Skip to main content

​
Overview

The integration of Google Gemini with Convertalk brings cutting-edge generative AI capabilities to your chatbot experience. Gemini, Google’s state-of-the-art multimodal LLM (Large Language Model), enables natural, context-aware, and multi-turn conversations that go beyond standard automation. This guide outlines the step-by-step process to integrate Google Gemini with Convertalk.

​
Prerequisites

Before you begin, ensure the following:
  • You have admin-level access to your Convertalk account.
  • A valid Google Cloud Project with the Gemini API enabled.
  • Access to Gemini API credentials (API key or OAuth token).
  • Access to Convertalk’s LLM Integration settings.

​
Steps to Integration

​
Step 1: Enable Gemini API on Google Cloud

  1. Visit Google Cloud Console.
  2. Select or create a new project.
  3. Go to APIs & Services > Library.
  4. Search for Gemini API (or Vertex AI API) and click Enable.

​
Step 2: Generate API Credentials

  1. Go to APIs & Services > Credentials.
  2. Click “Create Credentials” → choose API Key.
  3. Copy the API key and keep it secure.
🔐 Tip: For production-level integrations, use service accounts and OAuth for enhanced security.

​
Step 3: Add Gemini in Convertalk

  1. Log in to your Convertalk dashboard.
  2. Select the “Third-Party Apps Integrations”
  3. Search for “Google Gemini”
  4. Click on Connect, and enter the API key.
Congratulations! You have successfully integrated Convertalk with Google Gemini!

​
FAQ’s

Convertalk currently supports:
  • Gemini-Pro
  • Gemini-2.0-Flash
  • Gemini-2.0-Flash-Lite
These models offer a trade-off between response quality and speed, allowing you to pick what’s best for your use case.
You can generate your Gemini API key from the Google Cloud Console:
  • Go to APIs & Services > Credentials
  • Click “Create Credentials” > API Key
  • Ensure that the Gemini (Vertex AI) API is enabled in the selected project.
No, one bot can only be Intgrated to one LLM model at a time.
If the key becomes invalid or quota limits are hit:
  • The bot will fall back to a default message.
  • An error notification will appear in the integration logs under Settings > LLM Integration.
  • You will receive a platform alert to take corrective action.
⌘I