baoyu-danger-gemini-web

To generate text and images via the Gemini Web API, you provide a prompt input from a file or stdin to a CLI, which processes the request and returns the generated content. It supports multi-turn conversations and vision inputs.

Yes, you can supply optional reference images for vision input. The API processes these images alongside your prompt to generate text or images, enabling vision-enabled prompts within multi-turn conversations.

You maintain context in multi-turn conversations using session support. The CLI allows you to manage sessions, passing prompts sequentially to keep the conversation history intact for text and image generation.

The best way to handle API response errors is through the robust error handling implemented in the CLI. It catches API response failures during text and image generation, preventing workflow crashes.

Yes, you need the baoyu-chrome-cdp dependency. This prerequisite tool is required to interface with the Gemini Web API, enabling the CLI to execute text and image generation commands successfully.