The Google Gemini Plugin for Hexabot Chatbot / Agent Builder to enable the LLM RAG Capability

Google Gemini Plugin for Hexabot Chatbot Builder

The Gemini Plugin allows you to integrate Google Generative AI into your Hexabot chatbot workflows, enabling the creation of generative AI blocks. This plugin provides settings for customizing responses, including controlling the maximum length of the generated content and using recent conversation messages as context for generating more relevant replies.

Hexabot is an open-source chatbot / agent solution that allows users to create and manage AI-powered, multi-channel, and multilingual chatbots with ease. If you would like to learn more, please visit the official github repo.

Prerequisites

Before setting up the Gemini Plugin, you will need to generate an API token from Google’s Generative AI platform.

1. Go to the Google Generative AI API page.
2. Select "Develop in your own environment" to generate your API token.
3. Once you have your API token, you can proceed to configure the global gemini settings within Hexabot (Settings > Gemini).

Installation

Run the following command which will download and install the Gemini plugin:

cd ~/projects/my-chatbot
npm install hexabot-plugin-gemini
hexabot dev

Configuration

The Gemini Plugin provides several customizable settings that can be configured through the Hexabot admin interface. The following settings are available:

• Model: The model to be used for generating responses (e.g., gemini-1.5-flash).
• Temperature: The temperature controls the degree of randomness in token selection. Lower temperatures are good for prompts that require a more deterministic response, while higher temperatures can lead to more diverse or creative results. A temperature of 0 is deterministic, meaning that the highest probability response is always selected (default: 0.8).
• Candidate Count: Specifies the number of generated responses to return. Curr