-
Notifications
You must be signed in to change notification settings - Fork 173
/
Copy pathconfig.ini
149 lines (127 loc) · 5.36 KB
/
config.ini
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
[feature_store]
# `feature_store.py` use this throttle to distinct `good_questions` and `bad_questions`
reject_throttle = -1.0
# text2vec model, support local relative path, huggingface repo and URL.
# for example:
# "maidalun1020/bce-embedding-base_v1"
# "BAAI/bge-m3"
# "https://api.siliconflow.cn/v1/embeddings"
embedding_model_path = "maidalun1020/bce-embedding-base_v1"
# reranker model, support list:
# "maidalun1020/bce-reranker-base_v1"
# "BAAI/bge-reranker-v2-minicpm-layerwise"
# "https://api.siliconflow.cn/v1/rerank"
reranker_model_path = "maidalun1020/bce-reranker-base_v1"
# if using `siliconcloud` API as `embedding_model_path` or `reranker_model_path`, give the token
api_token = ""
api_rpm = 1000
api_tpm = 40000
work_dir = "workdir"
[web_search]
engine = "serper"
# web search engine support ddgs and serper
# For ddgs, see https://pypi.org/project/duckduckgo-search
# For serper, check https://serper.dev/api-key to get a free API key
serper_x_api_key = "YOUR-API-KEY-HERE"
domain_partial_order = ["arxiv.org", "openai.com", "pytorch.org", "readthedocs.io", "nvidia.com", "stackoverflow.com", "juejin.cn", "zhuanlan.zhihu.com", "www.cnblogs.com"]
save_dir = "logs/web_search_result"
[llm]
[llm.server]
# remote LLM service configuration
# support "gpt", "kimi", "deepseek", "zhipuai", "step", "internlm", "xi-api", "vllm", "siliconcloud" and "ppio"
# support "siliconcloud", see https://siliconflow.cn/zh-cn/siliconcloud
# xi-api and alles-apin is chinese gpt proxy
# for internlm, see https://internlm.intern-ai.org.cn/api/document
remote_type = "kimi"
remote_api_key = "sk_XXXXXXXXXXXXXXXXXXXXXx"
# max token length for LLM input.
# use 128000 for kimi, 192000 for gpt/xi-api, 16000 for deepseek, 128000 for zhipuai, 32000 for others.
remote_llm_max_text_length = 32000
# openai API model type, support model list:
# "auto" for kimi. To save money, we auto select model name by prompt length.
# "auto" for stepfun, see https://platform.stepfun.com/
# "gpt-4-0613" for gpt/xi-api
# "deepseek-chat" for deepseek
# "glm-4" for zhipuai
# "vllm" for `http://127.0.0.1:8000/v1/`
# "internlm3-latest" for `https://internlm.intern-ai.org.cn`
# siliconcloud
# for example "alibaba/Qwen1.5-110B-Chat", see https://siliconflow.readme.io/reference/chat-completions-1
# ppio
# for example "thudm/glm-4-9b-chat", see https://ppinfra.com/model-api/console
remote_llm_model = "auto"
# request per minute
rpm = 500
tpm = 200000
[worker]
# enable web search or not
enable_web_search = 1
save_path = "logs/work.txt"
[worker.time]
enable = 0
start = "00:00:00"
end = "23:59:59"
has_weekday = 1
[frontend]
# chat group assistant type, support "lark_group", "wechat_personal", "wechat_wkteam" and "none"
# for "lark_group", open https://open.feishu.cn/document/home/introduction-to-custom-app-development/self-built-application-development-process to create one
# for "wechat_personal", read ./docs/add_wechat_group_zh.md to setup gateway
# for "wkteam", see https://wkteam.cn/
type = "none"
# for "lark", it is chat group webhook url, send reply to group, for example "https://open.feishu.cn/open-apis/bot/v2/hook/xxxxxxxxxxxxxxx"
# for "lark_group", it is the url to fetch chat group message, for example "http://101.133.161.20:6666/fetch", `101.133.161.20` is your own public IPv4 addr
# for "wechat_personal", it is useless
webhook_url = "https://open.feishu.cn/open-apis/bot/v2/hook/xxxxxxxxxxxxxxx"
# when a new group chat message is received, should it be processed immediately or wait for 18 seconds in case the user hasn't finished speaking?
# support "immediate"
message_process_policy = "immediate"
[frontend.lark_group]
# "lark_group" configuration examples, use your own app_id and secret !!!
app_id = "cli_a53a34dcb778500e"
app_secret = "2ajhg1ixSvlNm1bJkH4tJhPfTCsGGHT1"
encrypt_key = "abc"
verification_token = "def"
[frontend.wechat_personal]
# "wechat_personal" listen port
bind_port = 9527
[frontend.wechat_wkteam]
# wechat message callback server ip
callback_ip = "101.133.161.11"
callback_port = 9528
# public redis config
redis_host = "101.133.161.11"
redis_port = "6380"
redis_passwd = "hxd123"
# wkteam
account = ""
password = ""
# !!! `proxy` is very import parameter, it's your account location
# 1：北京 2：天津 3：上海 4：重庆 5：河北
# 6：山西 7：江苏 8：浙江 9：安徽 10：福建
# 11：江西 12：山东 13：河南 14：湖北 15：湖南
# 16：广东 17：海南 18：四川 20：陕西
# bad proxy would cause account deactivation !!!
proxy = -1
# save dir
dir = "wkteam"
# 群号和介绍
# 茴香豆相关
[frontend.wechat_wkteam.43925126702]
name = "茴香豆群（大暑）"
introduction = "github https://github.com/InternLM/HuixiangDou 用户体验群"
[frontend.wechat_wkteam.44546611710]
name = "茴香豆群（立夏）"
introduction = "github https://github.com/InternLM/HuixiangDou 用户体验群"
[frontend.wechat_wkteam.38720590618]
name = "茴香豆群（惊蛰）"
introduction = "github https://github.com/InternLM/HuixiangDou 用户体验群"
[frontend.wechat_wkteam.48437885473]
name = "茴香豆群（谷雨）"
introduction = "github https://github.com/InternLM/HuixiangDou 用户体验群"
[frontend.wechat_wkteam.34744063953]
name = "茴香豆群（雨水）"
introduction = "github https://github.com/InternLM/HuixiangDou 用户体验群"
# github.com/tencent/ncnn contributors
[frontend.wechat_wkteam.18356748488]
name = "卷卷群"
introduction = "ncnn contributors group"