OpenAI Chat Responses

Alternate one agent between OpenAIChat and OpenAIResponses mid-session over shared Postgres history.

openai_chat_responses.py

import os

from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.models.openai import OpenAIChat, OpenAIResponses


def get_weather(city: str) -> str:
    """Get the current weather for a city."""
    return f"The weather in {city} is sunny and 22C."


def main() -> None:
    db_url = os.getenv(
        "AGNO_POSTGRES_URL",
        "postgresql+psycopg://ai:ai@localhost:5532/ai",
    )
    db = PostgresDb(db_url)

    agent = Agent(
        model=OpenAIChat(id="gpt-4o"),
        db=db,
        add_history_to_context=True,
        num_history_runs=10,
        tools=[get_weather],
        debug_mode=True,
    )

    # Turn 1 — OpenAI with tool call (works fine)
    agent.print_response("What is the weather in Paris?")

    # Turn 2 — OpenAI Responses with tool call
    agent.model = OpenAIResponses()
    agent.print_response("What is the weather in London?")

    # Turn 3 — OpenAI with tool call (works fine on its own)
    agent.model = OpenAIChat(id="gpt-4o")
    agent.print_response("What is the weather in Tokyo?")

    # Turn 4 — OpenAI Responses summary
    agent.model = OpenAIResponses()
    agent.print_response("Summarize all the weather we checked.")


if __name__ == "__main__":
    main()

Run the Example

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   

   uv venv --python 3.12
   .venv\Scripts\activate
   
2. Install dependencies

   uv pip install -U agno "psycopg[binary]" openai sqlalchemy
   
3. Export your OpenAI API key

   Mac/Linux

   export OPENAI_API_KEY="your_openai_api_key_here"
   

   $Env:OPENAI_API_KEY="your_openai_api_key_here"
   
4. Run PgVector

   macOS / Linux

   docker run -d \
     -e POSTGRES_DB=ai \
     -e POSTGRES_USER=ai \
     -e POSTGRES_PASSWORD=ai \
     -e PGDATA=/var/lib/postgresql \
     -v pgvolume:/var/lib/postgresql \
     -p 5532:5432 \
     --name pgvector \
     agnohq/pgvector:18
   

   docker run -d `
     -e POSTGRES_DB=ai `
     -e POSTGRES_USER=ai `
     -e POSTGRES_PASSWORD=ai `
     -e PGDATA=/var/lib/postgresql `
     -v pgvolume:/var/lib/postgresql `
     -p 5532:5432 `
     --name pgvector `
     agnohq/pgvector:18
   
5. Run the example

   Save the code above as openai_chat_responses.py, then run:

   python openai_chat_responses.py
   

Full source: cookbook/02_agents/14_advanced/interchange_model/openai_chat_responses.py