mirror of
https://github.com/csunny/DB-GPT.git
synced 2025-10-22 01:22:34 +00:00
169 lines
7.0 KiB
Plaintext
169 lines
7.0 KiB
Plaintext
#*******************************************************************#
|
|
#** 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-v1.5
|
|
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 /pilot/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
|
|
|
|
#*******************************************************************#
|
|
#** 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
|
|
# Control whether to display the source document of knowledge on the front end.
|
|
KNOWLEDGE_CHAT_SHOW_RELATIONS=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 /pilot/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
|
|
|
|
|
|
#*******************************************************************#
|
|
#** 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
|
|
|
|
|
|
#*******************************************************************#
|
|
#** 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}
|
|
|
|
#*******************************************************************#
|
|
#** 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= |