feat: initial red teaming orchestrator setup #2
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
wip - generated prompts wip - add scenarios and handle db
keith-oak
approved these changes
Apr 30, 2024
QDAP-Fred
added a commit
that referenced
this pull request
May 4, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
wip - generated prompts
wip - add scenarios and handle db
This pull request primarily introduces a new red teaming functionality to the codebase. The most significant changes include the addition of new environment variables, the creation of a red teaming orchestrator in
src/red_teaming_orchestrator.py, and the addition of new prompts insrc/scenarios/prompts.json.Environment Variables:
.env_example: AddedDATABASE_NAMEandMAX_CONVERSATION_TURNenvironment variables. These variables are used to set the database name and to limit the number of conversation turns respectively.Red Teaming Orchestrator:
src/red_teaming_orchestrator.py: This new file contains the logic for the red teaming functionality. It reads prompts from a JSON file, sets up a red teaming orchestrator, and applies an attack strategy until a conversation objective is reached or the maximum number of turns is reached. It also sets up logging and starts a new thread for each prompt.Prompts:
src/scenarios/prompts.json: Added new prompts for the red teaming functionality. These prompts are read by the red teaming orchestrator and used to guide the conversation.