
Security News
Follow-up and Clarification on Recent Malicious Ruby Gems Campaign
A clarification on our recent research investigating 60 malicious Ruby gems.
Welcome to react_ai
a gemified version of my attempt to recreate the ReAct pattern in Ruby with added features.
The ReAct pattern is a technique used to circumvent the limitation LLMs have of only being able to respond past the date they were trained. We do this by prompting our LLM to use tools that we can define for it. Another advantage of using tools is that we can reduce hallucinations and therefore improve accuracy of LLM responses.
Install the gem and add to the application's Gemfile by executing:
$ bundle add react_ai
If bundler is not being used to manage dependencies, install the gem by executing:
$ gem install react_ai
Create a .env
file in the root directory and add your open-ai key and your're ready to go!🔥
OPEN_AI_KEY='your open ai key'
You can use this gem via the commmand line after it is installed by typing:
./exe/react_ai "Some prompt for our LLM!"
Here's an example of what a user prompt and subsequent response might look like:
https://github.com/thedayisntgray/react_ai/assets/4859128/bbc6cba8-914b-4d6a-9a45-77e819acaec2
Bug reports and pull requests are welcome on GitHub at https://github.com/thedayisntgray/react_ai.
FAQs
Unknown package
We found that react_ai demonstrated a not healthy version release cadence and project activity because the last version was released a year ago. It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Security News
A clarification on our recent research investigating 60 malicious Ruby gems.
Security News
ESLint now supports parallel linting with a new --concurrency flag, delivering major speed gains and closing a 10-year-old feature request.
Research
/Security News
A malicious Go module posing as an SSH brute forcer exfiltrates stolen credentials to a Telegram bot controlled by a Russian-speaking threat actor.