With this workflow, you can extract data from resume documents uploaded via a Telegram bot. The workflow transforms the readable content of a PDF resume into structured data using AI nodes, and returns the PDF with formatted plain HTML.
You can modify this workflow to perform other actions with structured data (e.g., inserting it into a database or creating other well-formatted documents).
The functionality of this workflow was presented during the rantir community call on March 7, 2024. A recording of the presentation is available here.
Workflow made for demo purposes. If you want to use it in real life, please ensure necessary measures for personal data protection are set.
How it works?
The user uploads a readable PDF resume document into the Telegram bot. After authentication based on the chat ID parameter, the workflow extracts text from the PDF and transfers it into an AI chain with connected sub-nodes: OpenAI Chat Model and Structured Output (JSON) Parser.
Next, each extracted section (e.g., employment history, projects, etc.) is formatted into the desired HTML structure. Finally, the document is converted into a new, structured PDF using Gotenberg.
Set up steps
- Create a Telegram bot and add its credentials in rantir.
- Set your chat ID parameter in Auth node.
- Adjust the JSON schema in Structured Output Parser according to your needs.
- Optionally, replace the HTTP call to Gotenberg with a PDF generation service of your choice.
Other Workflows like this one
Your connected stack awaits to automate AI workflows with 24-7 uptime performance and engagement