dev2049 a094b7f807 Improve eval chain prompt (#2798) ...

Eval chain is currently very sensitive to differences in phrasing,
punctuation, and tangential information. This prompt has worked better
for me on my examples.

More general q: Do we have any framework for evaluating default prompt
changes? Could maybe start doing some regression testing?

2023-04-12 17:05:20 -07:00

..

qa

Improve eval chain prompt (#2798)

2023-04-12 17:05:20 -07:00

__init__.py

Harrison/evaluation notebook (#426)

2022-12-26 09:16:37 -05:00

loading.py

Harrison/agent eval (#1620)

2023-03-14 12:37:48 -07:00