DB

Store CerebrasOpenAI agent sessions in Postgres with history added to context.

This example uses a Cerebras model ID that has been retired. Replace the retired ID with gpt-oss-120b before running. Review the Cerebras migration notes when the example uses reasoning, tools, or structured output.

db.py

"""Run `uv pip install ddgs sqlalchemy cerebras_cloud_sdk` to install dependencies."""

from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.models.cerebras import CerebrasOpenAI
from agno.tools.websearch import WebSearchTools

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------

# Setup the database
db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"
db = PostgresDb(db_url=db_url)

agent = Agent(
    model=CerebrasOpenAI(id="llama-4-scout-17b-16e-instruct"),
    db=db,
    tools=[WebSearchTools()],
    add_history_to_context=True,
)
agent.print_response("How many people live in Canada?")
agent.print_response("What is their national anthem called?")

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    pass

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]" cerebras-cloud-sdk ddgs openai sqlalchemy
   
3. Export your Cerebras OpenAI-compatible API key

   Mac/Linux

   export CEREBRAS_API_KEY="your_cerebras_api_key_here"
   

   $Env:CEREBRAS_API_KEY="your_cerebras_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. Use a current Cerebras model

   Replace llama-4-scout-17b-16e-instruct with gpt-oss-120b in the saved Python file before running.

6. Run the example

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

   python db.py
   

Full source: cookbook/90_models/cerebras_openai/db.py