The timeout in milliseconds of the control request, -1 for waiting forever
Default: 60
--polling
The polling strategy of the Deployment and its endpoints (when shards>1).
Can be defined for all endpoints of a Deployment or by endpoint.
Define per Deployment:
- ANY: only one (whoever is idle) Pod polls the message
- ALL: all Pods poll the message (like a broadcast)
Define per Endpoint:
JSON dict, {endpoint: PollingType}
{‘/custom’: ‘ALL’, ‘/search’: ‘ANY’, ‘*’: ‘ANY’}
The config of the executor, it could be one of the followings:
* the string literal of an Executor class name
* an Executor YAML file (.yml, .yaml, .jaml)
* a Jina Hub Executor (must start with jinahub:// or jinahub+docker://)
* a docker image (must start with docker://)
* the string literal of a YAML config (must start with ! or `jtype: `)
* the string literal of a JSON config
When use it under Python, one can use the following values additionally:
- a Python dict that represents the config
- a text file stream has .read() interface
Default: “BaseExecutor”
--uses-with
Dictionary of keyword arguments that will override the with configuration in uses
--uses-metas
Dictionary of keyword arguments that will override the metas configuration in uses
--uses-requests
Dictionary of keyword arguments that will override the requests configuration in uses
--py-modules
The customized python modules need to be imported before loading the executor
Note that the recommended way is to only import a single module - a simple python file, if your
executor can be defined in a single file, or an __init__.py file if you have multiple files,
which should be structured as a python package. For more details, please see the
Executor cookbook
--port-in
The port for input data to bind to, default a random port between [49152, 65535]
Default: 50143
--host-in
The host address for binding to, by default it is 0.0.0.0
Default: “0.0.0.0”
--native
If set, only native Executors is allowed, and the Executor is always run inside WorkerRuntime.
Default: False
--output-array-type
The type of array tensor and embedding will be serialized to.
Supports the same types as docarray.to_protobuf(.., ndarray_type=…), which can be found
here <https://docarray.jina.ai/fundamentals/document/serialization/#from-to-protobuf>.
Defaults to retaining whatever type is returned by the Executor.
--grpc-server-options
Dictionary of kwargs arguments that will be passed to the grpc server as options when starting the server, example : {‘grpc.max_send_message_length’: -1}
The path on the host to be mounted inside the container.
Note,
- If separated by :, then the first part will be considered as the local host path and the second part is the path in the container system.
- If no split provided, then the basename of that directory will be mounted into container’s root path, e.g. –volumes=”/user/test/my-workspace” will be mounted into /my-workspace inside the container.
- All volumes are mounted with read-write mode.
--gpus
This argument allows dockerized Jina executor discover local gpu devices.
Note,
- To access all gpus, use –gpus all.
- To access multiple gpus, e.g. make use of 2 gpus, use –gpus 2.
- To access specified gpus based on device id, use –gpus device=[YOUR-GPU-DEVICE-ID]
- To access specified gpus based on multiple device id, use –gpus device=[YOUR-GPU-DEVICE-ID1],device=[YOUR-GPU-DEVICE-ID2]
- To specify more parameters, use `–gpus device=[YOUR-GPU-DEVICE-ID],runtime=nvidia,capabilities=display
--disable-auto-volume
Do not automatically mount a volume for dockerized Executors.
Do not display the streaming of remote logs on local console
Default: False
--upload-files
The files on the host to be uploaded to the remote
workspace. This can be useful when your Deployment has more
file dependencies beyond a single YAML file, e.g.
Python files, data files.
Note,
- currently only flatten structure is supported, which means if you upload [./foo/a.py, ./foo/b.pp, ./bar/c.yml], then they will be put under the _same_ workspace on the remote, losing all hierarchies.
- by default, –uses YAML file is always uploaded.
- uploaded files are by default isolated across the runs. To ensure files are submitted to the same workspace across different runs, use –workspace-id to specify the workspace.
The timeout in milliseconds of the control request, -1 for waiting forever
Default: 60
--polling
The polling strategy of the Deployment and its endpoints (when shards>1).
Can be defined for all endpoints of a Deployment or by endpoint.
Define per Deployment:
- ANY: only one (whoever is idle) Pod polls the message
- ALL: all Pods poll the message (like a broadcast)
Define per Endpoint:
JSON dict, {endpoint: PollingType}
{‘/custom’: ‘ALL’, ‘/search’: ‘ANY’, ‘*’: ‘ANY’}
The config of the executor, it could be one of the followings:
* the string literal of an Executor class name
* an Executor YAML file (.yml, .yaml, .jaml)
* a Jina Hub Executor (must start with jinahub:// or jinahub+docker://)
* a docker image (must start with docker://)
* the string literal of a YAML config (must start with ! or `jtype: `)
* the string literal of a JSON config
When use it under Python, one can use the following values additionally:
- a Python dict that represents the config
- a text file stream has .read() interface
Default: “BaseExecutor”
--uses-with
Dictionary of keyword arguments that will override the with configuration in uses
--uses-metas
Dictionary of keyword arguments that will override the metas configuration in uses
--uses-requests
Dictionary of keyword arguments that will override the requests configuration in uses
--py-modules
The customized python modules need to be imported before loading the executor
Note that the recommended way is to only import a single module - a simple python file, if your
executor can be defined in a single file, or an __init__.py file if you have multiple files,
which should be structured as a python package. For more details, please see the
Executor cookbook
--port-in
The port for input data to bind to, default a random port between [49152, 65535]
Default: 58328
--host-in
The host address for binding to, by default it is 0.0.0.0
Default: “0.0.0.0”
--native
If set, only native Executors is allowed, and the Executor is always run inside WorkerRuntime.
Default: False
--output-array-type
The type of array tensor and embedding will be serialized to.
Supports the same types as docarray.to_protobuf(.., ndarray_type=…), which can be found
here <https://docarray.jina.ai/fundamentals/document/serialization/#from-to-protobuf>.
Defaults to retaining whatever type is returned by the Executor.
--grpc-server-options
Dictionary of kwargs arguments that will be passed to the grpc server as options when starting the server, example : {‘grpc.max_send_message_length’: -1}
The host address of the runtime, by default it is 0.0.0.0.
Default: “0.0.0.0”
--proxy
If set, respect the http_proxy and https_proxy environment variables. otherwise, it will unset these proxy variables before start. gRPC seems to prefer no proxy
Default: False
--port-expose
The port that the gateway exposes for clients for GRPC connections.
The string ID of a flow for single removal, or a list of space seperated string IDs for multiple removal, or string ‘all’ for deleting ALL ALIVE flows.
The timeout in milliseconds of the control request, -1 for waiting forever
Default: 60
--polling
The polling strategy of the Deployment and its endpoints (when shards>1).
Can be defined for all endpoints of a Deployment or by endpoint.
Define per Deployment:
- ANY: only one (whoever is idle) Pod polls the message
- ALL: all Pods poll the message (like a broadcast)
Define per Endpoint:
JSON dict, {endpoint: PollingType}
{‘/custom’: ‘ALL’, ‘/search’: ‘ANY’, ‘*’: ‘ANY’}
The config of the executor, it could be one of the followings:
* the string literal of an Executor class name
* an Executor YAML file (.yml, .yaml, .jaml)
* a Jina Hub Executor (must start with jinahub:// or jinahub+docker://)
* a docker image (must start with docker://)
* the string literal of a YAML config (must start with ! or `jtype: `)
* the string literal of a JSON config
When use it under Python, one can use the following values additionally:
- a Python dict that represents the config
- a text file stream has .read() interface
Default: “BaseExecutor”
--uses-with
Dictionary of keyword arguments that will override the with configuration in uses
--uses-metas
Dictionary of keyword arguments that will override the metas configuration in uses
--uses-requests
Dictionary of keyword arguments that will override the requests configuration in uses
--py-modules
The customized python modules need to be imported before loading the executor
Note that the recommended way is to only import a single module - a simple python file, if your
executor can be defined in a single file, or an __init__.py file if you have multiple files,
which should be structured as a python package. For more details, please see the
Executor cookbook
--port-in
The port for input data to bind to, default a random port between [49152, 65535]
Default: 52762
--host-in
The host address for binding to, by default it is 0.0.0.0
Default: “0.0.0.0”
--native
If set, only native Executors is allowed, and the Executor is always run inside WorkerRuntime.
Default: False
--output-array-type
The type of array tensor and embedding will be serialized to.
Supports the same types as docarray.to_protobuf(.., ndarray_type=…), which can be found
here <https://docarray.jina.ai/fundamentals/document/serialization/#from-to-protobuf>.
Defaults to retaining whatever type is returned by the Executor.
--grpc-server-options
Dictionary of kwargs arguments that will be passed to the grpc server as options when starting the server, example : {‘grpc.max_send_message_length’: -1}
The path on the host to be mounted inside the container.
Note,
- If separated by :, then the first part will be considered as the local host path and the second part is the path in the container system.
- If no split provided, then the basename of that directory will be mounted into container’s root path, e.g. –volumes=”/user/test/my-workspace” will be mounted into /my-workspace inside the container.
- All volumes are mounted with read-write mode.
--gpus
This argument allows dockerized Jina executor discover local gpu devices.
Note,
- To access all gpus, use –gpus all.
- To access multiple gpus, e.g. make use of 2 gpus, use –gpus 2.
- To access specified gpus based on device id, use –gpus device=[YOUR-GPU-DEVICE-ID]
- To access specified gpus based on multiple device id, use –gpus device=[YOUR-GPU-DEVICE-ID1],device=[YOUR-GPU-DEVICE-ID2]
- To specify more parameters, use `–gpus device=[YOUR-GPU-DEVICE-ID],runtime=nvidia,capabilities=display
--disable-auto-volume
Do not automatically mount a volume for dockerized Executors.
Do not display the streaming of remote logs on local console
Default: False
--upload-files
The files on the host to be uploaded to the remote
workspace. This can be useful when your Deployment has more
file dependencies beyond a single YAML file, e.g.
Python files, data files.
Note,
- currently only flatten structure is supported, which means if you upload [./foo/a.py, ./foo/b.pp, ./bar/c.yml], then they will be put under the _same_ workspace on the remote, losing all hierarchies.
- by default, –uses YAML file is always uploaded.
- uploaded files are by default isolated across the runs. To ensure files are submitted to the same workspace across different runs, use –workspace-id to specify the workspace.
The timeout in milliseconds of the control request, -1 for waiting forever
Default: 60
--polling
The polling strategy of the Deployment and its endpoints (when shards>1).
Can be defined for all endpoints of a Deployment or by endpoint.
Define per Deployment:
- ANY: only one (whoever is idle) Pod polls the message
- ALL: all Pods poll the message (like a broadcast)
Define per Endpoint:
JSON dict, {endpoint: PollingType}
{‘/custom’: ‘ALL’, ‘/search’: ‘ANY’, ‘*’: ‘ANY’}
The config of the executor, it could be one of the followings:
* the string literal of an Executor class name
* an Executor YAML file (.yml, .yaml, .jaml)
* a Jina Hub Executor (must start with jinahub:// or jinahub+docker://)
* a docker image (must start with docker://)
* the string literal of a YAML config (must start with ! or `jtype: `)
* the string literal of a JSON config
When use it under Python, one can use the following values additionally:
- a Python dict that represents the config
- a text file stream has .read() interface
Default: “BaseExecutor”
--uses-with
Dictionary of keyword arguments that will override the with configuration in uses
--uses-metas
Dictionary of keyword arguments that will override the metas configuration in uses
--uses-requests
Dictionary of keyword arguments that will override the requests configuration in uses
--py-modules
The customized python modules need to be imported before loading the executor
Note that the recommended way is to only import a single module - a simple python file, if your
executor can be defined in a single file, or an __init__.py file if you have multiple files,
which should be structured as a python package. For more details, please see the
Executor cookbook
--port-in
The port for input data to bind to, default a random port between [49152, 65535]
Default: 50358
--host-in
The host address for binding to, by default it is 0.0.0.0
Default: “0.0.0.0”
--native
If set, only native Executors is allowed, and the Executor is always run inside WorkerRuntime.
Default: False
--output-array-type
The type of array tensor and embedding will be serialized to.
Supports the same types as docarray.to_protobuf(.., ndarray_type=…), which can be found
here <https://docarray.jina.ai/fundamentals/document/serialization/#from-to-protobuf>.
Defaults to retaining whatever type is returned by the Executor.
--grpc-server-options
Dictionary of kwargs arguments that will be passed to the grpc server as options when starting the server, example : {‘grpc.max_send_message_length’: -1}
The path on the host to be mounted inside the container.
Note,
- If separated by :, then the first part will be considered as the local host path and the second part is the path in the container system.
- If no split provided, then the basename of that directory will be mounted into container’s root path, e.g. –volumes=”/user/test/my-workspace” will be mounted into /my-workspace inside the container.
- All volumes are mounted with read-write mode.
--gpus
This argument allows dockerized Jina executor discover local gpu devices.
Note,
- To access all gpus, use –gpus all.
- To access multiple gpus, e.g. make use of 2 gpus, use –gpus 2.
- To access specified gpus based on device id, use –gpus device=[YOUR-GPU-DEVICE-ID]
- To access specified gpus based on multiple device id, use –gpus device=[YOUR-GPU-DEVICE-ID1],device=[YOUR-GPU-DEVICE-ID2]
- To specify more parameters, use `–gpus device=[YOUR-GPU-DEVICE-ID],runtime=nvidia,capabilities=display
--disable-auto-volume
Do not automatically mount a volume for dockerized Executors.
Do not display the streaming of remote logs on local console
Default: False
--upload-files
The files on the host to be uploaded to the remote
workspace. This can be useful when your Deployment has more
file dependencies beyond a single YAML file, e.g.
Python files, data files.
Note,
- currently only flatten structure is supported, which means if you upload [./foo/a.py, ./foo/b.pp, ./bar/c.yml], then they will be put under the _same_ workspace on the remote, losing all hierarchies.
- by default, –uses YAML file is always uploaded.
- uploaded files are by default isolated across the runs. To ensure files are submitted to the same workspace across different runs, use –workspace-id to specify the workspace.
The executor attached before the Pods described by –uses, typically before sending to all shards, accepted type follows –uses. This argument only applies for sharded Deployments (shards > 1).
--uses-after
The executor attached after the Pods described by –uses, typically used for receiving from all shards, accepted type follows –uses. This argument only applies for sharded Deployments (shards > 1).
--when
The condition that the documents need to fulfill before reaching the Executor.The condition can be defined in the form of a DocArray query condition <https://docarray.jina.ai/fundamentals/documentarray/find/#query-by-conditions>
--external
The Deployment will be considered an external Deployment that has been started independently from the Flow.This Deployment will not be context managed by the Flow.
Default: False
--tls
If set, connect to deployment using tls encryption
The host address of the runtime, by default it is 0.0.0.0.
Default: “0.0.0.0”
--proxy
If set, respect the http_proxy and https_proxy environment variables. otherwise, it will unset these proxy variables before start. gRPC seems to prefer no proxy
Default: False
--port
The port of the Gateway, which the client should connect to.