Roman Lutz

Results 458 comments of Roman Lutz

I assumed I'd be able to use an API key which I now understand is wrong. I have yet to try out the identity-based version you implemented. It took us...

Can you put the resulting image in the description @jbolor21 ?

In the current setup, PyRIT is always the user and any target has the assistant role. There's one conversation with adversarial_chat, one with objective_target, and one with the scoring_target (assuming...

Potentially. I am curious if @rlundeen2 has thoughts.

You can see I tagged you and this PR in #822 because I think a lot of these patterns can be generalized so that we don't have to reinvent the...

> Is this idea actually any good? I love it! What do others think? @rlundeen2 @nina-msft @eugeniavkim @jbolor21 @jsong468 @bashirpartovi

@paulinek13 I suppose we can continue this one now that #847 is in! It might be much simpler now 🙂

@herick-santos-ey I'm a little confused. Are you using OpenAIChatTarget or HTTPTarget? OpenAIChatTarget does allow for headers, so I'm not entirely sure what you're asking. Perhaps if you have a comparison...

OK, so to rephrase, you're saying the HTTPTarget isn't forwarding the headers on your request, correct? Have you tried checking whether the following line (copied from HTTPTarget) has the correct...