An example of how to use Pydantic AI with Llama Stack and the Responses API

pydantic_agent_test.py

# Dependencies:
#  pip install openai pydantic-ai

# This example uses the web_search builtin tool, so it assumes you
# have a valid TAVILY_API_KEY environment variable set before starting
# your Llama Stack server.

# Usage:
#
#  ollama run llama3.2:3b
#
#  ENABLE_OLLAMA="ollama" OLLAMA_INFERENCE_MODEL="llama3.2:3b" uv run llama stack run llama_stack/templates/starter/run.yaml
#
# python pydantic_agent_test.py

from openai import AsyncOpenAI
from openai.types.responses import WebSearchToolParam 
from pydantic import BaseModel
from pydantic_ai import Agent
from pydantic_ai.models.openai import OpenAIResponsesModel, OpenAIResponsesModelSettings
from pydantic_ai.providers.openai import OpenAIProvider


client = AsyncOpenAI(
    base_url="http://localhost:8321/v1/openai/v1",
    api_key="fake",
)
model_settings = OpenAIResponsesModelSettings(
    openai_builtin_tools=[WebSearchToolParam(type="web_search_preview")],
)
model = OpenAIResponsesModel(
    "ollama/llama3.2:3b",
    provider=OpenAIProvider(openai_client=client),
)
agent = Agent(model, model_settings=model_settings)

result = agent.run_sync('What is the weather in Tokyo?')
print(result.output)
#> The current weather in Tokyo is sunny with a temperature of 32.2°C (90°F). The wind is blowing at 3.6 mph from the southwest, and the pressure is 1013.0 mb. There is no precipitation expected, but the humidity is relatively high at 63%.