The Telex AI Chatbot Integration brings intelligent, real-time responses to your Telex channels. It empowers your team with an AI-driven assistant that answers questions using a robust knowledge base of preloaded company documents and FAQsβall directly within Telex.
- Users can type questions into a Telex channel and receive immediate, relevant answers generated by an AI service.
- Designed specifically for Telex, the integration ensures smooth communication without leaving your chat environment.
- Upload and manage documents through a dedicated endpoint. The system indexes these documents to provide accurate and context-rich answers.
- Utilize free-tier AI services (e.g., Hugging Face, Cohere, or trial credits from OpenAI) to power your chatbot without heavy expenses.
-
User Interaction
- A team member posts a question in a Telex channel.
-
Payload Processing
- The integration captures the query along with metadata (user and channel details).
-
AI Query
- The question, plus any additional context, is sent to an AI service that leverages your preloaded documents to generate a response.
-
Response Delivery
- The AIβs answer is relayed back to the Telex channel, alongside the original question.
-
Document Updates
- A separate endpoint lets you upload documents to keep the knowledge base current and comprehensive.
- Backend: Golang with Gin framework
- AI Service: Gemini AI for document-based responses
- Database: Gemini AI serving as both the LLM and storage solution
- Deployment: Designed to run on cloud platforms with easy API integration
- Clone the repository:
git clone https://github.com/telexintegrations/customer-service-ai-chatbot.git cd customer-service-ai-chatbot
- Install dependencies:
go mod tidy
- Set up environment variables:
export GEMINI_API_KEY="your_api_key" export TELEX_WEBHOOK="your_telex_webhook" export FILE_PATH="your_document_path"
- Run the application:
go run main.go
GET /integration
POST /target
Request:
{
"message": "What are the company policies on remote work?",
"settings": [
{
"label": "Api Key",
"type": "text",
"required": true,
"default": ""
}
]
}
- Fork the repository
- Create a feature branch (
git checkout -b feature-name
) - Commit your changes (
git commit -m "Added new feature"
) - Push to the branch (
git push origin feature-name
) - Create a Pull Request
This project is licensed under the MIT License.