Roman Lutz
Roman Lutz
@KutalVolkan I totally agree! I'd like to share what we already have first, and then we can compare and see what makes sense. We call this type of indirect prompt...
Sounds great! I should also mention that our existing XPIA work is by no means set in stone. We can modify it if it's useful to support more scenarios. Thanks!
Ah, we ran into the limits of fpdf2 faster than so had hoped... Looks like the license for pypdf is permissible so we should be fine. Thanks for investigating that...
Thank you! Yes, that actually makes perfect sense. I haven't heard of chroma and probably would have used an Azure AI search which is similar but that's a small detail....
Go ahead! It's yours 🙂
I would stick to the word level, not char level. The charswap converter has a way to select the words randomly. Feel free to copy from there. Or better, move...
Sounds great! Just make sure the unit test doesn't actually make a network call. We do the full test in the integration tests (where you can follow the established pattern...
Of course! If you have questions please don't hesitate to ask.
@yash01699 are you still looking into this? If so, great! If you have yet to start you could pick up where #907 left off. If you're no longer interested we...
It is! Reach out if you have questions. This should be doable with a local DuckDB provided you add a few hundred entries.