Multimodal inputs

from typing import Literal

from agno.agent import Agent
from agno.media import Image
from agno.models.google import Gemini
from pydantic import BaseModel, Field


class Classification(BaseModel):
    label: Literal["wildlife", "landscape", "sports", "architecture", "other"] = Field(
        ..., description="The primary scene type of the image"
    )


agent = Agent(
    model=Gemini(id="gemini-3.5-flash"),
    instructions="You classify images by scene type.",
    output_schema=Classification,
)

url = "https://storage.googleapis.com/generativeai-downloads/images/generated_elephants_giraffes_zebras_sunset.jpg"
result = agent.run("Classify this image.", images=[Image(url=url)]).content
# Classification(label='wildlife')

import httpx

from agno.agent import Agent
from agno.media import Audio
from agno.models.google import Gemini
from pydantic import BaseModel, Field


class Transcript(BaseModel):
    text: str = Field(..., description="Verbatim transcript of all spoken audio")


transcription_agent = Agent(
    model=Gemini(id="gemini-3.5-flash"),
    instructions="Transcribe all spoken audio. Return only the transcript.",
    output_schema=Transcript,
)

url = "https://agno-public.s3.us-east-1.amazonaws.com/demo_data/QA-01.mp3"
response = httpx.get(url, timeout=30.0)
response.raise_for_status()

result = transcription_agent.run(
    "Transcribe this audio.",
    audio=[Audio(content=response.content)],
).content
# Transcript(text='...')

from pydantic import BaseModel, Field


class BoundingBox(BaseModel):
    label: str = Field(..., description="What the box contains")
    x: float = Field(..., ge=0.0, le=1.0, description="Top-left x in [0, 1]")
    y: float = Field(..., ge=0.0, le=1.0, description="Top-left y in [0, 1]")
    width: float = Field(..., ge=0.0, le=1.0, description="Width in [0, 1]")
    height: float = Field(..., ge=0.0, le=1.0, description="Height in [0, 1]")