Google Gemini AI Model Configuration in ConvyAI
Overview
The Google Gemini integration connects ConvyAI to Google's multimodal foundation models for intent classification, entity extraction, and response generation within the bot flow.
Prerequisites
- A Google Gemini API key.
- API key configured in Generative AI Settings.
Create a Gemini AI Model
Navigate to Generative AI → AI Models and click New Model → Gemini.
Configuration options
| Field | Description |
|---|---|
| Name | A unique name to identify this AI Model. |
| API Key | Your Google Gemini API key. |
ConvyAI supports any Gemini model accessible via the Google AI API. The model is specified by name in the Completion model advanced parameter (e.g., gemini-2.5-flash, gemini-2.5-pro, gemini-2.0-flash). Refer to the Google AI model documentation for the full list of available models and their identifiers.
Advanced parameters
| Parameter | Default | Description |
|---|---|---|
| Prompt version | v3 | System prompt version applied when using the model in Knowledge Base nodes. |
| Completion model | gemini-2.5-flash | The Gemini model used for response generation. Enter the model identifier as provided by Google. |
| Embedding model | gemini-embedding-001 | The model used for embedding during Knowledge Base indexing and retrieval. |
| Thinking budget | 0 | Number of thinking tokens the model can use to reason before generating a response. Set to 0 to disable extended thinking. |
| Max token completion | 1000 | Maximum number of tokens in the generated response. |
| Temperature | 0.7 | Controls response creativity. Lower values produce more deterministic outputs. |
| Top P | 1 | Nucleus sampling parameter. Limits token selection to the top probability mass. |
| Frequency penalty | 0.0 | Reduces repetition of tokens that have already appeared in the output. |
| Presence penalty | 0.0 | Encourages the model to introduce new topics by penalizing tokens that have already appeared. |
| Number of extracted chunks | 3 | How many Knowledge Base chunks are retrieved and passed to the model as context during RAG. |
Intents, entities, and testing
Configuring intents and entities and testing the model are features shared across all AI Model providers. See Intents, Entities & Testing for full documentation.