Implementation:Bentoml BentoML Deployment Update Get List

Overview

Deployment Update, Get, List implements the Principle:Bentoml_BentoML_Deployment_Lifecycle_Management principle by providing functions to update running deployments, retrieve deployment details, and list deployments across clusters.

API

• bentoml.deployment.update()
• bentoml.deployment.get()
• bentoml.deployment.list()

Source

src/bentoml/deployment.py:L173-375

Import

import bentoml

Signatures

update()

def update(
    name: str = None,
    path_context: str = None,
    cluster: str = None,
    *,
    bento: Tag | str = None,
    scaling_min: int = None,
    scaling_max: int = None,
    instance_type: str = None,
    strategy: str = None,
    envs: list = None,
    labels: list = None,
    secrets: list[str] = None,
    extras: dict = None,
    config_dict: dict = None,
    config_file: str = None,
    args: dict = None,
) -> Deployment

get()

def get(
    name: str,
    cluster: str = None,
) -> Deployment

list()

def list(
    cluster: str = None,
    search: str = None,
    q: str = None,
    labels: list = None,
) -> list[Deployment]

Key Parameters

Function	Parameter	Type	Description
update	name	str	Deployment name to update
update	bento	str	New Bento version to deploy
update	scaling_min	int	Updated minimum replicas
update	scaling_max	int	Updated maximum replicas
update	instance_type	str	Updated compute instance type
update	config_file	str	Updated YAML config file
get	name	str	Deployment name to retrieve
get	cluster	str	Cluster to look in (optional)
list	cluster	str	Filter by cluster
list	search	str	Full-text search across deployment names
list	q	str	Structured query filter
list	labels	list	Filter by key-value labels

Inputs and Outputs

Inputs:

• Deployment name and updated configuration parameters (for update)
• Deployment name (for get)
• Optional filter criteria (for list)

Outputs:

• Deployment object (for update and get)
• list[Deployment] (for list)

Usage Examples

Update a Deployment

import bentoml

# Update to a new Bento version with zero downtime
deployment = bentoml.deployment.update(
    name="my-llm-service",
    bento="llm_service:v3",
    scaling_max=10,
)
print(f"Updated: {deployment.name}, status: {deployment.status}")

Get Deployment Details

import bentoml

# Retrieve deployment information
deployment = bentoml.deployment.get("my-llm-service")
print(f"Name: {deployment.name}")
print(f"Status: {deployment.status}")
print(f"Cluster: {deployment.cluster}")
print(f"Console: {deployment.admin_console}")

List All Deployments

import bentoml

# List all deployments
all_deployments = bentoml.deployment.list()
for d in all_deployments:
    print(f"{d.name}: {d.status}")

# Filter by cluster
cluster_deployments = bentoml.deployment.list(cluster="gcp-us-central1")

# Search by name
search_results = bentoml.deployment.list(search="llm")

# Filter by labels
labeled = bentoml.deployment.list(labels=[{"key": "team", "value": "ml-platform"}])

CLI Usage

# Update deployment
bentoml deployment update my-llm-service --bento llm_service:v3

# Get deployment info
bentoml deployment get my-llm-service

# List deployments
bentoml deployment list
bentoml deployment list --cluster gcp-us-central1
bentoml deployment list --search llm

Metadata

Property	Value
Implementation	Deployment Update, Get, List
API	bentoml.deployment.update(), .get(), .list()
Source	src/bentoml/deployment.py:L173-375
Domain	ML_Serving, Cloud_Deployment, Operations
Workflow	BentoCloud_Deployment
Principle	Principle:Bentoml_BentoML_Deployment_Lifecycle_Management

Knowledge Sources

• BentoML
• BentoML Docs

Related Pages

• Principle:Bentoml_BentoML_Deployment_Lifecycle_Management
• Environment:Bentoml_BentoML_BentoCloud_Credentials