Integrations
This rantir workflow showcases the use of Multimodal LLMs for parsing and extracting information from PDF documents within rantir.
In this scenario, we’re reviewing a candidate’s CV/resume through an AI that filters out unqualified applications. However, the candidate has included a hidden prompt intended to bypass our filter! By leveraging AI Vision, we can effectively address this issue. Read on to learn how!
How it works
- The candidate’s CV/resume, in PDF format, is downloaded from Google Drive for demonstration purposes.
- The PDF is converted to a PNG image using Stirling PDF. Since the hidden prompt is in white font, it remains invisible in the converted image.
- The image is processed by a Basic LLM node using a multimodal model, such as Google’s Gemini 1.5 Pro.
- Within the Basic LLM node, a "User Message" with Binary type is configured, allowing us to send the image file directly in the request.
- The LLM now successfully ignores the hidden prompt, yielding the expected response.
Requirements
- Google Gemini API Key. Alternatively, GPT-4 can also handle this use case.
- Stirling PDF or another service for converting PDFs to images. For privacy, consider self-hosting Stirling PDF to avoid using public APIs.
Customizing the workflow
- Replace the manual trigger with a webhook or other trigger to integrate into your existing services.
- This example validates qualifications; you can expand it to extract data points like years of experience, previous employers, etc.
Other Workflows like this one
Your connected stack awaits to automate AI workflows with 24-7 uptime performance and engagement
Summarize Google Sheets with OpenAI's GPT-4
Google Sheets
Gmail
OpenAI
Markdown
Sticky Note
AI Customer feedback analysis
Google Sheets
OpenAI
Merge
Sticky Note
Rantir Form Trigger
AI: Summarize podcast episode and enhance using Wikipedia
Gmail
Item Lists
Code
AI Agent
Summarization Chain
Voice Activated Multi-Agent Demo for Vagent.io using Notion and Google Calendar
AI Agent
OpenAI Chat Model
Window Buffer Memory (easiest)
Call rantir Workflow Tool
HTTP Request Tool
AI chatbot that can search the web
AI Agent
OpenAI Chat Model
Window Buffer Memory (easiest)
SerpApi (Google Search)
Wikipedia
Discord AI-powered bot
Discord
OpenAI
No Operation, do nothing
Edit Fields (Set)
Webhook
Compare features across plans
Computir Cloud Suite All Access
$99/m
Per team/per month, with 10 GB of data and storage
Everything in Free, and:
Host up to around 4-5 Applications
Advanced user roles
Unlimited AI applications & workflows
Custom onboarding & Customer management
Advanced integrations
International capabilities
Unlimited Team Plan & Custom Integration
$299/m
Per $1K Tokens or 1 TB added, custom integration (per month)
Everything in Professional, and:
Host up to around 20+ Applications
Tailored implementation services
Advanced ERP integration capabilities
Extra bandwidth and open-source AI models
Fine-tuning & data logic
SOX or integration customization
Dedicated premium support
Computir Cloud
AI Application & Automation platform suite
Get access to generate dashboards, websites or content
Chat to Explore Data
Custom Develop integrations
Chat to Transform Data
Direct or Enterprise application connections
Webflow, Wix or Wordpress
+ Acumatica, Microsoft, Netsuite & Sage
+ Oracle & Workday
Rules to automate AI
Basic
Advanced
Advanced
Custom Integrations
Build & Share Live Reports
Generated
Human-Led
Train Classification Models
Human-Led
Train Time Series Forecasts
"I highly recommend Computir, they are a great dev team with quick turn around on all projects and requests. We recently worked with them on updating our website and any changes, updates or modifications I needed were always taken care of quickly!"
Paige J, VP of Marketing, Heavy AI