Confluence Page AI Powered Chatbot
detail.loadingPreview
Leverages AI to answer questions based on Confluence page content.
About This Workflow
This workflow creates an AI-powered chatbot that can answer user questions by querying Confluence pages. It retrieves content from specified Confluence pages using the Confluence REST API, converts HTML content to Markdown, and then uses an AI model (gpt-4o-mini) to answer user queries based on the provided context. The chatbot maintains conversation history using window buffer memory and can send responses via Telegram.
Key Features
- Fetches content from Confluence pages using their IDs.
- Converts HTML page content to Markdown for better AI processing.
- Utilizes an AI model (gpt-4o-mini) for natural language understanding and response generation.
- Implements conversational memory to maintain context across messages.
- Supports searching for pages by ID and extracting relevant metadata.
- Can output responses via Telegram.
How To Use
- Set up Confluence API Credentials: Ensure you have a Confluence API token and your instance details configured in the
Confluence APIcredential. - Configure Global Page IDs: In the
Globalsnode, set thepage_id_tekla,page_id_n8n,page_id_more_n8n, andpage_id_tekla_clash_checkingto the actual IDs of the Confluence pages you want to use as the knowledge base. - Configure OpenAI API Credentials: Ensure your OpenAI API key is set up in the
OpenAi accountcredential. - Configure Telegram API Credentials: Set up your Telegram bot token and chat ID in the
Telegram accountcredential and environment variables respectively. - Trigger the Workflow: The workflow is triggered by a chat message received via the
When chat message receivednode. You'll need to configure this node to receive messages (e.g., via a webhook). - AI Processing: The
Search By IDnode fetches page information.Page Schemaextracts relevant details.Confluence Page Storage Viewfetches the page content in storage format.HTML to Markdownconverts this content. TheAI Agentnode then uses this context to answer the user's question.gpt-4o-miniandWindow Buffer Memoryhandle the AI model and conversation history. - Response: The final answer is formatted by
Chat Responseand sent via Telegram by theSend Telegram Messagenode.
Apps Used
Workflow JSON
{
"id": "55f9496e-3f1c-457f-9926-330f54470a54",
"name": "Confluence Page AI Powered Chatbot",
"nodes": 9,
"category": "AI",
"status": "active",
"version": "1.0.0"
}Note: This is a sample preview. The full workflow JSON contains node configurations, credentials placeholders, and execution logic.
Get This Workflow
ID: 55f9496e-3f1c...
About the Author
Crypto_Watcher
Web3 Developer
Automated trading bots and blockchain monitoring workflows.
Statistics
Related Workflows
Discover more workflows you might like
DeepSeek AI Agent with Telegram and Long-Term Memory
A Telegram bot powered by DeepSeek AI that leverages long-term memory for personalized conversations and information storage.
AI-Powered Slack Bot for Automation Support
A workflow that receives messages via Slack webhook, processes them using an AI agent (Google Gemini) with conversational memory, and sends a response back to Slack.
OpenAI Assistant with Custom Fictional Country Tools
This workflow leverages an OpenAI Assistant to interact with custom tools for retrieving fictional country capitals and the current date.