> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agno.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Video Input (File Upload)

> Upload a video to Gemini's Files API, poll until it's ready, and pass it to an agent.

## Code

```python video_input_file_upload.py theme={null}
import time
from pathlib import Path

from agno.agent import Agent
from agno.media import Video
from agno.models.google import Gemini
from agno.utils.log import logger
from google.genai.types import UploadFileConfig

model = Gemini(id="gemini-3.5-flash")
agent = Agent(
    model=model,
    markdown=True,
)

# Please download a sample video file to test this Agent
# Run: `wget https://storage.googleapis.com/generativeai-downloads/images/GreatRedSpot.mp4` to download a sample video
video_path = Path(__file__).parent.joinpath("GreatRedSpot.mp4")
video_file = None
remote_file_name = f"files/{video_path.stem.lower().replace('_', '')}"
try:
    video_file = model.get_client().files.get(name=remote_file_name)
except Exception as e:
    logger.info(f"Error getting file {video_path.stem}: {e}")
    pass

# Upload the video file if it doesn't exist
if not video_file:
    try:
        logger.info(f"Uploading video: {video_path}")
        video_file = model.get_client().files.upload(
            file=video_path,
            config=UploadFileConfig(name=video_path.stem, display_name=video_path.stem),
        )

        # Check whether the file is ready to be used.
        while video_file and video_file.state and video_file.state.name == "PROCESSING":
            time.sleep(2)
            if video_file and video_file.name:
                video_file = model.get_client().files.get(name=video_file.name)
            else:
                video_file = None

        logger.info(f"Uploaded video: {video_file}")
    except Exception as e:
        logger.error(f"Error uploading video: {e}")

if __name__ == "__main__":
    agent.print_response(
        "Tell me about this video",
        videos=[Video(content=video_file)],
        stream=True,
    )
```

## Usage

<Steps>
  <Snippet file="create-venv-step.mdx" />

  <Step title="Set your API key">
    ```bash theme={null}
    export GOOGLE_API_KEY=xxx
    ```
  </Step>

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U google-genai agno
    ```
  </Step>

  <Step title="Run Agent">
    Save the code above as `video_input_file_upload.py`, then run:

    ```bash theme={null}
    python video_input_file_upload.py
    ```
  </Step>
</Steps>
