# Telegram chatbot answering from Google Docs via semantic search
This automation enables instant, accurate responses to user queries by leveraging content from a Google Docs file through semantic search and AI. The system uses Retrieval-Augmented Generation (RAG) with vector embeddings to retrieve context and generate natural-language answers. Ideal for support, training, and knowledge delivery teams.
## Who it´s for
- Training specialists building document-based chatbots
- Support teams using automated knowledge-base responses
- Telegram bot owners needing information retrieval features
- Developers implementing RAG systems without heavy coding
## What the automation does
- Fetches text content from a specified Google Docs file
- Splits content into chunks and generates vector embeddings via Together API
- Stores embeddings in Supabase for semantic search
- On receiving a Telegram message, embeds the query and finds semantically closest chunks
- Aggregates top-matching context and sends it to Qwen LLM via OpenRouter
- Returns the generated answer to the user in the chat
- Supports HTTP webhooks as an alternative trigger
## What´s included
- Ready-to-use n8n workflow
- Trigger logic: incoming chat message or HTTP request
- Integrations with Google Docs, Telegram, Supabase, Together AI, and OpenRouter
- Basic textual instructions for launch and adaptation
## Requirements for setup
- n8n account (cloud or self-hosted)
- Access to a Google Docs file with read permissions
- Telegram bot token
- Supabase project with vector storage enabled
- API keys from Together AI and OpenRouter
- Basic understanding of nodes and environment variables
## Benefits and outcomes
- Faster response handling without human involvement
- Reduced load on support and HR teams
- 24/7 availability of institutional knowledge
- Scalable employee or customer training
- Answers strictly based on source document — minimized hallucinations
- No data duplication — always up-to-date source
## Important: template only
Important: you are purchasing a ready-made automation workflow template only. Rollout into your infrastructure, connecting specific accounts and services, 1:1 setup help, custom adjustments for non-standard stacks and any consulting support are provided as a separate paid service at an individual rate. To discuss custom work or 1:1 help, contact via chat
Telegram chatbot
document-based Q A
semantic search in documents
RAG chatbot
Google Docs integration
vector embeddings storage
Supabase vector database
n8n workflow automation
LangChain with RAG
AI-powered support bot
knowledge retrieval from docs
customer support automation
employee training bot
OpenRouter LLM
Together API embeddings
contextual answer generation
No feedback yet