Compose reply draft in Gmail with OpenAI Assistant

Published 7 months ago

Created by

Oskar

Template description

This workflow uses OpenAI Assistant to compose draft replies for labeled email messages. It automatically connects the drafts to Gmail threads.

💡 You can add knowledge base to your OpenAI Assistant and make your reply drafts very customized (e.g. compose response with product information in response to inquiry from customer).

🎬 See this workflow in action in my YouTube video about automating Gmail.

How it works?

The workflow is triggered at regular intervals (default: every 1 minute – you can change this value) to check for messages with a specific label (e.g., "AI").

The content of the retrieved email message is then forwarded to the OpenAI Assistant node, and a reply draft is generated. Next, the response from the Assistant is converted to HTML, and a raw message in RFC standard is composed.

💡 You can learn more about composing drafts with the Gmail API in the official Google documentation.

The raw email message (reply draft) is encoded and attached to the original thread ID. Finally, the trigger label (in this case: "AI") is removed to prevent the workflow from looping.

Set up steps

Set credentials for Gmail and OpenAI.
Add new label in Gmail account for messages that should be handled by the workflow (e.g. name it "AI").
Select this label in the first and last Gmail nodes in workflow.
Create and configure your OpenAI Assistant. Select your assistant in "OpenAI Assistant" node.
Optionally: change trigger interval (by default interval is 1 minute).

If you like this workflow, please subscribe to my YouTube channel and/or my newsletter.

Share Template

More AI workflow templates

AI agent chat

This workflow employs OpenAI's language models and SerpAPI to create a responsive, intelligent conversational agent. It comes equipped with manual chat triggers and memory buffer capabilities to ensure seamless interactions. To use this template, you need to be on n8n version 1.50.0 or later.

n8n Team

Scrape and summarize webpages with AI

This workflow integrates both web scraping and NLP functionalities. It uses HTML parsing to extract links, HTTP requests to fetch essay content, and AI-based summarization using GPT-4o. It's an excellent example of an end-to-end automated task that is not only efficient but also provides real value by summarizing valuable content. Note that to use this template, you need to be on n8n version 1.50.0 or later.

n8n Team

AI agent that can scrape webpages

⚙️🛠️🚀🤖🦾 This template is a PoC of a ReAct AI Agent capable of fetching random pages (not only Wikipedia or Google search results). On the top part there's a manual chat node connected to a LangChain ReAct Agent. The agent has access to a workflow tool for getting page content. The page content extraction starts with converting query parameters into a JSON object. There are 3 pre-defined parameters: url** – an address of the page to fetch method** = full / simplified maxlimit** - maximum length for the final page. For longer pages an error message is returned back to the agent Page content fetching is a multistep process: An HTTP Request mode tries to get the page content. If the page content was successfuly retrieved, a series of post-processing begin: Extract HTML BODY; content Remove all unnecessary tags to recude the page size Further eliminate external URLs and IMG scr values (based on the method query parameter) Remaining HTML is converted to Markdown, thus recuding the page lengh even more while preserving the basic page structure The remaining content is sent back to an Agent if it's not too long (maxlimit = 70000 by default, see CONFIG node). NB: You can isolate the HTTP Request part into a separate workflow. Check the Workflow Tool description, it guides the agent to provide a query string with several parameters instead of a JSON object. Please reach out to Eduard is you need further assistance with you n8n workflows and automations! Note that to use this template, you need to be on n8n version 1.19.4 or later.

Eduard

Implement complex processes faster with n8n

Get started