agents-v2-py

Name: agents-v2-py
Author: sickn33

44kstars6.5kforks

How to install agents-v2-py?

sickn33/agentic-awesome-skills/agents-v2-py

$npx -y skills add sickn33/agentic-awesome-skills --skill agents-v2-py

Installs into the current project.

Summary

Build container-based Foundry Agents with Azure AI Projects SDK (ImageBasedHostedAgentDefinition). Use when creating hosted agents with custom container images in Azure AI Foundry.

Files · 1

View on GitHub

SKILL.md

1	# Azure AI Hosted Agents (Python)
2
3	Build container-based hosted agents using `ImageBasedHostedAgentDefinition` from the Azure AI Projects SDK.
4
5	## Installation
6
7	```bash
8	pip install azure-ai-projects>=2.0.0b3 azure-identity
9	```
10
11	Minimum SDK Version: `2.0.0b3` or later required for hosted agent support.
12
13	## Environment Variables
14
15	```bash
16	AZURE_AI_PROJECT_ENDPOINT=https://<resource>.services.ai.azure.com/api/projects/<project>
17	```
18
19	## Prerequisites
20
21	Before creating hosted agents:
22
23	1. Container Image - Build and push to Azure Container Registry (ACR)
24	2. ACR Pull Permissions - Grant your project's managed identity `AcrPull` role on the ACR
25	3. Capability Host - Account-level capability host with `enablePublicHostingEnvironment=true`
26	4. SDK Version - Ensure `azure-ai-projects>=2.0.0b3`
27
28	## Authentication
29
30	Always use `DefaultAzureCredential`:
31
32	```python
33	from azure.identity import DefaultAzureCredential
34	from azure.ai.projects import AIProjectClient
35
36	credential = DefaultAzureCredential()
37	client = AIProjectClient(
38	endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
39	credential=credential
40	)
41	```
42
43	## Core Workflow
44
45	### 1. Imports
46
47	```python
48	import os
49	from azure.identity import DefaultAzureCredential
50	from azure.ai.projects import AIProjectClient
51	from azure.ai.projects.models import (
52	ImageBasedHostedAgentDefinition,
53	ProtocolVersionRecord,
54	AgentProtocol,
55	)
56	```
57
58	### 2. Create Hosted Agent
59
60	```python
61	client = AIProjectClient(
62	endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
63	credential=DefaultAzureCredential()
64	)
65
66	agent = client.agents.create_version(
67	agent_name="my-hosted-agent",
68	definition=ImageBasedHostedAgentDefinition(
69	container_protocol_versions=[
70	ProtocolVersionRecord(protocol=AgentProtocol.RESPONSES, version="v1")
71	],
72	cpu="1",
73	memory="2Gi",
74	image="myregistry.azurecr.io/my-agent:latest",
75	tools=[{"type": "code_interpreter"}],
76	environment_variables={
77	"AZURE_AI_PROJECT_ENDPOINT": os.environ["AZURE_AI_PROJECT_ENDPOINT"],
78	"MODEL_NAME": "gpt-4o-mini"
79	}
80	)
81	)
82
83	print(f"Created agent: {agent.name} (version: {agent.version})")
84	```
85
86	### 3. List Agent Versions
87
88	```python
89	versions = client.agents.list_versions(agent_name="my-hosted-agent")
90	for version in versions:
91	print(f"Version: {version.version}, State: {version.state}")
92	```
93
94	### 4. Delete Agent Version
95
96	```python
97	client.agents.delete_version(
98	agent_name="my-hosted-agent",
99	version=agent.version
100	)
101	```
102
103	## ImageBasedHostedAgentDefinition Parameters
104
105	\| Parameter \| Type \| Required \| Description \|
106	\|-----------\|------\|----------\|-------------\|
107	\| `container_protocol_versions` \| `list[ProtocolVersionRecord]` \| Yes \| Protocol versions the agent supports \|
108	\| `image` \| `str` \| Yes \| Full container image path (registry/image:tag) \|
109	\| `cpu` \| `str` \| No \| CPU allocation (e.g., "1", "2") \|
110	\| `memory` \| `str` \| No \| Memory allocation (e.g., "2Gi", "4Gi") \|
111	\| `tools` \| `list[dict]` \| No \| Tools available to the agent \|
112	\| `environment_variables` \| `dict[str, str]` \| No \| Environment variables for the container \|
113
114	## Protocol Versions
115
116	The `container_protocol_versions` parameter specifies which protocols your agent supports:
117
118	```python
119	from azure.ai.projects.models import ProtocolVersionRecord, AgentProtocol
120
121	# RESPONSES protocol - standard agent responses
122	container_protocol_versions=[
123	ProtocolVersionRecord(protocol=AgentProtocol.RESPONSES, version="v1")
124	]
125	```
126
127	Available Protocols:
128	\| Protocol \| Description \|
129	\|----------\|-------------\|
130	\| `AgentProtocol.RESPONSES` \| Standard response protocol for agent interactions \|
131
132	## Resource Allocation
133
134	Specify CPU and memory for your container:
135
136	```python
137	definition=ImageBasedHostedAgentDefinition(
138	container_protocol_versions=[...],
139	image="myregistry.azurecr.io/my-agent:latest",
140	cpu="2", # 2 CPU cores
141	memory="4Gi" # 4 GiB memory
142	)
143	```
144
145	Resource Limits:
146	\| Resource \| Min \| Max \| Default \|
147	\|----------\|-----\|-----\|---------\|
148	\| CPU \| 0.5 \| 4 \| 1 \|
149	\| Memory \| 1Gi \| 8Gi \| 2Gi \|
150
151	## Tools Configuration
152
153	Add tools to your hosted agent:
154
155	### Code Interpreter
156
157	```python
158	tools=[{"type": "code_interpreter"}]
159	```
160
161	### MCP Tools
162
163	```python
164	tools=[
165	{"type": "code_interpreter"},
166	{
167	"type": "mcp",
168	"server_label": "my-mcp-server",
169	"server_url": "https://my-mcp-server.example.com"
170	}
171	]
172	```
173
174	### Multiple Tools
175
176	```python
177	tools=[
178	{"type": "code_interpreter"},
179	{"type": "file_search"},
180	{
181	"type": "mcp",
182	"server_label": "custom-tool",
183	"server_url": "https://custom-tool.example.com"
184	}
185	]
186	```
187
188	### Environment Variables
189
190	Pass configuration to y

People who liked this also viewed

6 picks

Type

find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 20262.6M27k
grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026633k182k
vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026573k29k
improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026522k182k
setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026454k182k
triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026424k182k

agents-v2-py

44kstars6.5kforks

View on GitHub

How to install agents-v2-py?

sickn33/agentic-awesome-skills/agents-v2-py

$npx -y skills add sickn33/agentic-awesome-skills --skill agents-v2-py

Installs into the current project.

Summary

Build container-based Foundry Agents with Azure AI Projects SDK (ImageBasedHostedAgentDefinition). Use when creating hosted agents with custom container images in Azure AI Foundry.

Files · 1

View on GitHub

SKILL.md

1	# Azure AI Hosted Agents (Python)
2
3	Build container-based hosted agents using `ImageBasedHostedAgentDefinition` from the Azure AI Projects SDK.
4
5	## Installation
6
7	```bash
8	pip install azure-ai-projects>=2.0.0b3 azure-identity
9	```
10
11	Minimum SDK Version: `2.0.0b3` or later required for hosted agent support.
12
13	## Environment Variables
14
15	```bash
16	AZURE_AI_PROJECT_ENDPOINT=https://<resource>.services.ai.azure.com/api/projects/<project>
17	```
18
19	## Prerequisites
20
21	Before creating hosted agents:
22
23	1. Container Image - Build and push to Azure Container Registry (ACR)
24	2. ACR Pull Permissions - Grant your project's managed identity `AcrPull` role on the ACR
25	3. Capability Host - Account-level capability host with `enablePublicHostingEnvironment=true`
26	4. SDK Version - Ensure `azure-ai-projects>=2.0.0b3`
27
28	## Authentication
29
30	Always use `DefaultAzureCredential`:
31
32	```python
33	from azure.identity import DefaultAzureCredential
34	from azure.ai.projects import AIProjectClient
35
36	credential = DefaultAzureCredential()
37	client = AIProjectClient(
38	endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
39	credential=credential
40	)
41	```
42
43	## Core Workflow
44
45	### 1. Imports
46
47	```python
48	import os
49	from azure.identity import DefaultAzureCredential
50	from azure.ai.projects import AIProjectClient
51	from azure.ai.projects.models import (
52	ImageBasedHostedAgentDefinition,
53	ProtocolVersionRecord,
54	AgentProtocol,
55	)
56	```
57
58	### 2. Create Hosted Agent
59
60	```python
61	client = AIProjectClient(
62	endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
63	credential=DefaultAzureCredential()
64	)
65
66	agent = client.agents.create_version(
67	agent_name="my-hosted-agent",
68	definition=ImageBasedHostedAgentDefinition(
69	container_protocol_versions=[
70	ProtocolVersionRecord(protocol=AgentProtocol.RESPONSES, version="v1")
71	],
72	cpu="1",
73	memory="2Gi",
74	image="myregistry.azurecr.io/my-agent:latest",
75	tools=[{"type": "code_interpreter"}],
76	environment_variables={
77	"AZURE_AI_PROJECT_ENDPOINT": os.environ["AZURE_AI_PROJECT_ENDPOINT"],
78	"MODEL_NAME": "gpt-4o-mini"
79	}
80	)
81	)
82
83	print(f"Created agent: {agent.name} (version: {agent.version})")
84	```
85
86	### 3. List Agent Versions
87
88	```python
89	versions = client.agents.list_versions(agent_name="my-hosted-agent")
90	for version in versions:
91	print(f"Version: {version.version}, State: {version.state}")
92	```
93
94	### 4. Delete Agent Version
95
96	```python
97	client.agents.delete_version(
98	agent_name="my-hosted-agent",
99	version=agent.version
100	)
101	```
102
103	## ImageBasedHostedAgentDefinition Parameters
104
105	\| Parameter \| Type \| Required \| Description \|
106	\|-----------\|------\|----------\|-------------\|
107	\| `container_protocol_versions` \| `list[ProtocolVersionRecord]` \| Yes \| Protocol versions the agent supports \|
108	\| `image` \| `str` \| Yes \| Full container image path (registry/image:tag) \|
109	\| `cpu` \| `str` \| No \| CPU allocation (e.g., "1", "2") \|
110	\| `memory` \| `str` \| No \| Memory allocation (e.g., "2Gi", "4Gi") \|
111	\| `tools` \| `list[dict]` \| No \| Tools available to the agent \|
112	\| `environment_variables` \| `dict[str, str]` \| No \| Environment variables for the container \|
113
114	## Protocol Versions
115
116	The `container_protocol_versions` parameter specifies which protocols your agent supports:
117
118	```python
119	from azure.ai.projects.models import ProtocolVersionRecord, AgentProtocol
120
121	# RESPONSES protocol - standard agent responses
122	container_protocol_versions=[
123	ProtocolVersionRecord(protocol=AgentProtocol.RESPONSES, version="v1")
124	]
125	```
126
127	Available Protocols:
128	\| Protocol \| Description \|
129	\|----------\|-------------\|
130	\| `AgentProtocol.RESPONSES` \| Standard response protocol for agent interactions \|
131
132	## Resource Allocation
133
134	Specify CPU and memory for your container:
135
136	```python
137	definition=ImageBasedHostedAgentDefinition(
138	container_protocol_versions=[...],
139	image="myregistry.azurecr.io/my-agent:latest",
140	cpu="2", # 2 CPU cores
141	memory="4Gi" # 4 GiB memory
142	)
143	```
144
145	Resource Limits:
146	\| Resource \| Min \| Max \| Default \|
147	\|----------\|-----\|-----\|---------\|
148	\| CPU \| 0.5 \| 4 \| 1 \|
149	\| Memory \| 1Gi \| 8Gi \| 2Gi \|
150
151	## Tools Configuration
152
153	Add tools to your hosted agent:
154
155	### Code Interpreter
156
157	```python
158	tools=[{"type": "code_interpreter"}]
159	```
160
161	### MCP Tools
162
163	```python
164	tools=[
165	{"type": "code_interpreter"},
166	{
167	"type": "mcp",
168	"server_label": "my-mcp-server",
169	"server_url": "https://my-mcp-server.example.com"
170	}
171	]
172	```
173
174	### Multiple Tools
175
176	```python
177	tools=[
178	{"type": "code_interpreter"},
179	{"type": "file_search"},
180	{
181	"type": "mcp",
182	"server_label": "custom-tool",
183	"server_url": "https://custom-tool.example.com"
184	}
185	]
186	```
187
188	### Environment Variables
189
190	Pass configuration to y

People who liked this also viewed

6 picks

Type