azure foundry - creating project and chatting with an agent or model

To use Azure Foundry, first we need to ceate a project. It is important to note the project endpoint after you created it. Next, you will need to deploy a model. 

We also need to install the required packages

pip install azure-ai-projects>=2.0.0


The key environment variable to set are :- 

PROJECT_ENDPOINT=<endpoint copied from welcome screen>

AGENT_NAME="MyAgent"


Chatting with a model

To chat with an Azure Foundry model we can use the following 


from azure.identity import DefaultAzureCredential
from azure.ai.projects import AIProjectClient

# Format: "https://resource_name.ai.azure.com/api/projects/project_name"
PROJECT_ENDPOINT = "your_project_endpoint"

# Create project and openai clients to call Foundry API
project = AIProjectClient(
    endpoint=PROJECT_ENDPOINT,
    credential=DefaultAzureCredential(),
)
openai = project.get_openai_client()

# Run a responses API call
response = openai.responses.create(
    model="gpt-5-mini",
    input="What is the size of France in square miles?",
)
print(f"Response output: {response.output_text}")



Interacting with an agent 

To interact with your agent - think of your agent as a model that you have injected with special capabilities like a funny model or a super critical analyzer

This is the code to create an agent


from azure.identity import DefaultAzureCredential
from azure.ai.projects import AIProjectClient
from azure.ai.projects.models import PromptAgentDefinition

# Format: "https://resource_name.ai.azure.com/api/projects/project_name"
PROJECT_ENDPOINT = "your_project_endpoint"
AGENT_NAME = "your_agent_name"

# Create project client to call Foundry API
project = AIProjectClient(
    endpoint=PROJECT_ENDPOINT,
    credential=DefaultAzureCredential(),
)

# Create an agent with a model and instructions
agent = project.agents.create_version(
    agent_name=AGENT_NAME,
    definition=PromptAgentDefinition(
        model="gpt-5-mini",  # supports all Foundry direct models"
        instructions="You are a helpful assistant that answers general questions",
    ),
)
print(f"Agent created (id: {agent.id}, name: {agent.name}, version: {agent.version})")


And then if you would like to interact with this agent :-

from azure.identity import DefaultAzureCredential
from azure.ai.projects import AIProjectClient

# Format: "https://resource_name.ai.azure.com/api/projects/project_name"
PROJECT_ENDPOINT = "your_project_endpoint"
AGENT_NAME = "your_agent_name"

# Create project and openai clients to call Foundry API
project = AIProjectClient(
    endpoint=PROJECT_ENDPOINT,
    credential=DefaultAzureCredential(),
)
openai = project.get_openai_client()

# Create a conversation for multi-turn chat
conversation = openai.conversations.create()

# Chat with the agent to answer questions
response = openai.responses.create(
    conversation=conversation.id,
    extra_body={"agent_reference": {"name": AGENT_NAME, "type": "agent_reference"}},
    input="What is the size of France in square miles?",
)
print(response.output_text)

# Ask a follow-up question in the same conversation
response = openai.responses.create(
    conversation=conversation.id,
    extra_body={"agent_reference": {"name": AGENT_NAME, "type": "agent_reference"}},
    input="And what is the capital city?",
)
print(response.output_text)




Comments

Post a Comment

Popular posts from this blog

mongosh install properly

To install mongosh property on ubuntu 24.04, we need to wget -qO- https://www.mongodb.org/static/pgp/server-8.0.asc | sudo tee /etc/apt/trusted.gpg.d/server-8.0.asc Then run  echo "deb [ arch=amd64,arm64 ] https://repo.mongodb.org/apt/ubuntu noble/mongodb-org/8.0 multiverse" | sudo tee /etc/apt/sources.list.d/mongodb-org-8.0.list Next we will run  sudo apt-get update And then finally install it using  sudo apt-get install -y mongodb-mongosh To verify if it is running we run  mongosh --version
Read more

gemini cli getting file not defined error

Image
 While trying to run gemini cli on my windows linux subsystem, i bump into this error here - "/Roaming/npm/node_modules/@google/gemini-cli/node_modules/undici/lib/web/webidl/index.js:512 webidl.is.File = webidl.util.MakeTypeAssertion(File)"  "ReferenceError: File is not defined" In Node.js, there’s no built-in File (until very recent Node 20+ with experimental WHATWG APIs). So, unless polyfilled, File is undefined, leading to the ReferenceError. And to resolve this, I had to upgrade to node 22 (might work for node 20) and then I was able to run it.
Read more

vllm : Failed to infer device type

Trying to run vllm without gpu will typicaly lands you into this issue. To resolve this issue: we can use set these both. Setting one does not work for me. So i had to configure both settings below:- 1.  environment variable CUDA_VISIBLE_DEVICES = "" 2. in the command line, change to use device cpu and remove  tensor-parallel-size. For example, python3 -m vllm.entrypoints.openai.api_server --port 8080 --model deepseek-ai/DeepSeek-R1 --device cpu --trust-remote-code --max-model-len 4096" References https://docs.vllm.ai/en/latest/getting_started/troubleshooting.html#failed-to-infer-device-type
Read more