Load Workflow from Database

Fetch a stored workflow from PostgresDb with get_workflow_by_id and run it, with get_workflows shown for listing all.

Demonstrates loading a workflow from the database by ID and running it.

get_workflow.py

"""
Load Workflow from Database
===========================

Demonstrates loading a workflow from the database by ID and running it.
"""

from agno.db.postgres import PostgresDb
from agno.workflow.workflow import get_workflow_by_id, get_workflows  # noqa: F401

# ---------------------------------------------------------------------------
# Create Database Client
# ---------------------------------------------------------------------------
db = PostgresDb(db_url="postgresql+psycopg://ai:ai@localhost:5532/ai")

# ---------------------------------------------------------------------------
# Run Workflow Load Example
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    workflow = get_workflow_by_id(db=db, id="content-creation-workflow")

    if workflow:
        workflow.print_response(input="AI trends in 2024", markdown=True)
    else:
        print("Workflow not found")

    # You can also get all workflows from the database
    # workflows = get_workflows(db=db)
    # for workflow in workflows:
    #     print(workflow)

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]" fastapi openai sqlalchemy
   
3. Export your API keys

   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. Clone Agno

   Clone the repository and run the remaining commands from its root:

   git clone https://github.com/agno-agi/agno.git
   cd agno
   
6. Save the workflow

   Persist the content-creation-workflow record before loading it:

   python cookbook/93_components/save_workflow.py
   
7. Run the example

   Run the example from the repository root:

   python cookbook/93_components/get_workflow.py
   

Full source: cookbook/93_components/get_workflow.py