diff --git a/Makefile b/Makefile index b32f3e695..43fe72dd4 100644 --- a/Makefile +++ b/Makefile @@ -35,9 +35,11 @@ fmt: setup ## Format Python code # Format code $(VENV_BIN)/ruff format packages $(VENV_BIN)/ruff format --exclude="examples/notebook" examples + $(VENV_BIN)/ruff format i18n # Sort imports $(VENV_BIN)/ruff check --select I --fix packages $(VENV_BIN)/ruff check --select I --fix --exclude="examples/notebook" examples + $(VENV_BIN)/ruff check --select I --fix i18n $(VENV_BIN)/ruff check --fix packages \ --exclude="packages/dbgpt-serve/src/**" diff --git a/docs/docs/config-reference/baichuan_baichuandeploymodelparameters_0bf9cc.mdx b/docs/docs/config-reference/baichuan_baichuandeploymodelparameters_0bf9cc.mdx new file mode 100644 index 000000000..3f3138fed --- /dev/null +++ b/docs/docs/config-reference/baichuan_baichuandeploymodelparameters_0bf9cc.mdx @@ -0,0 +1,91 @@ +--- +title: "Baichuan Proxy LLM Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + +')", + "defaultValue": "proxy/baichuan" + }, + { + "name": "verbose", + "type": "boolean", + "required": false, + "description": "Show verbose output.", + "defaultValue": "False" + }, + { + "name": "concurrency", + "type": "integer", + "required": false, + "description": "Model concurrency limit", + "defaultValue": "100" + }, + { + "name": "prompt_template", + "type": "string", + "required": false, + "description": "Prompt template. If None, the prompt template is automatically determined from model. Just for local deployment." + }, + { + "name": "context_length", + "type": "integer", + "required": false, + "description": "The context length of the OpenAI API. If None, it is determined by the model." + }, + { + "name": "api_base", + "type": "string", + "required": false, + "description": "The base url of the Baichuan API.", + "defaultValue": "${env:BAICHUAN_API_BASE:-https://api.baichuan-ai.com/v1}" + }, + { + "name": "api_key", + "type": "string", + "required": false, + "description": "The API key of the Baichuan API.", + "defaultValue": "${env:BAICHUAN_API_KEY}" + }, + { + "name": "api_type", + "type": "string", + "required": false, + "description": "The type of the OpenAI API, if you use Azure, it can be: azure" + }, + { + "name": "api_version", + "type": "string", + "required": false, + "description": "The version of the OpenAI API." + }, + { + "name": "http_proxy", + "type": "string", + "required": false, + "description": "The http or https proxy to use openai" + } + ] +}} /> + diff --git a/docs/docs/config-reference/base_rdbmsdatasourceparameters_4f774f.mdx b/docs/docs/config-reference/base_rdbmsdatasourceparameters_4f774f.mdx new file mode 100644 index 000000000..217cf6c9d --- /dev/null +++ b/docs/docs/config-reference/base_rdbmsdatasourceparameters_4f774f.mdx @@ -0,0 +1,86 @@ +--- +title: "RDBMSDatasourceParameters Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/chatgpt_openaicompatibledeploymodelparameters_c3d426.mdx b/docs/docs/config-reference/chatgpt_openaicompatibledeploymodelparameters_c3d426.mdx new file mode 100644 index 000000000..58c281833 --- /dev/null +++ b/docs/docs/config-reference/chatgpt_openaicompatibledeploymodelparameters_c3d426.mdx @@ -0,0 +1,91 @@ +--- +title: "OpenAI Compatible Proxy LLM Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + +')", + "defaultValue": "proxy/openai" + }, + { + "name": "verbose", + "type": "boolean", + "required": false, + "description": "Show verbose output.", + "defaultValue": "False" + }, + { + "name": "concurrency", + "type": "integer", + "required": false, + "description": "Model concurrency limit", + "defaultValue": "100" + }, + { + "name": "prompt_template", + "type": "string", + "required": false, + "description": "Prompt template. If None, the prompt template is automatically determined from model. Just for local deployment." + }, + { + "name": "context_length", + "type": "integer", + "required": false, + "description": "The context length of the OpenAI API. If None, it is determined by the model." + }, + { + "name": "api_base", + "type": "string", + "required": false, + "description": "The base url of the OpenAI API.", + "defaultValue": "${env:OPENAI_API_BASE:-https://api.openai.com/v1}" + }, + { + "name": "api_key", + "type": "string", + "required": false, + "description": "The API key of the OpenAI API.", + "defaultValue": "${env:OPENAI_API_KEY}" + }, + { + "name": "api_type", + "type": "string", + "required": false, + "description": "The type of the OpenAI API, if you use Azure, it can be: azure" + }, + { + "name": "api_version", + "type": "string", + "required": false, + "description": "The version of the OpenAI API." + }, + { + "name": "http_proxy", + "type": "string", + "required": false, + "description": "The http or https proxy to use openai" + } + ] +}} /> + diff --git a/docs/docs/config-reference/claude_claudedeploymodelparameters_1f0c45.mdx b/docs/docs/config-reference/claude_claudedeploymodelparameters_1f0c45.mdx new file mode 100644 index 000000000..7307d017d --- /dev/null +++ b/docs/docs/config-reference/claude_claudedeploymodelparameters_1f0c45.mdx @@ -0,0 +1,91 @@ +--- +title: "Claude Proxy LLM Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + +')", + "defaultValue": "proxy/claude" + }, + { + "name": "verbose", + "type": "boolean", + "required": false, + "description": "Show verbose output.", + "defaultValue": "False" + }, + { + "name": "concurrency", + "type": "integer", + "required": false, + "description": "Model concurrency limit", + "defaultValue": "100" + }, + { + "name": "prompt_template", + "type": "string", + "required": false, + "description": "Prompt template. If None, the prompt template is automatically determined from model. Just for local deployment." + }, + { + "name": "context_length", + "type": "integer", + "required": false, + "description": "The context length of the OpenAI API. If None, it is determined by the model." + }, + { + "name": "api_base", + "type": "string", + "required": false, + "description": "The base url of the claude API.", + "defaultValue": "${env:ANTHROPIC_BASE_URL:-https://api.anthropic.com}" + }, + { + "name": "api_key", + "type": "string", + "required": false, + "description": "The API key of the claude API.", + "defaultValue": "${env:ANTHROPIC_API_KEY}" + }, + { + "name": "api_type", + "type": "string", + "required": false, + "description": "The type of the OpenAI API, if you use Azure, it can be: azure" + }, + { + "name": "api_version", + "type": "string", + "required": false, + "description": "The version of the OpenAI API." + }, + { + "name": "http_proxy", + "type": "string", + "required": false, + "description": "The http or https proxy to use openai" + } + ] +}} /> + diff --git a/docs/docs/config-reference/config_applicationconfig_72fd1c.mdx b/docs/docs/config-reference/config_applicationconfig_72fd1c.mdx new file mode 100644 index 000000000..63b4b83c5 --- /dev/null +++ b/docs/docs/config-reference/config_applicationconfig_72fd1c.mdx @@ -0,0 +1,186 @@ +--- +title: "ApplicationConfig Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/config_ragparameters_7483b2.mdx b/docs/docs/config-reference/config_ragparameters_7483b2.mdx new file mode 100644 index 000000000..2d9ee0ab5 --- /dev/null +++ b/docs/docs/config-reference/config_ragparameters_7483b2.mdx @@ -0,0 +1,98 @@ +--- +title: "RagParameters Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/config_serveconfig_1a9284.mdx b/docs/docs/config-reference/config_serveconfig_1a9284.mdx new file mode 100644 index 000000000..13fa6bbb7 --- /dev/null +++ b/docs/docs/config-reference/config_serveconfig_1a9284.mdx @@ -0,0 +1,20 @@ +--- +title: "My dbgpts Serve Configurations Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/config_serveconfig_313252.mdx b/docs/docs/config-reference/config_serveconfig_313252.mdx new file mode 100644 index 000000000..0466f3dcd --- /dev/null +++ b/docs/docs/config-reference/config_serveconfig_313252.mdx @@ -0,0 +1,26 @@ +--- +title: "Conversation Serve Configurations Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/config_serveconfig_63f1e9.mdx b/docs/docs/config-reference/config_serveconfig_63f1e9.mdx new file mode 100644 index 000000000..d12805fde --- /dev/null +++ b/docs/docs/config-reference/config_serveconfig_63f1e9.mdx @@ -0,0 +1,20 @@ +--- +title: "Datasource Serve Configurations Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/config_serveconfig_7889f9.mdx b/docs/docs/config-reference/config_serveconfig_7889f9.mdx new file mode 100644 index 000000000..b7cdf16c3 --- /dev/null +++ b/docs/docs/config-reference/config_serveconfig_7889f9.mdx @@ -0,0 +1,90 @@ +--- +title: "RAG Serve Configurations Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/config_serveconfig_7a0577.mdx b/docs/docs/config-reference/config_serveconfig_7a0577.mdx new file mode 100644 index 000000000..65efefe17 --- /dev/null +++ b/docs/docs/config-reference/config_serveconfig_7a0577.mdx @@ -0,0 +1,30 @@ +--- +title: "Model Serve Configurations Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/config_serveconfig_854dad.mdx b/docs/docs/config-reference/config_serveconfig_854dad.mdx new file mode 100644 index 000000000..9d573ef73 --- /dev/null +++ b/docs/docs/config-reference/config_serveconfig_854dad.mdx @@ -0,0 +1,32 @@ +--- +title: "Prompt Serve Configurations Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/config_serveconfig_8839e0.mdx b/docs/docs/config-reference/config_serveconfig_8839e0.mdx new file mode 100644 index 000000000..ddec2776d --- /dev/null +++ b/docs/docs/config-reference/config_serveconfig_8839e0.mdx @@ -0,0 +1,34 @@ +--- +title: "Evaluate Serve Configurations Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/config_serveconfig_adbd6f.mdx b/docs/docs/config-reference/config_serveconfig_adbd6f.mdx new file mode 100644 index 000000000..2ad8bdee5 --- /dev/null +++ b/docs/docs/config-reference/config_serveconfig_adbd6f.mdx @@ -0,0 +1,20 @@ +--- +title: "ServeConfig Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/config_serveconfig_b1c2b9.mdx b/docs/docs/config-reference/config_serveconfig_b1c2b9.mdx new file mode 100644 index 000000000..9bb98d66b --- /dev/null +++ b/docs/docs/config-reference/config_serveconfig_b1c2b9.mdx @@ -0,0 +1,20 @@ +--- +title: "Libro Serve Configurations Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/config_serveconfig_c0b589.mdx b/docs/docs/config-reference/config_serveconfig_c0b589.mdx new file mode 100644 index 000000000..e0c234c43 --- /dev/null +++ b/docs/docs/config-reference/config_serveconfig_c0b589.mdx @@ -0,0 +1,33 @@ +--- +title: "AWEL Flow Serve Configurations Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/config_serveconfig_cb64c6.mdx b/docs/docs/config-reference/config_serveconfig_cb64c6.mdx new file mode 100644 index 000000000..d468d4290 --- /dev/null +++ b/docs/docs/config-reference/config_serveconfig_cb64c6.mdx @@ -0,0 +1,74 @@ +--- +title: "File Serve Configurations Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/config_serveconfig_ec2d70.mdx b/docs/docs/config-reference/config_serveconfig_ec2d70.mdx new file mode 100644 index 000000000..48eb485ab --- /dev/null +++ b/docs/docs/config-reference/config_serveconfig_ec2d70.mdx @@ -0,0 +1,20 @@ +--- +title: "Hub dbgpts Serve Configurations Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/config_serveconfig_fa1f35.mdx b/docs/docs/config-reference/config_serveconfig_fa1f35.mdx new file mode 100644 index 000000000..8de95b55e --- /dev/null +++ b/docs/docs/config-reference/config_serveconfig_fa1f35.mdx @@ -0,0 +1,20 @@ +--- +title: "Feedback Serve Configurations Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/config_serviceconfig_81a10f.mdx b/docs/docs/config-reference/config_serviceconfig_81a10f.mdx new file mode 100644 index 000000000..fd630e2d6 --- /dev/null +++ b/docs/docs/config-reference/config_serviceconfig_81a10f.mdx @@ -0,0 +1,42 @@ +--- +title: "ServiceConfig Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + +, model: dbgpt.model.parameter.ModelServiceConfig = )", + "documentationUrl": "", + "parameters": [ + { + "name": "model", + "type": "ModelServiceConfig", + "required": false, + "description": "Model service configuration", + "nestedTypes": [ + { + "type": "link", + "text": "modelserviceconfig configuration", + "url": "././parameter_modelserviceconfig_20d67d" + } + ], + "defaultValue": "ModelServiceConfig" + }, + { + "name": "web", + "type": "ServiceWebParameters", + "required": false, + "description": "Web service configuration", + "nestedTypes": [ + { + "type": "link", + "text": "servicewebparameters configuration", + "url": "././config_servicewebparameters_3ab7fd" + } + ], + "defaultValue": "ServiceWebParameters" + } + ] +}} /> + diff --git a/docs/docs/config-reference/config_servicewebparameters_3ab7fd.mdx b/docs/docs/config-reference/config_servicewebparameters_3ab7fd.mdx new file mode 100644 index 000000000..360d53f50 --- /dev/null +++ b/docs/docs/config-reference/config_servicewebparameters_3ab7fd.mdx @@ -0,0 +1,224 @@ +--- +title: "ServiceWebParameters Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + +, 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 = , embedding_model_max_seq_len: Optional[int] = 512)", + "documentationUrl": "", + "parameters": [ + { + "name": "port", + "type": "integer", + "required": false, + "description": "Webserver deploy port, default is 5670", + "defaultValue": "5670" + }, + { + "name": "light", + "type": "boolean", + "required": false, + "description": "Run Webserver in light mode", + "defaultValue": "False" + }, + { + "name": "controller_addr", + "type": "string", + "required": false, + "description": "The Model controller address to connect. If None, read model controller address from environment key `MODEL_SERVER`." + }, + { + "name": "database", + "type": "BaseDatasourceParameters", + "required": false, + "description": "Database connection config, now support SQLite, OceanBase and MySQL", + "nestedTypes": [ + { + "type": "link", + "text": "rdbmsdatasourceparameters configuration", + "url": "././base_rdbmsdatasourceparameters_4f774f" + }, + { + "type": "link", + "text": "sqlite configuration", + "url": "././conn_sqlite_sqliteconnectorparameters_82c8b5" + }, + { + "type": "link", + "text": "tugraph configuration", + "url": "././conn_tugraph_tugraphparameters_0c844e" + }, + { + "type": "link", + "text": "spark configuration", + "url": "././conn_spark_sparkparameters_174bbc" + }, + { + "type": "link", + "text": "clickhouse configuration", + "url": "././conn_clickhouse_clickhouseparameters_4a1237" + }, + { + "type": "link", + "text": "doris configuration", + "url": "././conn_doris_dorisparameters_e33c53" + }, + { + "type": "link", + "text": "duckdb configuration", + "url": "././conn_duckdb_duckdbconnectorparameters_c672c7" + }, + { + "type": "link", + "text": "hive configuration", + "url": "././conn_hive_hiveparameters_ec3601" + }, + { + "type": "link", + "text": "mssql configuration", + "url": "././conn_mssql_mssqlparameters_d79d1c" + }, + { + "type": "link", + "text": "mysql configuration", + "url": "././conn_mysql_mysqlparameters_4393c4" + }, + { + "type": "link", + "text": "oceanbase configuration", + "url": "././conn_oceanbase_oceanbaseparameters_260d2d" + }, + { + "type": "link", + "text": "postgresql configuration", + "url": "././conn_postgresql_postgresqlparameters_22efa5" + }, + { + "type": "link", + "text": "starrocks configuration", + "url": "././conn_starrocks_starrocksparameters_e511f7" + }, + { + "type": "link", + "text": "vertica configuration", + "url": "././conn_vertica_verticaparameters_c712b8" + } + ], + "defaultValue": "SQLiteConnectorParameters" + }, + { + "name": "model_storage", + "type": "string", + "required": false, + "description": "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.", + "validValues": [ + "database", + "memory" + ] + }, + { + "name": "trace", + "type": "TracerParameters", + "required": false, + "description": "Tracer config for web server, if None, use global tracer config", + "nestedTypes": [ + { + "type": "link", + "text": "tracerparameters configuration", + "url": "././tracer_impl_tracerparameters_f8f272" + } + ] + }, + { + "name": "log", + "type": "LoggingParameters", + "required": false, + "description": "Logging configuration for web server, if None, use global config", + "nestedTypes": [ + { + "type": "link", + "text": "loggingparameters configuration", + "url": "././utils_loggingparameters_4ba5c6" + } + ] + }, + { + "name": "disable_alembic_upgrade", + "type": "boolean", + "required": false, + "description": "Whether to disable alembic to initialize and upgrade database metadata", + "defaultValue": "False" + }, + { + "name": "db_ssl_verify", + "type": "boolean", + "required": false, + "description": "Whether to verify the SSL certificate of the database", + "defaultValue": "False" + }, + { + "name": "default_thread_pool_size", + "type": "integer", + "required": false, + "description": "The default thread pool size, If None, use default config of python thread pool" + }, + { + "name": "remote_embedding", + "type": "boolean", + "required": false, + "description": "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`", + "defaultValue": "False" + }, + { + "name": "remote_rerank", + "type": "boolean", + "required": false, + "description": "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`", + "defaultValue": "False" + }, + { + "name": "awel_dirs", + "type": "string", + "required": false, + "description": "The directories to search awel files, split by `,`" + }, + { + "name": "new_web_ui", + "type": "boolean", + "required": false, + "description": "Whether to use the new web UI, default is True", + "defaultValue": "True" + }, + { + "name": "model_cache", + "type": "ModelCacheParameters", + "required": false, + "description": "Model cache configuration", + "nestedTypes": [ + { + "type": "link", + "text": "modelcacheparameters configuration", + "url": "././manager_modelcacheparameters_152367" + } + ], + "defaultValue": "ModelCacheParameters" + }, + { + "name": "embedding_model_max_seq_len", + "type": "integer", + "required": false, + "description": "The max sequence length of the embedding model, default is 512", + "defaultValue": "512" + }, + { + "name": "host", + "type": "string", + "required": false, + "description": "Webserver deploy host", + "defaultValue": "0.0.0.0" + } + ] +}} /> + diff --git a/docs/docs/config-reference/config_storageconfig_028579.mdx b/docs/docs/config-reference/config_storageconfig_028579.mdx new file mode 100644 index 000000000..3672923a6 --- /dev/null +++ b/docs/docs/config-reference/config_storageconfig_028579.mdx @@ -0,0 +1,35 @@ +--- +title: "StorageConfig Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + +, graph: dbgpt_ext.storage.knowledge_graph.knowledge_graph.BuiltinKnowledgeGraphConfig = , full_text: dbgpt_ext.storage.knowledge_graph.knowledge_graph.BuiltinKnowledgeGraphConfig = )", + "documentationUrl": "", + "parameters": [ + { + "name": "graph", + "type": "BuiltinKnowledgeGraphConfig", + "required": false, + "description": "default graph type", + "defaultValue": "type='TuGraph' name='dbgpt_collection' embedding_fn=None max_chunks_once_load=10 max_threads=1 llm_client=None model_name=None" + }, + { + "name": "full_text", + "type": "BuiltinKnowledgeGraphConfig", + "required": false, + "description": "default graph type", + "defaultValue": "type='TuGraph' name='dbgpt_collection' embedding_fn=None max_chunks_once_load=10 max_threads=1 llm_client=None model_name=None" + }, + { + "name": "vector", + "type": "VectorStoreConfig", + "required": false, + "description": "default vector type", + "defaultValue": "type=None name='dbgpt_collection' embedding_fn=None max_chunks_once_load=10 max_threads=1 user=None password=None topk=5 score_threshold=0.3" + } + ] +}} /> + diff --git a/docs/docs/config-reference/config_storagegraphconfig_4de01b.mdx b/docs/docs/config-reference/config_storagegraphconfig_4de01b.mdx new file mode 100644 index 000000000..dfc21e22c --- /dev/null +++ b/docs/docs/config-reference/config_storagegraphconfig_4de01b.mdx @@ -0,0 +1,21 @@ +--- +title: "StorageGraphConfig Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/config_storagevectorconfig_12eb66.mdx b/docs/docs/config-reference/config_storagevectorconfig_12eb66.mdx new file mode 100644 index 000000000..74d5c5560 --- /dev/null +++ b/docs/docs/config-reference/config_storagevectorconfig_12eb66.mdx @@ -0,0 +1,21 @@ +--- +title: "StorageVectorConfig Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/config_systemparameters_fd92b9.mdx b/docs/docs/config-reference/config_systemparameters_fd92b9.mdx new file mode 100644 index 000000000..80736685d --- /dev/null +++ b/docs/docs/config-reference/config_systemparameters_fd92b9.mdx @@ -0,0 +1,57 @@ +--- +title: "SystemParameters Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/conn_clickhouse_clickhouseparameters_4a1237.mdx b/docs/docs/config-reference/conn_clickhouse_clickhouseparameters_4a1237.mdx new file mode 100644 index 000000000..ec933af2a --- /dev/null +++ b/docs/docs/config-reference/conn_clickhouse_clickhouseparameters_4a1237.mdx @@ -0,0 +1,73 @@ +--- +title: "Clickhouse datasource Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/conn_doris_dorisparameters_e33c53.mdx b/docs/docs/config-reference/conn_doris_dorisparameters_e33c53.mdx new file mode 100644 index 000000000..cd8cdb12f --- /dev/null +++ b/docs/docs/config-reference/conn_doris_dorisparameters_e33c53.mdx @@ -0,0 +1,87 @@ +--- +title: "Apache Doris datasource Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/conn_duckdb_duckdbconnectorparameters_c672c7.mdx b/docs/docs/config-reference/conn_duckdb_duckdbconnectorparameters_c672c7.mdx new file mode 100644 index 000000000..bd71b408e --- /dev/null +++ b/docs/docs/config-reference/conn_duckdb_duckdbconnectorparameters_c672c7.mdx @@ -0,0 +1,27 @@ +--- +title: "DuckDB datasource Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/conn_hive_hiveparameters_ec3601.mdx b/docs/docs/config-reference/conn_hive_hiveparameters_ec3601.mdx new file mode 100644 index 000000000..4dedfaab5 --- /dev/null +++ b/docs/docs/config-reference/conn_hive_hiveparameters_ec3601.mdx @@ -0,0 +1,83 @@ +--- +title: "Apache Hive datasource Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/conn_mssql_mssqlparameters_d79d1c.mdx b/docs/docs/config-reference/conn_mssql_mssqlparameters_d79d1c.mdx new file mode 100644 index 000000000..873cb648e --- /dev/null +++ b/docs/docs/config-reference/conn_mssql_mssqlparameters_d79d1c.mdx @@ -0,0 +1,87 @@ +--- +title: "MSSQL datasource Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/conn_mysql_mysqlparameters_4393c4.mdx b/docs/docs/config-reference/conn_mysql_mysqlparameters_4393c4.mdx new file mode 100644 index 000000000..985bd6eb1 --- /dev/null +++ b/docs/docs/config-reference/conn_mysql_mysqlparameters_4393c4.mdx @@ -0,0 +1,87 @@ +--- +title: "MySQL datasource Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/conn_oceanbase_oceanbaseparameters_260d2d.mdx b/docs/docs/config-reference/conn_oceanbase_oceanbaseparameters_260d2d.mdx new file mode 100644 index 000000000..7bb7e7d9b --- /dev/null +++ b/docs/docs/config-reference/conn_oceanbase_oceanbaseparameters_260d2d.mdx @@ -0,0 +1,87 @@ +--- +title: "OceanBase datasource Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/conn_postgresql_postgresqlparameters_22efa5.mdx b/docs/docs/config-reference/conn_postgresql_postgresqlparameters_22efa5.mdx new file mode 100644 index 000000000..8ce2f7ff5 --- /dev/null +++ b/docs/docs/config-reference/conn_postgresql_postgresqlparameters_22efa5.mdx @@ -0,0 +1,94 @@ +--- +title: "PostreSQL datasource Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/conn_spark_sparkparameters_174bbc.mdx b/docs/docs/config-reference/conn_spark_sparkparameters_174bbc.mdx new file mode 100644 index 000000000..614150a32 --- /dev/null +++ b/docs/docs/config-reference/conn_spark_sparkparameters_174bbc.mdx @@ -0,0 +1,20 @@ +--- +title: "Apache Spark datasource Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/conn_sqlite_sqliteconnectorparameters_82c8b5.mdx b/docs/docs/config-reference/conn_sqlite_sqliteconnectorparameters_82c8b5.mdx new file mode 100644 index 000000000..692d04707 --- /dev/null +++ b/docs/docs/config-reference/conn_sqlite_sqliteconnectorparameters_82c8b5.mdx @@ -0,0 +1,34 @@ +--- +title: "SQLite datasource Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/conn_starrocks_starrocksparameters_e511f7.mdx b/docs/docs/config-reference/conn_starrocks_starrocksparameters_e511f7.mdx new file mode 100644 index 000000000..52362b9ee --- /dev/null +++ b/docs/docs/config-reference/conn_starrocks_starrocksparameters_e511f7.mdx @@ -0,0 +1,87 @@ +--- +title: "StarRocks datasource Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/conn_tugraph_tugraphparameters_0c844e.mdx b/docs/docs/config-reference/conn_tugraph_tugraphparameters_0c844e.mdx new file mode 100644 index 000000000..b3e0dea9d --- /dev/null +++ b/docs/docs/config-reference/conn_tugraph_tugraphparameters_0c844e.mdx @@ -0,0 +1,47 @@ +--- +title: "TuGraph datasource Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/conn_vertica_verticaparameters_c712b8.mdx b/docs/docs/config-reference/conn_vertica_verticaparameters_c712b8.mdx new file mode 100644 index 000000000..f36366145 --- /dev/null +++ b/docs/docs/config-reference/conn_vertica_verticaparameters_c712b8.mdx @@ -0,0 +1,87 @@ +--- +title: "Vertica datasource Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/deepseek_deepseekdeploymodelparameters_194cbd.mdx b/docs/docs/config-reference/deepseek_deepseekdeploymodelparameters_194cbd.mdx new file mode 100644 index 000000000..cfe2db187 --- /dev/null +++ b/docs/docs/config-reference/deepseek_deepseekdeploymodelparameters_194cbd.mdx @@ -0,0 +1,91 @@ +--- +title: "Deepseek Proxy LLM Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + +')", + "defaultValue": "proxy/deepseek" + }, + { + "name": "verbose", + "type": "boolean", + "required": false, + "description": "Show verbose output.", + "defaultValue": "False" + }, + { + "name": "concurrency", + "type": "integer", + "required": false, + "description": "Model concurrency limit", + "defaultValue": "100" + }, + { + "name": "prompt_template", + "type": "string", + "required": false, + "description": "Prompt template. If None, the prompt template is automatically determined from model. Just for local deployment." + }, + { + "name": "context_length", + "type": "integer", + "required": false, + "description": "The context length of the OpenAI API. If None, it is determined by the model." + }, + { + "name": "api_base", + "type": "string", + "required": false, + "description": "The base url of the DeepSeek API.", + "defaultValue": "${env:DEEPSEEK_API_BASE:-https://api.deepseek.com/v1}" + }, + { + "name": "api_key", + "type": "string", + "required": false, + "description": "The API key of the DeepSeek API.", + "defaultValue": "${env:DEEPSEEK_API_KEY}" + }, + { + "name": "api_type", + "type": "string", + "required": false, + "description": "The type of the OpenAI API, if you use Azure, it can be: azure" + }, + { + "name": "api_version", + "type": "string", + "required": false, + "description": "The version of the OpenAI API." + }, + { + "name": "http_proxy", + "type": "string", + "required": false, + "description": "The http or https proxy to use openai" + } + ] +}} /> + diff --git a/docs/docs/config-reference/embeddings_hfembeddingdeploymodelparameters_f588e1.mdx b/docs/docs/config-reference/embeddings_hfembeddingdeploymodelparameters_f588e1.mdx new file mode 100644 index 000000000..070cc0438 --- /dev/null +++ b/docs/docs/config-reference/embeddings_hfembeddingdeploymodelparameters_f588e1.mdx @@ -0,0 +1,99 @@ +--- +title: "HFEmbeddingDeployModelParameters Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + +, encode_kwargs: Dict[str, Any] = , embed_instruction: Optional[str] = None, query_instruction: Optional[str] = None)", + "documentationUrl": "", + "parameters": [ + { + "name": "name", + "type": "string", + "required": true, + "description": "The name of the model." + }, + { + "name": "path", + "type": "string", + "required": false, + "description": "The path of the model, if you want to deploy a local model." + }, + { + "name": "device", + "type": "string", + "required": false, + "description": "Device to run model. If None, the device is automatically determined" + }, + { + "name": "provider", + "type": "string", + "required": false, + "description": "The provider of the model. If model is deployed in local, this is the inference type. If model is deployed in third-party service, this is platform name('proxy/')", + "defaultValue": "hf" + }, + { + "name": "verbose", + "type": "boolean", + "required": false, + "description": "Show verbose output.", + "defaultValue": "False" + }, + { + "name": "concurrency", + "type": "integer", + "required": false, + "description": "Model concurrency limit", + "defaultValue": "100" + }, + { + "name": "cache_folder", + "type": "string", + "required": false, + "description": "Path of the cache folder." + }, + { + "name": "normalize_embeddings", + "type": "boolean", + "required": false, + "description": "Normalize embeddings.", + "defaultValue": "False" + }, + { + "name": "multi_process", + "type": "boolean", + "required": false, + "description": "Run encode() on multiple GPUs.", + "defaultValue": "False" + }, + { + "name": "model_kwargs", + "type": "object", + "required": false, + "description": "Keyword arguments to pass to the model.", + "defaultValue": "{}" + }, + { + "name": "encode_kwargs", + "type": "object", + "required": false, + "description": "Keyword arguments to pass when calling the `encode` method.", + "defaultValue": "{}" + }, + { + "name": "embed_instruction", + "type": "string", + "required": false, + "description": "Instruction to use for embedding documents. Just for Instructor model." + }, + { + "name": "query_instruction", + "type": "string", + "required": false, + "description": "Instruction to use for embedding query. Just for Instructor model." + } + ] +}} /> + diff --git a/docs/docs/config-reference/embeddings_openapiembeddingdeploymodelparameters_f9ba47.mdx b/docs/docs/config-reference/embeddings_openapiembeddingdeploymodelparameters_f9ba47.mdx new file mode 100644 index 000000000..8b8cb4ca9 --- /dev/null +++ b/docs/docs/config-reference/embeddings_openapiembeddingdeploymodelparameters_f9ba47.mdx @@ -0,0 +1,67 @@ +--- +title: "OpenAPIEmbeddingDeployModelParameters Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + +')", + "defaultValue": "proxy/openai" + }, + { + "name": "verbose", + "type": "boolean", + "required": false, + "description": "Show verbose output.", + "defaultValue": "False" + }, + { + "name": "concurrency", + "type": "integer", + "required": false, + "description": "Model concurrency limit", + "defaultValue": "100" + }, + { + "name": "api_url", + "type": "string", + "required": false, + "description": "The URL of the embeddings API.", + "defaultValue": "http://localhost:8100/api/v1/embeddings" + }, + { + "name": "api_key", + "type": "string", + "required": false, + "description": "The API key for the embeddings API." + }, + { + "name": "backend", + "type": "string", + "required": false, + "description": "The real model name to pass to the provider, default is None. If backend is None, use name as the real model name." + }, + { + "name": "timeout", + "type": "integer", + "required": false, + "description": "The timeout for the request in seconds.", + "defaultValue": "60" + } + ] +}} /> + diff --git a/docs/docs/config-reference/gemini_geminideploymodelparameters_5113b9.mdx b/docs/docs/config-reference/gemini_geminideploymodelparameters_5113b9.mdx new file mode 100644 index 000000000..de54ac220 --- /dev/null +++ b/docs/docs/config-reference/gemini_geminideploymodelparameters_5113b9.mdx @@ -0,0 +1,91 @@ +--- +title: "Gemini Proxy LLM Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + +')", + "defaultValue": "proxy/gemini" + }, + { + "name": "verbose", + "type": "boolean", + "required": false, + "description": "Show verbose output.", + "defaultValue": "False" + }, + { + "name": "concurrency", + "type": "integer", + "required": false, + "description": "Model concurrency limit", + "defaultValue": "100" + }, + { + "name": "prompt_template", + "type": "string", + "required": false, + "description": "Prompt template. If None, the prompt template is automatically determined from model. Just for local deployment." + }, + { + "name": "context_length", + "type": "integer", + "required": false, + "description": "The context length of the OpenAI API. If None, it is determined by the model." + }, + { + "name": "api_base", + "type": "string", + "required": false, + "description": "The base url of the gemini API.", + "defaultValue": "${env:GEMINI_PROXY_API_BASE}" + }, + { + "name": "api_key", + "type": "string", + "required": false, + "description": "The API key of the gemini API.", + "defaultValue": "${env:GEMINI_PROXY_API_KEY}" + }, + { + "name": "api_type", + "type": "string", + "required": false, + "description": "The type of the OpenAI API, if you use Azure, it can be: azure" + }, + { + "name": "api_version", + "type": "string", + "required": false, + "description": "The version of the OpenAI API." + }, + { + "name": "http_proxy", + "type": "string", + "required": false, + "description": "The http or https proxy to use openai" + } + ] +}} /> + diff --git a/docs/docs/config-reference/gitee_giteedeploymodelparameters_d1bdb3.mdx b/docs/docs/config-reference/gitee_giteedeploymodelparameters_d1bdb3.mdx new file mode 100644 index 000000000..b13bd3514 --- /dev/null +++ b/docs/docs/config-reference/gitee_giteedeploymodelparameters_d1bdb3.mdx @@ -0,0 +1,91 @@ +--- +title: "Gitee Proxy LLM Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + +')", + "defaultValue": "proxy/gitee" + }, + { + "name": "verbose", + "type": "boolean", + "required": false, + "description": "Show verbose output.", + "defaultValue": "False" + }, + { + "name": "concurrency", + "type": "integer", + "required": false, + "description": "Model concurrency limit", + "defaultValue": "100" + }, + { + "name": "prompt_template", + "type": "string", + "required": false, + "description": "Prompt template. If None, the prompt template is automatically determined from model. Just for local deployment." + }, + { + "name": "context_length", + "type": "integer", + "required": false, + "description": "The context length of the OpenAI API. If None, it is determined by the model." + }, + { + "name": "api_base", + "type": "string", + "required": false, + "description": "The base url of the Gitee API.", + "defaultValue": "${env:GITEE_API_BASE:-https://ai.gitee.com/v1}" + }, + { + "name": "api_key", + "type": "string", + "required": false, + "description": "The API key of the Gitee API.", + "defaultValue": "${env:GITEE_API_KEY}" + }, + { + "name": "api_type", + "type": "string", + "required": false, + "description": "The type of the OpenAI API, if you use Azure, it can be: azure" + }, + { + "name": "api_version", + "type": "string", + "required": false, + "description": "The version of the OpenAI API." + }, + { + "name": "http_proxy", + "type": "string", + "required": false, + "description": "The http or https proxy to use openai" + } + ] +}} /> + diff --git a/docs/docs/config-reference/hf_adapter_hfllmdeploymodelparameters_103e81.mdx b/docs/docs/config-reference/hf_adapter_hfllmdeploymodelparameters_103e81.mdx new file mode 100644 index 000000000..8818187e4 --- /dev/null +++ b/docs/docs/config-reference/hf_adapter_hfllmdeploymodelparameters_103e81.mdx @@ -0,0 +1,132 @@ +--- +title: "HFLLMDeployModelParameters Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + +')", + "defaultValue": "hf" + }, + { + "name": "verbose", + "type": "boolean", + "required": false, + "description": "Show verbose output.", + "defaultValue": "False" + }, + { + "name": "concurrency", + "type": "integer", + "required": false, + "description": "Model concurrency limit", + "defaultValue": "5" + }, + { + "name": "prompt_template", + "type": "string", + "required": false, + "description": "Prompt template. If None, the prompt template is automatically determined from model. Just for local deployment." + }, + { + "name": "context_length", + "type": "integer", + "required": false, + "description": "The context length of the model. If None, it is automatically determined from model." + }, + { + "name": "trust_remote_code", + "type": "boolean", + "required": false, + "description": "Trust remote code or not.", + "defaultValue": "True" + }, + { + "name": "quantization", + "type": "BaseHFQuantization", + "required": false, + "description": "The quantization parameters.", + "nestedTypes": [ + { + "type": "link", + "text": "bitsandbytes configuration", + "url": "././parameter_bitsandbytesquantization_d40e3b" + }, + { + "type": "link", + "text": "bitsandbytes_8bits configuration", + "url": "././parameter_bitsandbytesquantization8bits_909aed" + }, + { + "type": "link", + "text": "bitsandbytes_4bits configuration", + "url": "././parameter_bitsandbytesquantization4bits_52b778" + } + ] + }, + { + "name": "low_cpu_mem_usage", + "type": "boolean", + "required": false, + "description": "Whether to use low CPU memory usage mode. It can reduce the memory when loading the model, if you load your model with quantization, it will be True by default. You must install `accelerate` to make it work." + }, + { + "name": "num_gpus", + "type": "integer", + "required": false, + "description": "The number of gpus you expect to use, if it is empty, use all of them as much as possible" + }, + { + "name": "max_gpu_memory", + "type": "string", + "required": false, + "description": "The maximum memory limit of each GPU, only valid in multi-GPU configuration, eg: 10GiB, 24GiB" + }, + { + "name": "torch_dtype", + "type": "string", + "required": false, + "description": "The dtype of the model, default is None.", + "validValues": [ + "auto", + "float16", + "bfloat16", + "float", + "float32" + ] + } + ] +}} /> + diff --git a/docs/docs/config-reference/jina_jinaembeddingsdeploymodelparameters_40b0f2.mdx b/docs/docs/config-reference/jina_jinaembeddingsdeploymodelparameters_40b0f2.mdx new file mode 100644 index 000000000..437c6af32 --- /dev/null +++ b/docs/docs/config-reference/jina_jinaembeddingsdeploymodelparameters_40b0f2.mdx @@ -0,0 +1,68 @@ +--- +title: "JinaEmbeddingsDeployModelParameters Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + +')", + "defaultValue": "proxy/jina" + }, + { + "name": "verbose", + "type": "boolean", + "required": false, + "description": "Show verbose output.", + "defaultValue": "False" + }, + { + "name": "concurrency", + "type": "integer", + "required": false, + "description": "Model concurrency limit", + "defaultValue": "100" + }, + { + "name": "api_url", + "type": "string", + "required": false, + "description": "The URL of the embeddings API.", + "defaultValue": "https://api.jina.ai/v1/embeddings" + }, + { + "name": "api_key", + "type": "string", + "required": false, + "description": "The API key for the embeddings API." + }, + { + "name": "backend", + "type": "string", + "required": false, + "description": "The real model name to pass to the provider, default is None. If backend is None, use name as the real model name.", + "defaultValue": "jina-embeddings-v2-base-en" + }, + { + "name": "timeout", + "type": "integer", + "required": false, + "description": "The timeout for the request in seconds.", + "defaultValue": "60" + } + ] +}} /> + diff --git a/docs/docs/config-reference/llama_cpp_adapter_llamaserverparameters_421f40.mdx b/docs/docs/config-reference/llama_cpp_adapter_llamaserverparameters_421f40.mdx new file mode 100644 index 000000000..48fa27ddb --- /dev/null +++ b/docs/docs/config-reference/llama_cpp_adapter_llamaserverparameters_421f40.mdx @@ -0,0 +1,281 @@ +--- +title: "LlamaServerParameters Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + +, no_context_shift: bool = False, no_webui: Optional[bool] = None, startup_timeout: Optional[int] = None)", + "documentationUrl": "", + "parameters": [ + { + "name": "name", + "type": "string", + "required": true, + "description": "The name of the model." + }, + { + "name": "path", + "type": "string", + "required": false, + "description": "Local model file path" + }, + { + "name": "backend", + "type": "string", + "required": false, + "description": "The real model name to pass to the provider, default is None. If backend is None, use name as the real model name." + }, + { + "name": "device", + "type": "string", + "required": false, + "description": "Device to run model. If None, the device is automatically determined" + }, + { + "name": "provider", + "type": "string", + "required": false, + "description": "The provider of the model. If model is deployed in local, this is the inference type. If model is deployed in third-party service, this is platform name('proxy/')", + "defaultValue": "llama.cpp.server" + }, + { + "name": "verbose", + "type": "boolean", + "required": false, + "description": "Show verbose output.", + "defaultValue": "False" + }, + { + "name": "concurrency", + "type": "integer", + "required": false, + "description": "Model concurrency limit", + "defaultValue": "20" + }, + { + "name": "prompt_template", + "type": "string", + "required": false, + "description": "Prompt template. If None, the prompt template is automatically determined from model. Just for local deployment." + }, + { + "name": "context_length", + "type": "integer", + "required": false, + "description": "The context length of the model. If None, it is automatically determined from model." + }, + { + "name": "model_hf_repo", + "type": "string", + "required": false, + "description": "Hugging Face repository for model download" + }, + { + "name": "model_hf_file", + "type": "string", + "required": false, + "description": "Model file name in the Hugging Face repository" + }, + { + "name": "server_bin_path", + "type": "string", + "required": false, + "description": "Path to the server binary executable" + }, + { + "name": "server_host", + "type": "string", + "required": false, + "description": "Host address to bind the server", + "defaultValue": "127.0.0.1" + }, + { + "name": "server_port", + "type": "integer", + "required": false, + "description": "Port to bind the server. 0 for random available port", + "defaultValue": "0" + }, + { + "name": "temperature", + "type": "number", + "required": false, + "description": "Sampling temperature for text generation", + "defaultValue": "0.8" + }, + { + "name": "seed", + "type": "integer", + "required": false, + "description": "Random seed for reproducibility", + "defaultValue": "42" + }, + { + "name": "debug", + "type": "boolean", + "required": false, + "description": "Enable debug mode", + "defaultValue": "False" + }, + { + "name": "model_url", + "type": "string", + "required": false, + "description": "Model download URL (env: LLAMA_ARG_MODEL_URL)" + }, + { + "name": "model_draft", + "type": "string", + "required": false, + "description": "Draft model file path" + }, + { + "name": "threads", + "type": "integer", + "required": false, + "description": "Number of threads to use during generation (default: -1) (env: LLAMA_ARG_THREADS)" + }, + { + "name": "n_gpu_layers", + "type": "integer", + "required": false, + "description": "Number of layers to store in VRAM (env: LLAMA_ARG_N_GPU_LAYERS), set 1000000000 to use all layers" + }, + { + "name": "batch_size", + "type": "integer", + "required": false, + "description": "Logical maximum batch size (default: 2048) (env: LLAMA_ARG_BATCH)" + }, + { + "name": "ubatch_size", + "type": "integer", + "required": false, + "description": "Physical maximum batch size (default: 512) (env: LLAMA_ARG_UBATCH)" + }, + { + "name": "ctx_size", + "type": "integer", + "required": false, + "description": "Size of the prompt context (default: 4096, 0 = loaded from model) (env: LLAMA_ARG_CTX_SIZE)" + }, + { + "name": "grp_attn_n", + "type": "integer", + "required": false, + "description": "Group-attention factor (default: 1)" + }, + { + "name": "grp_attn_w", + "type": "integer", + "required": false, + "description": "Group-attention width (default: 512)" + }, + { + "name": "n_predict", + "type": "integer", + "required": false, + "description": "Number of tokens to predict (default: -1, -1 = infinity, -2 = until context filled) (env: LLAMA_ARG_N_PREDICT)" + }, + { + "name": "slot_save_path", + "type": "string", + "required": false, + "description": "Path to save slot kv cache (default: disabled)" + }, + { + "name": "n_slots", + "type": "integer", + "required": false, + "description": "Number of slots for KV cache" + }, + { + "name": "cont_batching", + "type": "boolean", + "required": false, + "description": "Enable continuous batching (a.k.a dynamic batching)", + "defaultValue": "False" + }, + { + "name": "embedding", + "type": "boolean", + "required": false, + "description": "Restrict to only support embedding use case; use only with dedicated embedding models (env: LLAMA_ARG_EMBEDDINGS)", + "defaultValue": "False" + }, + { + "name": "reranking", + "type": "boolean", + "required": false, + "description": "Enable reranking endpoint on server (env: LLAMA_ARG_RERANKING)", + "defaultValue": "False" + }, + { + "name": "metrics", + "type": "boolean", + "required": false, + "description": "Enable prometheus compatible metrics endpoint (env: LLAMA_ARG_ENDPOINT_METRICS)", + "defaultValue": "False" + }, + { + "name": "slots", + "type": "boolean", + "required": false, + "description": "Enable slots monitoring endpoint (env: LLAMA_ARG_ENDPOINT_SLOTS)", + "defaultValue": "False" + }, + { + "name": "draft", + "type": "integer", + "required": false, + "description": "Number of tokens to draft for speculative decoding (default: 16) (env: LLAMA_ARG_DRAFT_MAX)" + }, + { + "name": "draft_max", + "type": "integer", + "required": false, + "description": "Same as draft" + }, + { + "name": "draft_min", + "type": "integer", + "required": false, + "description": "Minimum number of draft tokens to use for speculative decoding (default: 5)" + }, + { + "name": "api_key", + "type": "string", + "required": false, + "description": "API key to use for authentication (env: LLAMA_API_KEY)" + }, + { + "name": "lora_files", + "type": "string", + "required": false, + "description": "Path to LoRA adapter (can be repeated to use multiple adapters)", + "defaultValue": "[]" + }, + { + "name": "no_context_shift", + "type": "boolean", + "required": false, + "description": "Disables context shift on infinite text generation", + "defaultValue": "False" + }, + { + "name": "no_webui", + "type": "boolean", + "required": false, + "description": "Disable web UI" + }, + { + "name": "startup_timeout", + "type": "integer", + "required": false, + "description": "Server startup timeout in seconds" + } + ] +}} /> + diff --git a/docs/docs/config-reference/llama_cpp_py_adapter_llamacppmodelparameters_e88874.mdx b/docs/docs/config-reference/llama_cpp_py_adapter_llamacppmodelparameters_e88874.mdx new file mode 100644 index 000000000..b2fec7719 --- /dev/null +++ b/docs/docs/config-reference/llama_cpp_py_adapter_llamacppmodelparameters_e88874.mdx @@ -0,0 +1,124 @@ +--- +title: "LlamaCppModelParameters Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + +')", + "defaultValue": "llama.cpp" + }, + { + "name": "verbose", + "type": "boolean", + "required": false, + "description": "Show verbose output.", + "defaultValue": "False" + }, + { + "name": "concurrency", + "type": "integer", + "required": false, + "description": "Model concurrency limit", + "defaultValue": "5" + }, + { + "name": "prompt_template", + "type": "string", + "required": false, + "description": "Prompt template. If None, the prompt template is automatically determined from model. Just for local deployment." + }, + { + "name": "context_length", + "type": "integer", + "required": false, + "description": "The context length of the model. If None, it is automatically determined from model." + }, + { + "name": "seed", + "type": "integer", + "required": false, + "description": "Random seed for llama-cpp models. -1 for random", + "defaultValue": "-1" + }, + { + "name": "n_threads", + "type": "integer", + "required": false, + "description": "Number of threads to use. If None, the number of threads is automatically determined" + }, + { + "name": "n_batch", + "type": "integer", + "required": false, + "description": "Maximum number of prompt tokens to batch together when calling llama_eval", + "defaultValue": "512" + }, + { + "name": "n_gpu_layers", + "type": "integer", + "required": false, + "description": "Number of layers to offload to the GPU, Set this to 1000000000 to offload all layers to the GPU.", + "defaultValue": "1000000000" + }, + { + "name": "n_gqa", + "type": "integer", + "required": false, + "description": "Grouped-query attention. Must be 8 for llama-2 70b." + }, + { + "name": "rms_norm_eps", + "type": "number", + "required": false, + "description": "5e-6 is a good value for llama-2 models.", + "defaultValue": "5e-06" + }, + { + "name": "cache_capacity", + "type": "string", + "required": false, + "description": "Maximum cache capacity. Examples: 2000MiB, 2GiB. When provided without units, bytes will be assumed. " + }, + { + "name": "prefer_cpu", + "type": "boolean", + "required": false, + "description": "If a GPU is available, it will be preferred by default, unless prefer_cpu=False is configured.", + "defaultValue": "False" + } + ] +}} /> + diff --git a/docs/docs/config-reference/manager_hookconfig_d9a481.mdx b/docs/docs/config-reference/manager_hookconfig_d9a481.mdx new file mode 100644 index 000000000..5f14ff7df --- /dev/null +++ b/docs/docs/config-reference/manager_hookconfig_d9a481.mdx @@ -0,0 +1,41 @@ +--- +title: "HookConfig Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/manager_modelcacheparameters_152367.mdx b/docs/docs/config-reference/manager_modelcacheparameters_152367.mdx new file mode 100644 index 000000000..65c6509d2 --- /dev/null +++ b/docs/docs/config-reference/manager_modelcacheparameters_152367.mdx @@ -0,0 +1,42 @@ +--- +title: "ModelCacheParameters Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/moonshot_moonshotdeploymodelparameters_aa2f6b.mdx b/docs/docs/config-reference/moonshot_moonshotdeploymodelparameters_aa2f6b.mdx new file mode 100644 index 000000000..be0384e3a --- /dev/null +++ b/docs/docs/config-reference/moonshot_moonshotdeploymodelparameters_aa2f6b.mdx @@ -0,0 +1,91 @@ +--- +title: "Moonshot Proxy LLM Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + +')", + "defaultValue": "proxy/moonshot" + }, + { + "name": "verbose", + "type": "boolean", + "required": false, + "description": "Show verbose output.", + "defaultValue": "False" + }, + { + "name": "concurrency", + "type": "integer", + "required": false, + "description": "Model concurrency limit", + "defaultValue": "100" + }, + { + "name": "prompt_template", + "type": "string", + "required": false, + "description": "Prompt template. If None, the prompt template is automatically determined from model. Just for local deployment." + }, + { + "name": "context_length", + "type": "integer", + "required": false, + "description": "The context length of the OpenAI API. If None, it is determined by the model." + }, + { + "name": "api_base", + "type": "string", + "required": false, + "description": "The base url of the Moonshot API.", + "defaultValue": "${env:MOONSHOT_API_BASE:-https://api.moonshot.cn/v1}" + }, + { + "name": "api_key", + "type": "string", + "required": false, + "description": "The API key of the Moonshot API.", + "defaultValue": "${env:MOONSHOT_API_KEY}" + }, + { + "name": "api_type", + "type": "string", + "required": false, + "description": "The type of the OpenAI API, if you use Azure, it can be: azure" + }, + { + "name": "api_version", + "type": "string", + "required": false, + "description": "The version of the OpenAI API." + }, + { + "name": "http_proxy", + "type": "string", + "required": false, + "description": "The http or https proxy to use openai" + } + ] +}} /> + diff --git a/docs/docs/config-reference/ollama_ollamadeploymodelparameters_d55be6.mdx b/docs/docs/config-reference/ollama_ollamadeploymodelparameters_d55be6.mdx new file mode 100644 index 000000000..76049104d --- /dev/null +++ b/docs/docs/config-reference/ollama_ollamadeploymodelparameters_d55be6.mdx @@ -0,0 +1,91 @@ +--- +title: "Ollama Proxy LLM Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + +')", + "defaultValue": "proxy/ollama" + }, + { + "name": "verbose", + "type": "boolean", + "required": false, + "description": "Show verbose output.", + "defaultValue": "False" + }, + { + "name": "concurrency", + "type": "integer", + "required": false, + "description": "Model concurrency limit", + "defaultValue": "100" + }, + { + "name": "prompt_template", + "type": "string", + "required": false, + "description": "Prompt template. If None, the prompt template is automatically determined from model. Just for local deployment." + }, + { + "name": "context_length", + "type": "integer", + "required": false, + "description": "The context length of the OpenAI API. If None, it is determined by the model." + }, + { + "name": "api_base", + "type": "string", + "required": false, + "description": "The base url of the Ollama API.", + "defaultValue": "${env:OLLAMA_API_BASE:-http://localhost:11434}" + }, + { + "name": "api_key", + "type": "string", + "required": false, + "description": "The API key of the OpenAI API.", + "defaultValue": "${env:OPENAI_API_KEY}" + }, + { + "name": "api_type", + "type": "string", + "required": false, + "description": "The type of the OpenAI API, if you use Azure, it can be: azure" + }, + { + "name": "api_version", + "type": "string", + "required": false, + "description": "The version of the OpenAI API." + }, + { + "name": "http_proxy", + "type": "string", + "required": false, + "description": "The http or https proxy to use openai" + } + ] +}} /> + diff --git a/docs/docs/config-reference/ollama_ollamaembeddingdeploymodelparameters_b511e0.mdx b/docs/docs/config-reference/ollama_ollamaembeddingdeploymodelparameters_b511e0.mdx new file mode 100644 index 000000000..4de0e2518 --- /dev/null +++ b/docs/docs/config-reference/ollama_ollamaembeddingdeploymodelparameters_b511e0.mdx @@ -0,0 +1,54 @@ +--- +title: "OllamaEmbeddingDeployModelParameters Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + +')", + "defaultValue": "proxy/ollama" + }, + { + "name": "verbose", + "type": "boolean", + "required": false, + "description": "Show verbose output.", + "defaultValue": "False" + }, + { + "name": "concurrency", + "type": "integer", + "required": false, + "description": "Model concurrency limit", + "defaultValue": "100" + }, + { + "name": "api_url", + "type": "string", + "required": false, + "description": "The URL of the embeddings API.", + "defaultValue": "http://localhost:11434" + }, + { + "name": "backend", + "type": "string", + "required": false, + "description": "The real model name to pass to the provider, default is None. If backend is None, use name as the real model name." + } + ] +}} /> + diff --git a/docs/docs/config-reference/overview.mdx b/docs/docs/config-reference/overview.mdx new file mode 100644 index 000000000..77cfd0236 --- /dev/null +++ b/docs/docs/config-reference/overview.mdx @@ -0,0 +1,483 @@ +import { ConfigDiagram } from "@site/src/components/mdx/ConfigDiagram"; + +# Configuration Overview + +## The layout of configuration classes + + \ No newline at end of file diff --git a/docs/docs/config-reference/parameter_bitsandbytesquantization4bits_52b778.mdx b/docs/docs/config-reference/parameter_bitsandbytesquantization4bits_52b778.mdx new file mode 100644 index 000000000..d4d7efdc2 --- /dev/null +++ b/docs/docs/config-reference/parameter_bitsandbytesquantization4bits_52b778.mdx @@ -0,0 +1,57 @@ +--- +title: "BitsandbytesQuantization4bits Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + + + diff --git a/docs/docs/config-reference/parameter_bitsandbytesquantization8bits_909aed.mdx b/docs/docs/config-reference/parameter_bitsandbytesquantization8bits_909aed.mdx new file mode 100644 index 000000000..9ef0b8a3a --- /dev/null +++ b/docs/docs/config-reference/parameter_bitsandbytesquantization8bits_909aed.mdx @@ -0,0 +1,49 @@ +--- +title: "BitsandbytesQuantization8bits Configuration" +--- + +import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail"; + +