Google Gemini
Google Gemini enables you to use multimodal AI models to generate, analyze, and process text, images, and documents within workflows.
Actions
- Analyze Document: Extracts insights and information from documents.
- Analyze Image: Interprets and analyzes visual content from images.
- Analyze Text: Processes and derives insights from input text.
- Categorize Text: Classifies text into predefined categories.
- Custom Action: Executes user-defined operations with Gemini models.
- Draft Email: Generates email content based on input prompts.
- Generate Content: Creates text or multimodal content from prompts.
- Generate Text Embedding: Converts text into embeddings for similarity and search.
- Parse Text: Structures and extracts key elements from raw text.
- Send Messages to Gemini Models: Interacts with Gemini models in a conversational format.
- Translate Text: Translates text between languages.