datarobot-model-deployment

Name: datarobot-model-deployment
Author: datarobot-oss

22stars19forks

How to install datarobot-model-deployment?

datarobot-oss/datarobot-agent-skills/datarobot-model-deployment

$npx -y skills add datarobot-oss/datarobot-agent-skills --skill datarobot-model-deployment

Installs into the current project.

Summary

Tools and guidance for deploying DataRobot models, managing deployments, configuring prediction environments, and deployment operations. Use when deploying models, creating or updating deployments, or configuring prediction environments.

Files · 1

View on GitHub

SKILL.md

1	# DataRobot Model Deployment Skill
2
3	This skill provides comprehensive guidance for deploying models, managing deployment configurations, and operating production deployments.
4
5	## Quick Start
6
7	Most common use case: Deploy a trained model to production
8
9	1. Get best model: Find the best model from a project (highest metric score)
10	2. Create deployment: `create_deployment(model_id, deployment_name)` to deploy model
11	3. Get endpoint: `get_deployment_endpoint(deployment_id)` to retrieve prediction URL
12
13	Example: "Deploy the best model from project abc123 as 'Sales Prediction v1'"
14
15	## When to use this skill
16
17	Use this skill when you need to:
18	- Deploy trained models to production
19	- Configure deployment settings and environments
20	- Manage multiple deployments
21	- Replace a deployment’s champion model with a new model version
22	- Configure prediction servers and environments
23	- Monitor deployment health and status
24	- Manage deployment access and permissions
25
26	## Key capabilities
27
28	### 1. Deployment Creation
29
30	- Deploy models from projects or registered models
31	- Choose prediction environment (DataRobot Serverless, external)
32	- Configure deployment settings (challenger models, A/B testing)
33	- Set up deployment metadata and descriptions
34
35	### 2. Deployment Configuration
36
37	- Configure prediction servers and environments
38	- Set up batch prediction settings
39	- Configure real-time prediction endpoints
40	- Manage deployment credentials and access
41
42	### 3. Deployment Management
43
44	- Replace deployment champion model (model swap)
45	- Enable/disable deployments
46	- Manage challenger models for A/B testing
47	- Configure replacement policies
48
49	### 4. Deployment Operations
50
51	- Get deployment information and status
52	- Retrieve deployment endpoints
53	- Manage deployment settings
54	- Handle deployment errors and issues
55
56	## Workflow examples
57
58	### Example 1: Deploy a model to production
59
60	User request: "Deploy the best model from project abc123 to production with the name 'Sales Prediction v1'."
61
62	Agent workflow:
63	1. Get the best model from the project (highest metric score)
64	2. Create a new deployment with the model
65	3. Configure deployment settings (name, description, environment)
66	4. Set up prediction environment (DataRobot Serverless recommended)
67	5. Retrieve deployment endpoint and credentials
68	6. Verify deployment is active and ready for predictions
69
70	### Example 2: Update deployment with new model
71
72	User request: "Replace the model in deployment xyz789 with the latest model from project abc123."
73
74	Agent workflow:
75	1. Get the latest model from the project
76	2. Retrieve current deployment information
77	3. Validate the replacement model is eligible (`deployment.validate_replacement_model(...)`)
78	4. Perform model replacement (`deployment.perform_model_replace(...)`)
79	5. Verify replacement completed successfully
80	6. Report deployment update status
81
82	## Using DataRobot SDK
83
84	This skill guides you to use the DataRobot Python SDK directly. Install the SDK if needed:
85
86	```bash
87	pip install datarobot
88	```
89
90	### Key SDK Operations
91
92	Use these DataRobot SDK methods for deployment management:
93
94	Deployments:
95	- `dr.Deployment.create_from_learning_model(model_id, label)` - Create deployment
96	- `dr.Deployment.get(deployment_id)` - Get deployment details
97	- `dr.Deployment.list(project_id)` - List deployments
98	- `deployment.delete()` - Delete deployment
99
100	Model Replacement (champion swap):
101	- `deployment.validate_replacement_model(new_model_id=...)` - Validate replacement eligibility
102	- `deployment.perform_model_replace(new_model_id=..., reason=...)` - Replace champion model (async)
103
104	Challenger Models (limited via SDK):
105	- `deployment.list_challengers()` - List challenger models (if enabled/configured)
106	- `deployment.get_challenger_models_settings()` / `deployment.update_challenger_models_settings(...)` - Configure challenger models settings
107
108	Deployment Info:
109	- `deployment.get_features()` - Get required features
110
111	See the [Common Patterns](#common-patterns) section below for complete examples.
112
113	## Best practices
114
115	1. Naming conventions: Use clear, versioned names for deployments
116	2. Environment selection: Choose appropriate prediction environment for your use case
117	3. Challenger models: Use challenger models to test new models before full replacement
118	4. Monitoring: Set up monitoring and alerts for production deployments
119	5. Documentation: Document deployment purpose, model version, and configuration
120	6. Access control: Configure appropriate access permissions for deployments
121
122	## Common patterns
123
124	### Pattern 1: Standard deployment
125	```python
126	import datarobot as dr
127	import os
128
129	# Initialize client
130	client = dr.Client(
131	token=os.getenv("DATAROBOT_API_TOKEN"),
132	end

People who liked this also viewed

6 picks

Type

datarobot-model-deployment

22stars19forks

View on GitHub

How to install datarobot-model-deployment?

datarobot-oss/datarobot-agent-skills/datarobot-model-deployment

$npx -y skills add datarobot-oss/datarobot-agent-skills --skill datarobot-model-deployment

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# DataRobot Model Deployment Skill
2
3	This skill provides comprehensive guidance for deploying models, managing deployment configurations, and operating production deployments.
4
5	## Quick Start
6
7	Most common use case: Deploy a trained model to production
8
9	1. Get best model: Find the best model from a project (highest metric score)
10	2. Create deployment: `create_deployment(model_id, deployment_name)` to deploy model
11	3. Get endpoint: `get_deployment_endpoint(deployment_id)` to retrieve prediction URL
12
13	Example: "Deploy the best model from project abc123 as 'Sales Prediction v1'"
14
15	## When to use this skill
16
17	Use this skill when you need to:
18	- Deploy trained models to production
19	- Configure deployment settings and environments
20	- Manage multiple deployments
21	- Replace a deployment’s champion model with a new model version
22	- Configure prediction servers and environments
23	- Monitor deployment health and status
24	- Manage deployment access and permissions
25
26	## Key capabilities
27
28	### 1. Deployment Creation
29
30	- Deploy models from projects or registered models
31	- Choose prediction environment (DataRobot Serverless, external)
32	- Configure deployment settings (challenger models, A/B testing)
33	- Set up deployment metadata and descriptions
34
35	### 2. Deployment Configuration
36
37	- Configure prediction servers and environments
38	- Set up batch prediction settings
39	- Configure real-time prediction endpoints
40	- Manage deployment credentials and access
41
42	### 3. Deployment Management
43
44	- Replace deployment champion model (model swap)
45	- Enable/disable deployments
46	- Manage challenger models for A/B testing
47	- Configure replacement policies
48
49	### 4. Deployment Operations
50
51	- Get deployment information and status
52	- Retrieve deployment endpoints
53	- Manage deployment settings
54	- Handle deployment errors and issues
55
56	## Workflow examples
57
58	### Example 1: Deploy a model to production
59
60	User request: "Deploy the best model from project abc123 to production with the name 'Sales Prediction v1'."
61
62	Agent workflow:
63	1. Get the best model from the project (highest metric score)
64	2. Create a new deployment with the model
65	3. Configure deployment settings (name, description, environment)
66	4. Set up prediction environment (DataRobot Serverless recommended)
67	5. Retrieve deployment endpoint and credentials
68	6. Verify deployment is active and ready for predictions
69
70	### Example 2: Update deployment with new model
71
72	User request: "Replace the model in deployment xyz789 with the latest model from project abc123."
73
74	Agent workflow:
75	1. Get the latest model from the project
76	2. Retrieve current deployment information
77	3. Validate the replacement model is eligible (`deployment.validate_replacement_model(...)`)
78	4. Perform model replacement (`deployment.perform_model_replace(...)`)
79	5. Verify replacement completed successfully
80	6. Report deployment update status
81
82	## Using DataRobot SDK
83
84	This skill guides you to use the DataRobot Python SDK directly. Install the SDK if needed:
85
86	```bash
87	pip install datarobot
88	```
89
90	### Key SDK Operations
91
92	Use these DataRobot SDK methods for deployment management:
93
94	Deployments:
95	- `dr.Deployment.create_from_learning_model(model_id, label)` - Create deployment
96	- `dr.Deployment.get(deployment_id)` - Get deployment details
97	- `dr.Deployment.list(project_id)` - List deployments
98	- `deployment.delete()` - Delete deployment
99
100	Model Replacement (champion swap):
101	- `deployment.validate_replacement_model(new_model_id=...)` - Validate replacement eligibility
102	- `deployment.perform_model_replace(new_model_id=..., reason=...)` - Replace champion model (async)
103
104	Challenger Models (limited via SDK):
105	- `deployment.list_challengers()` - List challenger models (if enabled/configured)
106	- `deployment.get_challenger_models_settings()` / `deployment.update_challenger_models_settings(...)` - Configure challenger models settings
107
108	Deployment Info:
109	- `deployment.get_features()` - Get required features
110
111	See the [Common Patterns](#common-patterns) section below for complete examples.
112
113	## Best practices
114
115	1. Naming conventions: Use clear, versioned names for deployments
116	2. Environment selection: Choose appropriate prediction environment for your use case
117	3. Challenger models: Use challenger models to test new models before full replacement
118	4. Monitoring: Set up monitoring and alerts for production deployments
119	5. Documentation: Document deployment purpose, model version, and configuration
120	6. Access control: Configure appropriate access permissions for deployments
121
122	## Common patterns
123
124	### Pattern 1: Standard deployment
125	```python
126	import datarobot as dr
127	import os
128
129	# Initialize client
130	client = dr.Client(
131	token=os.getenv("DATAROBOT_API_TOKEN"),
132	end

People who liked this also viewed

6 picks

Type