ServiceWebParameters Configuration

ServiceWebParameters(host: str = '0.0.0.0', port: int = 5670, light: Optional[bool] = False, controller_addr: Optional[str] = None, database: dbgpt.datasource.parameter.BaseDatasourceParameters = <factory>, model_storage: Optional[str] = None, trace: Optional[dbgpt.util.tracer.tracer_impl.TracerParameters] = None, log: Optional[dbgpt.util.utils.LoggingParameters] = None, disable_alembic_upgrade: Optional[bool] = False, db_ssl_verify: Optional[bool] = False, default_thread_pool_size: Optional[int] = None, remote_embedding: Optional[bool] = False, remote_rerank: Optional[bool] = False, awel_dirs: Optional[str] = None, new_web_ui: bool = True, model_cache: dbgpt.storage.cache.manager.ModelCacheParameters = <factory>, embedding_model_max_seq_len: Optional[int] = 512)

Parameters

Name	Type	Required	Description
host	string	❌	Webserver deploy host Defaults：0.0.0.0
port	integer	❌	Webserver deploy port, default is 5670 Defaults：5670
light	boolean	❌	Run Webserver in light mode Defaults：False
controller_addr	string	❌	The Model controller address to connect. If None, read model controller address from environment key `MODEL_SERVER`.
database	BaseDatasourceParameters	❌	Database connection config, now support SQLite, OceanBase and MySQL Defaults：SQLiteConnectorParameters
model_storage	string	❌	The storage type of model configures, if None, use the default storage(current database). When you run in light mode, it will not use any storage. Valid values:database, memory
trace	TracerParameters	❌	Tracer config for web server, if None, use global tracer config
log	LoggingParameters	❌	Logging configuration for web server, if None, use global config
disable_alembic_upgrade	boolean	❌	Whether to disable alembic to initialize and upgrade database metadata Defaults：False
db_ssl_verify	boolean	❌	Whether to verify the SSL certificate of the database Defaults：False
default_thread_pool_size	integer	❌	The default thread pool size, If None, use default config of python thread pool
remote_embedding	boolean	❌	Whether to enable remote embedding models. If it is True, you need to start a embedding model through `dbgpt start worker --worker_type text2vec --model_name xxx --model_path xxx` Defaults：False
remote_rerank	boolean	❌	Whether to enable remote rerank models. If it is True, you need to start a rerank model through `dbgpt start worker --worker_type text2vec --rerank --model_name xxx --model_path xxx` Defaults：False
awel_dirs	string	❌	The directories to search awel files, split by `,`
new_web_ui	boolean	❌	Whether to use the new web UI, default is True Defaults：True
model_cache	ModelCacheParameters	❌	Model cache configuration Defaults：ModelCacheParameters
embedding_model_max_seq_len	integer	❌	The max sequence length of the embedding model, default is 512 Defaults：512