Skip to content

Add support for Yi Model API #1635

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
binary-husky merged 3 commits into from
Mar 16, 2024
Merged

Add support for Yi Model API #1635

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
78fc006
更新以支持零一万物模型
Menghuan1918 Mar 16, 2024
4c83469
删除newbing
binary-husky Mar 16, 2024
f8c1fb9
修改config
binary-husky Mar 16, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,6 +47,7 @@
# "gpt-3.5-turbo-0613", "gpt-3.5-turbo-16k-0613", "gpt-3.5-turbo-0125"
# "claude-3-sonnet-20240229","claude-3-opus-20240229", "claude-2.1", "claude-instant-1.2",
# "moss", "llama2", "chatglm_onnx", "internlm", "jittorllms_pangualpha", "jittorllms_llama",
# "yi-34b-chat-0205", "yi-34b-chat-200k"
# ]
# --- --- --- ---
# 此外，为了更灵活地接入one-api多模型管理界面，您还可以在接入one-api时，
Expand Down Expand Up @@ -212,6 +213,10 @@
MOONSHOT_API_KEY = ""


# 零一万物(Yi Model) API KEY
YIMODEL_API_KEY = ""


# Mathpix 拥有执行PDF的OCR功能，但是需要注册账号
MATHPIX_APPID = ""
MATHPIX_APPKEY = ""
Expand Down Expand Up @@ -313,6 +318,9 @@
├── "glm-4", "glm-3-turbo", "zhipuai" 智谱AI大模型
│ └── ZHIPUAI_API_KEY
│
├── "yi-34b-chat-0205", "yi-34b-chat-200k" 等零一万物(Yi Model)大模型
│ └── YIMODEL_API_KEY
│
├── "qwen-turbo" 等通义千问大模型
│ └── DASHSCOPE_API_KEY
│
Expand Down
62 changes: 43 additions & 19 deletions request_llms/bridge_all.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,6 +63,7 @@ def decode(self, *args, **kwargs):
newbing_endpoint = "wss://sydney.bing.com/sydney/ChatHub"
gemini_endpoint = "https://generativelanguage.googleapis.com/v1beta/models"
claude_endpoint = "https://api.anthropic.com"
yimodel_endpoint = "https://api.lingyiwanwu.com/v1/chat/completions"

if not AZURE_ENDPOINT.endswith('/'): AZURE_ENDPOINT += '/'
azure_endpoint = AZURE_ENDPOINT + f'openai/deployments/{AZURE_ENGINE}/chat/completions?api-version=2023-05-15'
Expand All @@ -80,6 +81,7 @@ def decode(self, *args, **kwargs):
if newbing_endpoint in API_URL_REDIRECT: newbing_endpoint = API_URL_REDIRECT[newbing_endpoint]
if gemini_endpoint in API_URL_REDIRECT: gemini_endpoint = API_URL_REDIRECT[gemini_endpoint]
if claude_endpoint in API_URL_REDIRECT: claude_endpoint = API_URL_REDIRECT[claude_endpoint]
if yimodel_endpoint in API_URL_REDIRECT: yimodel_endpoint = API_URL_REDIRECT[yimodel_endpoint]

# 获取tokenizer
tokenizer_gpt35 = LazyloadTiktoken("gpt-3.5-turbo")
Expand Down Expand Up @@ -316,6 +318,7 @@ def decode(self, *args, **kwargs):
"moonshot-v1-8k": {
"fn_with_ui": moonshot_ui,
"fn_without_ui": moonshot_no_ui,
"can_multi_thread": True,
"endpoint": None,
"max_token": 1024 * 8,
"tokenizer": tokenizer_gpt35,
Expand All @@ -324,6 +327,7 @@ def decode(self, *args, **kwargs):
"moonshot-v1-32k": {
"fn_with_ui": moonshot_ui,
"fn_without_ui": moonshot_no_ui,
"can_multi_thread": True,
"endpoint": None,
"max_token": 1024 * 32,
"tokenizer": tokenizer_gpt35,
Expand All @@ -332,6 +336,7 @@ def decode(self, *args, **kwargs):
"moonshot-v1-128k": {
"fn_with_ui": moonshot_ui,
"fn_without_ui": moonshot_no_ui,
"can_multi_thread": True,
"endpoint": None,
"max_token": 1024 * 128,
"tokenizer": tokenizer_gpt35,
Expand Down Expand Up @@ -473,22 +478,6 @@ def decode(self, *args, **kwargs):
"token_cnt": get_token_num_gpt35,
}
})
if "newbing-free" in AVAIL_LLM_MODELS:
try:
from .bridge_newbingfree import predict_no_ui_long_connection as newbingfree_noui
from .bridge_newbingfree import predict as newbingfree_ui
model_info.update({
"newbing-free": {
"fn_with_ui": newbingfree_ui,
"fn_without_ui": newbingfree_noui,
"endpoint": newbing_endpoint,
"max_token": 4096,
"tokenizer": tokenizer_gpt35,
"token_cnt": get_token_num_gpt35,
}
})
except:
print(trimmed_format_exc())
if "newbing" in AVAIL_LLM_MODELS: # same with newbing-free
try:
from .bridge_newbingfree import predict_no_ui_long_connection as newbingfree_noui
Expand Down Expand Up @@ -521,6 +510,7 @@ def decode(self, *args, **kwargs):
})
except:
print(trimmed_format_exc())
# -=-=-=-=-=-=- 上海AI-LAB书生大模型 -=-=-=-=-=-=-
if "internlm" in AVAIL_LLM_MODELS:
try:
from .bridge_internlm import predict_no_ui_long_connection as internlm_noui
Expand Down Expand Up @@ -553,6 +543,7 @@ def decode(self, *args, **kwargs):
})
except:
print(trimmed_format_exc())
# -=-=-=-=-=-=- 通义-本地模型 -=-=-=-=-=-=-
if "qwen-local" in AVAIL_LLM_MODELS:
try:
from .bridge_qwen_local import predict_no_ui_long_connection as qwen_local_noui
Expand All @@ -570,6 +561,7 @@ def decode(self, *args, **kwargs):
})
except:
print(trimmed_format_exc())
# -=-=-=-=-=-=- 通义-在线模型 -=-=-=-=-=-=-
if "qwen-turbo" in AVAIL_LLM_MODELS or "qwen-plus" in AVAIL_LLM_MODELS or "qwen-max" in AVAIL_LLM_MODELS: # zhipuai
try:
from .bridge_qwen import predict_no_ui_long_connection as qwen_noui
Expand Down Expand Up @@ -605,7 +597,35 @@ def decode(self, *args, **kwargs):
})
except:
print(trimmed_format_exc())
if "spark" in AVAIL_LLM_MODELS: # 讯飞星火认知大模型
# -=-=-=-=-=-=- 零一万物模型 -=-=-=-=-=-=-
if "yi-34b-chat-0205" in AVAIL_LLM_MODELS or "yi-34b-chat-200k" in AVAIL_LLM_MODELS: # zhipuai
try:
from .bridge_yimodel import predict_no_ui_long_connection as yimodel_noui
from .bridge_yimodel import predict as yimodel_ui
model_info.update({
"yi-34b-chat-0205": {
"fn_with_ui": yimodel_ui,
"fn_without_ui": yimodel_noui,
"can_multi_thread": False, # 目前来说，默认情况下并发量极低，因此禁用
"endpoint": yimodel_endpoint,
"max_token": 4000,
"tokenizer": tokenizer_gpt35,
"token_cnt": get_token_num_gpt35,
},
"yi-34b-chat-200k": {
"fn_with_ui": yimodel_ui,
"fn_without_ui": yimodel_noui,
"can_multi_thread": False, # 目前来说，默认情况下并发量极低，因此禁用
"endpoint": yimodel_endpoint,
"max_token": 200000,
"tokenizer": tokenizer_gpt35,
"token_cnt": get_token_num_gpt35,
},
})
except:
print(trimmed_format_exc())
# -=-=-=-=-=-=- 讯飞星火认知大模型 -=-=-=-=-=-=-
if "spark" in AVAIL_LLM_MODELS:
try:
from .bridge_spark import predict_no_ui_long_connection as spark_noui
from .bridge_spark import predict as spark_ui
Expand Down Expand Up @@ -681,6 +701,7 @@ def decode(self, *args, **kwargs):
})
except:
print(trimmed_format_exc())
# -=-=-=-=-=-=- 智谱 -=-=-=-=-=-=-
if "zhipuai" in AVAIL_LLM_MODELS: # zhipuai 是glm-4的别名，向后兼容配置
try:
model_info.update({
Expand All @@ -695,6 +716,7 @@ def decode(self, *args, **kwargs):
})
except:
print(trimmed_format_exc())
# -=-=-=-=-=-=- 幻方-深度求索大模型 -=-=-=-=-=-=-
if "deepseekcoder" in AVAIL_LLM_MODELS: # deepseekcoder
try:
from .bridge_deepseekcoder import predict_no_ui_long_connection as deepseekcoder_noui
Expand All @@ -711,6 +733,8 @@ def decode(self, *args, **kwargs):
})
except:
print(trimmed_format_exc())


# -=-=-=-=-=-=- one-api 对齐支持 -=-=-=-=-=-=-
for model in [m for m in AVAIL_LLM_MODELS if m.startswith("one-api-")]:
# 为了更灵活地接入one-api多模型管理界面，设计了此接口，例子：AVAIL_LLM_MODELS = ["one-api-mixtral-8x7b(max_token=6666)"]
Expand All @@ -735,8 +759,8 @@ def decode(self, *args, **kwargs):
})


# <-- 用于定义和切换多个azure模型 -->
AZURE_CFG_ARRAY = get_conf("AZURE_CFG_ARRAY")
# -=-=-=-=-=-=- azure模型对齐支持 -=-=-=-=-=-=-
AZURE_CFG_ARRAY = get_conf("AZURE_CFG_ARRAY") # <-- 用于定义和切换多个azure模型 -->
if len(AZURE_CFG_ARRAY) > 0:
for azure_model_name, azure_cfg_dict in AZURE_CFG_ARRAY.items():
# 可能会覆盖之前的配置，但这是意料之中的
Expand Down
Loading