2. Environment Variable Placeholder:
# Use ${VARIABLE_NAME} syntax to load from environment variables. When agentUniverse starts,
# it will automatically read the value from environment variables during YAML configuration parsing.
# Example: api_key: '${QIANFAN_AK}'
#
# 3. Custom Function Loading:
# Use @FUNC annotation to dynamically load the API key at runtime through a custom function.
# Example: api_key: '@FUNC(load_api_key(model_name="wenxin"))'
# The function should be defined in the YamlFuncExtension class within yaml_func_extension.py
# When agentUniverse loads this configuration, it will:
# - Parse the @FUNC annotation
# - Execute the load_api_key function with the given argument
# - Replace the annotation with the function's return value
#
# The same configuration methods apply to other parameters below (api_base, organization, proxy)
#
# Note: Current configuration uses the second method (Environment Variable Placeholder)
#
api_key: '${QIANFAN_AK}'
secret_key: '${QIANFAN_SK}'
metadata:
type: 'LLM'
module: 'agentuniverse.llm.default.wenxin_llm'
class: 'WenXinLLM'

36
examples/sample_apps/toolkit_demo_app/intelligence/agentic/llm/buildin/wenxin/ernie_4_5_turbo_32k.yaml Normal file
View File

@@ -0,0 +1,36 @@
name: 'Ernie-4.5-turbo-32k'
description: 'Baidu Ernie-4.5-turbo-32k model'
model_name: 'Ernie-4.5-turbo-32k'
max_tokens: 1000
streaming: true
#
# There are three ways to configure the api_key:
#
# 1. Direct String Value:
# Directly input the API key as a string.
# Example: api_key: 'sk-xxxxxxxxxxxxxxxx'
#
# 2. Environment Variable Placeholder:
# Use ${VARIABLE_NAME} syntax to load from environment variables. When agentUniverse starts,
# it will automatically read the value from environment variables during YAML configuration parsing.
# Example: api_key: '${QIANFAN_AK}'
#
# 3. Custom Function Loading:
# Use @FUNC annotation to dynamically load the API key at runtime through a custom function.
# Example: api_key: '@FUNC(load_api_key(model_name="wenxin"))'
# The function should be defined in the YamlFuncExtension class within yaml_func_extension.py
# When agentUniverse loads this configuration, it will:
# - Parse the @FUNC annotation
# - Execute the load_api_key function with the given argument
# - Replace the annotation with the function's return value
#
# The same configuration methods apply to other parameters below (api_base, organization, proxy)
#
# Note: Current configuration uses the second method (Environment Variable Placeholder)
#
api_key: '${QIANFAN_AK}'
secret_key: '${QIANFAN_SK}'
metadata:
type: 'LLM'
module: 'agentuniverse.llm.default.wenxin_llm'
class: 'WenXinLLM'

36
examples/sample_standard_app/intelligence/agentic/llm/buildin/wenxin/ernie_4_5_8k_preview.yaml Normal file
View File

@@ -0,0 +1,36 @@
name: 'ERNIE-4.5-8K-Preview'
description: 'Baidu ERNIE-4.5-8K-Preview model'
model_name: 'ERNIE-4.5-8K-Preview'
max_tokens: 1000
streaming: true
#
# There are three ways to configure the api_key:
#
# 1. Direct String Value:
# Directly input the API key as a string.
# Example: api_key: 'sk-xxxxxxxxxxxxxxxx'
#
# 2. Environment Variable Placeholder:
# Use ${VARIABLE_NAME} syntax to load from environment variables. When agentUniverse starts,
# it will automatically read the value from environment variables during YAML configuration parsing.
# Example: api_key: '${QIANFAN_AK}'
#
# 3. Custom Function Loading:
# Use @FUNC annotation to dynamically load the API key at runtime through a custom function.
# Example: api_key: '@FUNC(load_api_key(model_name="wenxin"))'
# The function should be defined in the YamlFuncExtension class within yaml_func_extension.py
# When agentUniverse loads this configuration, it will:
# - Parse the @FUNC annotation
# - Execute the load_api_key function with the given argument
# - Replace the annotation with the function's return value
#
# The same configuration methods apply to other parameters below (api_base, organization, proxy)
#
# Note: Current configuration uses the second method (Environment Variable Placeholder)
#
api_key: '${QIANFAN_AK}'
secret_key: '${QIANFAN_SK}'
metadata:
type: 'LLM'
module: 'agentuniverse.llm.default.wenxin_llm'
class: 'WenXinLLM'

36
examples/sample_standard_app/intelligence/agentic/llm/buildin/wenxin/ernie_4_5_turbo_128k.yaml Normal file
View File

@@ -0,0 +1,36 @@
name: 'Ernie-4.5-turbo-128k'
description: 'Baidu Ernie-4.5-turbo-128k model'
model_name: 'Ernie-4.5-turbo-128k'
max_tokens: 1000
streaming: true
#
# There are three ways to configure the api_key:
#
# 1. Direct String Value:
# Directly input the API key as a string.
# Example: api_key: 'sk-xxxxxxxxxxxxxxxx'
#
# 2. Environment Variable Placeholder:
# Use ${VARIABLE_NAME} syntax to load from environment variables. When agentUniverse starts,
# it will automatically read the value from environment variables during YAML configuration parsing.
# Example: api_key: '${QIANFAN_AK}'
#
# 3. Custom Function Loading:
# Use @FUNC annotation to dynamically load the API key at runtime through a custom function.
# Example: api_key: '@FUNC(load_api_key(model_name="wenxin"))'
# The function should be defined in the YamlFuncExtension class within yaml_func_extension.py
# When agentUniverse loads this configuration, it will:
# - Parse the @FUNC annotation
# - Execute the load_api_key function with the given argument
# - Replace the annotation with the function's return value
#
# The same configuration methods apply to other parameters below (api_base, organization, proxy)
#
# Note: Current configuration uses the second method (Environment Variable Placeholder)
#
api_key: '${QIANFAN_AK}'
secret_key: '${QIANFAN_SK}'
metadata:
type: 'LLM'
module: 'agentuniverse.llm.default.wenxin_llm'
class: 'WenXinLLM'

36
examples/sample_standard_app/intelligence/agentic/llm/buildin/wenxin/ernie_4_5_turbo_32k.yaml Normal file
View File

@@ -0,0 +1,36 @@
name: 'Ernie-4.5-turbo-32k'
description: 'Baidu Ernie-4.5-turbo-32k model'
model_name: 'Ernie-4.5-turbo-32k'
max_tokens: 1000
streaming: true
#
# There are three ways to configure the api_key:
#
# 1. Direct String Value:
# Directly input the API key as a string.
# Example: api_key: 'sk-xxxxxxxxxxxxxxxx'
#
# 2. Environment Variable Placeholder:
# Use ${VARIABLE_NAME} syntax to load from environment variables. When agentUniverse starts,
# it will automatically read the value from environment variables during YAML configuration parsing.
# Example: api_key: '${QIANFAN_AK}'
#
# 3. Custom Function Loading:
# Use @FUNC annotation to dynamically load the API key at runtime through a custom function.
# Example: api_key: '@FUNC(load_api_key(model_name="wenxin"))'
# The function should be defined in the YamlFuncExtension class within yaml_func_extension.py
# When agentUniverse loads this configuration, it will:
# - Parse the @FUNC annotation
# - Execute the load_api_key function with the given argument
# - Replace the annotation with the function's return value
#
# The same configuration methods apply to other parameters below (api_base, organization, proxy)
#
# Note: Current configuration uses the second method (Environment Variable Placeholder)
#
api_key: '${QIANFAN_AK}'
secret_key: '${QIANFAN_SK}'
metadata:
type: 'LLM'
module: 'agentuniverse.llm.default.wenxin_llm'
class: 'WenXinLLM'