You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
swarms/multi_modal_auto_agent.py

21 lines
459 B

from swarms.structs import Agent
from swarms.models.gpt4_vision_api import GPT4VisionAPI
from swarms.prompts.multi_modal_autonomous_instruction_prompt import (
MULTI_MODAL_AUTO_AGENT_SYSTEM_PROMPT_1,
)
llm = GPT4VisionAPI()
task = "What is the color of the object?"
img = "images/swarms.jpeg"
## Initialize the workflow
agent = Agent(
llm=llm,
max_loops="auto",
sop=MULTI_MODAL_AUTO_AGENT_SYSTEM_PROMPT_1,
)
agent.run(task=task, img=img)