forked from eosphoros-ai/DB-GPT
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy path.env.template
146 lines (119 loc) · 6.2 KB
/
.env.template
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
#*******************************************************************#
#** DB-GPT - GENERAL SETTINGS **#
#*******************************************************************#
## DISABLED_COMMAND_CATEGORIES - The list of categories of commands that are disabled. Each of the below are an option:
## pilot.commands.query_execute
## For example, to disable coding related features, uncomment the next line
# DISABLED_COMMAND_CATEGORIES=
#*******************************************************************#
#** Webserver Port **#
#*******************************************************************#
WEB_SERVER_PORT=7860
#*******************************************************************#
#*** LLM PROVIDER ***#
#*******************************************************************#
# TEMPERATURE=0
#*******************************************************************#
#** LLM MODELS **#
#*******************************************************************#
# LLM_MODEL, see /pilot/configs/model_config.LLM_MODEL_CONFIG
LLM_MODEL=vicuna-13b
MODEL_SERVER=http://127.0.0.1:8000
LIMIT_MODEL_CONCURRENCY=5
MAX_POSITION_EMBEDDINGS=4096
QUANTIZE_QLORA=True
QUANTIZE_8bit=True
# QUANTIZE_4bit=False
## SMART_LLM_MODEL - Smart language model (Default: vicuna-13b)
## FAST_LLM_MODEL - Fast language model (Default: chatglm-6b)
# SMART_LLM_MODEL=vicuna-13b
# FAST_LLM_MODEL=chatglm-6b
## Proxy llm backend, this configuration is only valid when "LLM_MODEL=proxyllm", When we use the rest API provided by deployment frameworks like fastchat as a proxyllm,
## "PROXYLLM_BACKEND" is the model they actually deploy. We can use "PROXYLLM_BACKEND" to load the prompt of the corresponding scene.
# PROXYLLM_BACKEND=
#*******************************************************************#
#** EMBEDDING SETTINGS **#
#*******************************************************************#
EMBEDDING_MODEL=text2vec
KNOWLEDGE_CHUNK_SIZE=500
KNOWLEDGE_SEARCH_TOP_SIZE=5
## EMBEDDING_TOKENIZER - Tokenizer to use for chunking large inputs
## EMBEDDING_TOKEN_LIMIT - Chunk size limit for large inputs
# EMBEDDING_MODEL=all-MiniLM-L6-v2
# EMBEDDING_TOKENIZER=all-MiniLM-L6-v2
# EMBEDDING_TOKEN_LIMIT=8191
#*******************************************************************#
#** DATABASE SETTINGS **#
#*******************************************************************#
### SQLite database (Current default database)
LOCAL_DB_PATH=data/default_sqlite.db
LOCAL_DB_TYPE=sqlite
### MYSQL database
# LOCAL_DB_TYPE=mysql
# LOCAL_DB_USER=root
# LOCAL_DB_PASSWORD=aa12345678
# LOCAL_DB_HOST=127.0.0.1
# LOCAL_DB_PORT=3306
### MILVUS
## MILVUS_ADDR - Milvus remote address (e.g. localhost:19530)
## MILVUS_USERNAME - username for your Milvus database
## MILVUS_PASSWORD - password for your Milvus database
## MILVUS_SECURE - True to enable TLS. (Default: False)
## Setting MILVUS_ADDR to a `https://` URL will override this setting.
## MILVUS_COLLECTION - Milvus collection, change it if you want to start a new memory and retain the old memory.
# MILVUS_ADDR=localhost:19530
# MILVUS_USERNAME=
# MILVUS_PASSWORD=
# MILVUS_SECURE=
# MILVUS_COLLECTION=dbgpt
#*******************************************************************#
#** COMMANDS **#
#*******************************************************************#
EXECUTE_LOCAL_COMMANDS=False
#*******************************************************************#
#** ALLOWLISTED PLUGINS **#
#*******************************************************************#
#ALLOWLISTED_PLUGINS - Sets the listed plugins that are allowed (Example: plugin1,plugin2,plugin3)
#DENYLISTED_PLUGINS - Sets the listed plugins that are not allowed (Example: plugin1,plugin2,plugin3)
ALLOWLISTED_PLUGINS=
DENYLISTED_PLUGINS=
#*******************************************************************#
#** CHAT PLUGIN SETTINGS **#
#*******************************************************************#
# CHAT_MESSAGES_ENABLED - Enable chat messages (Default: False)
# CHAT_MESSAGES_ENABLED=False
#*******************************************************************#
#** VECTOR STORE SETTINGS **#
#*******************************************************************#
VECTOR_STORE_TYPE=Chroma
#MILVUS_URL=127.0.0.1
#MILVUS_PORT=19530
#MILVUS_USERNAME
#MILVUS_PASSWORD
#MILVUS_SECURE=
#*******************************************************************#
#** WebServer Language Support **#
#*******************************************************************#
LANGUAGE=en
#LANGUAGE=zh
#*******************************************************************#
# ** PROXY_SERVER (openai interface | chatGPT proxy service), use chatGPT as your LLM.
# ** if your server can visit openai, please set PROXY_SERVER_URL=https://api.openai.com/v1/chat/completions
# ** else if you have a chatgpt proxy server, you can set PROXY_SERVER_URL={your-proxy-serverip:port/xxx}
#*******************************************************************#
PROXY_API_KEY={your-openai-sk}
PROXY_SERVER_URL=https://api.openai.com/v1/chat/completions
# from https://bard.google.com/ f12-> application-> __Secure-1PSID
BARD_PROXY_API_KEY={your-bard-token}
#*******************************************************************#
#** SUMMARY_CONFIG **#
#*******************************************************************#
SUMMARY_CONFIG=FAST
#*******************************************************************#
#** MUlti-GPU **#
#*******************************************************************#
## See https://developer.nvidia.com/blog/cuda-pro-tip-control-gpu-visibility-cuda_visible_devices/
## If CUDA_VISIBLE_DEVICES is not configured, all available gpus will be used
# CUDA_VISIBLE_DEVICES=0
## You can configure the maximum memory used by each GPU.
# MAX_GPU_MEMORY=16Gib