deadbits / vigil-llm

⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs
https://vigil.deadbits.ai/
Apache License 2.0
303 stars 35 forks source link

Improved cache #6

Open deadbits opened 1 year ago

deadbits commented 1 year ago

There's a basic LRU cache implemented in the API server to return completed analysis if a prompt is submitted twice. This should be replaced with something more robust like Redis or similar.