This node uses Google's Gemini AI to generate text from prompts that can include both text and images, supporting multimodal input and customizable output schemas.
Report this node
Select the reason for reporting
Describe the issue in detail
Prompt
Image
schema
Model
Extract image from video (file_path)
Extracts a single image from a video at the specified timestamp.
Extract image from video
Extracts a single image from a video at the specified timestamp.
Gemini AI Text Generator
A keyless node that sends instructions and a prompt to an Gemini LLM model and returns the generated text.
By BuildShipMultimodal
A keyless node to use Google's Gemini AI to generate text from text-only or text-and-image input. [Full documentation](https://cloud.google.com/vertex-ai/docs/generative-ai/start/quickstarts/quickstart-multimodal).
By BuildShipGemini AI JSON Generator
A keyless node that sends instructions and a prompt to an Gemini LLM model and returns the generated text.
By BuildShipGemini AI Chat
A keyless node that sends instructions and a prompt to an Gemini LLM model with optional memory capabilities with selectable context window for multi-turn conversations.
By BuildShip