AI Assistant for Structured Metadata Generation
detail.loadingPreview
Automates the generation of structured metadata in English and Chinese using AI, leveraging communication platforms and various data sources.
About This Workflow
This n8n workflow orchestrates an AI-powered assistant to process incoming requests (text or voice) via Telegram and generate structured metadata. It can interact with Google Calendar, Gmail, and Baserow databases to gather information, process it using AI models, and output the results in both English and Chinese. The workflow aims to create comprehensive and localized metadata for various applications.
Key Features
- Multi-language Metadata Generation: Produces structured metadata in both English (en) and Chinese (zh).
- AI-Powered Processing: Utilizes OpenAI models for intelligent understanding, summarization, and generation.
- Communication Integration: Seamlessly integrates with Telegram for receiving user requests (text and voice).
- Data Source Integration: Connects to Google Calendar and Gmail for fetching relevant event and email data.
- Task Management Integration: Integrates with Baserow for accessing and managing tasks and contacts.
- Voice-to-Text Transcription: Transcribes voice messages into text for AI processing.
- Conditional Logic: Employs 'If' nodes to handle different types of incoming messages (text vs. voice).
- Memory Management: Utilizes 'Window Buffer Memory' for conversational context.
- Structured Output: Aims to output metadata in a structured, machine-readable format.
How To Use
- Trigger: The workflow starts with a 'Listen for incoming events' Telegram trigger.
- Message Handling: The 'Voice or Text' node determines if the incoming message is text or voice.
- Voice Processing: If it's a voice message, 'Get Voice File' downloads the audio, and 'Speech to Text' transcribes it.
- AI Assistant: The 'Angie, AI Assistant' node processes the transcribed text (or original text message) using the 'OpenAI Chat Model' and its system message, which includes instructions for data fetching and summarization, and potentially uses 'Window Buffer Memory' for context.
- Tool Integration: The AI assistant can utilize tools like 'Google Calendar', 'Get Email', 'Tasks' (BaserowTool), and 'Contacts' (BaserowTool) to gather information based on the user's request.
- Output Generation: The AI assistant generates a response, which is then sent back to the user via the 'Telegram' node.
- Conditional Logic for Text: An 'If' node is present, though its direct connection to handling text input needs further inspection to determine its exact role in differentiating message types.
Apps Used
Workflow JSON
{
"id": "6cf8d303-d34a-4d3d-a9cb-0ae127a9bf7c",
"name": "AI Assistant for Structured Metadata Generation",
"nodes": 8,
"category": "AI & Machine Learning",
"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: 6cf8d303-d34a...
About the Author
SaaS_Connector
Integration Guru
Connecting CRM, Notion, and Slack to automate your life.
Statistics
Related Workflows
Discover more workflows you might like
Visa Requirement Checker
A workflow to check visa requirements based on user input, leveraging Langchain, Cohere embeddings, Weaviate vector store, and Anthropic LLM.
OpenAI Text-to-Speech Workflow
Generate audio from text using OpenAI's TTS API.
Telegram OCR Bot with Mistral AI
Automated OCR for image and PDF files sent via Telegram, powered by Mistral AI.