forked from eosphoros-ai/DB-GPT
-
Notifications
You must be signed in to change notification settings - Fork 0
/
.env.template
222 lines (184 loc) · 9.15 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
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
#*******************************************************************#
#** 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 dbgpt/configs/model_config.LLM_MODEL_CONFIG
LLM_MODEL=vicuna-13b-v1.5
## LLM model path, by default, DB-GPT will read the model path from LLM_MODEL_CONFIG based on the LLM_MODEL.
## Of course you can specify your model path according to LLM_MODEL_PATH
## In DB-GPT, the priority from high to low to read model path:
## 1. environment variable with key: {LLM_MODEL}_MODEL_PATH (Avoid multi-model conflicts)
## 2. environment variable with key: MODEL_PATH
## 3. environment variable with key: LLM_MODEL_PATH
## 4. the config in dbgpt/configs/model_config.LLM_MODEL_CONFIG
# LLM_MODEL_PATH=/app/models/vicuna-13b-v1.5
# LLM_PROMPT_TEMPLATE=vicuna_v1.1
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=
### You can configure parameters for a specific model with {model name}_{config key}=xxx
### See dbgpt/model/parameter.py
## prompt template for current model
# llama_cpp_prompt_template=vicuna_v1.1
## llama-2-70b must be 8
# llama_cpp_n_gqa=8
## Model path
# llama_cpp_model_path=/data/models/TheBloke/vicuna-13B-v1.5-GGUF/vicuna-13b-v1.5.Q4_K_M.gguf
### LLM cache
## Enable Model cache
# MODEL_CACHE_ENABLE=True
## The storage type of model cache, now supports: memory, disk
# MODEL_CACHE_STORAGE_TYPE=disk
## The max cache data in memory, we always store cache data in memory fist for high speed.
# MODEL_CACHE_MAX_MEMORY_MB=256
## The dir to save cache data, this configuration is only valid when MODEL_CACHE_STORAGE_TYPE=disk
## The default dir is pilot/data/model_cache
# MODEL_CACHE_STORAGE_DISK_DIR=
#*******************************************************************#
#** EMBEDDING SETTINGS **#
#*******************************************************************#
EMBEDDING_MODEL=text2vec
#EMBEDDING_MODEL=m3e-large
#EMBEDDING_MODEL=bge-large-en
#EMBEDDING_MODEL=bge-large-zh
KNOWLEDGE_CHUNK_SIZE=500
KNOWLEDGE_SEARCH_TOP_SIZE=5
#KNOWLEDGE_CHUNK_OVERLAP=50
# Control whether to display the source document of knowledge on the front end.
KNOWLEDGE_CHAT_SHOW_RELATIONS=False
# Whether to enable Chat Knowledge Search Rewrite Mode
KNOWLEDGE_SEARCH_REWRITE=False
## 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
## Openai embedding model, See dbgpt/model/parameter.py
# EMBEDDING_MODEL=proxy_openai
# proxy_openai_proxy_server_url=https://api.openai.com/v1
# proxy_openai_proxy_api_key={your-openai-sk}
# proxy_openai_proxy_backend=text-embedding-ada-002
#*******************************************************************#
#** DB-GPT METADATA DATABASE SETTINGS **#
#*******************************************************************#
### SQLite database (Current default database)
LOCAL_DB_TYPE=sqlite
### MYSQL database
# LOCAL_DB_TYPE=mysql
# LOCAL_DB_USER=root
# LOCAL_DB_PASSWORD={your_password}
# LOCAL_DB_HOST=127.0.0.1
# LOCAL_DB_PORT=3306
# LOCAL_DB_NAME=dbgpt
### This option determines the storage location of conversation records. The default is not configured to the old version of duckdb. It can be optionally db or file (if the value is db, the database configured by LOCAL_DB will be used)
#CHAT_HISTORY_STORE_TYPE=db
#*******************************************************************#
#** 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 **#
#*******************************************************************#
### Chroma vector db config
VECTOR_STORE_TYPE=Chroma
#CHROMA_PERSIST_PATH=/root/DB-GPT/pilot/data
### Milvus vector db config
#VECTOR_STORE_TYPE=Milvus
#MILVUS_URL=127.0.0.1
#MILVUS_PORT=19530
#MILVUS_USERNAME
#MILVUS_PASSWORD
#MILVUS_SECURE=
### Weaviate vector db config
#VECTOR_STORE_TYPE=Weaviate
#WEAVIATE_URL=https://kt-region-m8hcy0wc.weaviate.network
#*******************************************************************#
#** 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}
#*******************************************************************#
# ** PROXY_SERVER + **#
#*******************************************************************#
# Aliyun tongyi
TONGYI_PROXY_API_KEY={your-tongyi-sk}
## Baidu wenxin
#WEN_XIN_MODEL_VERSION={version}
#WEN_XIN_API_KEY={your-wenxin-sk}
#WEN_XIN_API_SECRET={your-wenxin-sct}
## Zhipu
#ZHIPU_MODEL_VERSION={version}
#ZHIPU_PROXY_API_KEY={your-zhipu-sk}
## Baichuan
#BAICHUN_MODEL_NAME={version}
#BAICHUAN_PROXY_API_KEY={your-baichuan-sk}
#BAICHUAN_PROXY_API_SECRET={your-baichuan-sct}
# Xunfei Spark
#XUNFEI_SPARK_API_VERSION={version}
#XUNFEI_SPARK_APPID={your_app_id}
#XUNFEI_SPARK_API_KEY={your_api_key}
#XUNFEI_SPARK_API_SECRET={your_api_secret}
#*******************************************************************#
#** 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
#*******************************************************************#
#** LOG **#
#*******************************************************************#
# FATAL, ERROR, WARNING, WARNING, INFO, DEBUG, NOTSET
DBGPT_LOG_LEVEL=INFO
# LOG dir, default: ./logs
#DBGPT_LOG_DIR=