vigil-llm
vigil-llm copied to clipboard
Create example detection workflows
Now that Vigil can be imported as a library, it is a lot easier to call the different scanners and interact with canary tokens. This allows users to define custom detection workflows in Python.
I want to create a few cookbooks that demonstrate different possibilities here.
For example: *Canary token workflow
- Add canary token to system prompt template
- Receive user input to prompt and combine with canary prompt
- Send canary prompt to LLM and receive response
- Check LLM response for canary token presence
- If detection then add user prompt to vector database for future detections