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

..

__init__.py

Adding an in-context QA evaluation chain + chain of thought reasoning chain for improved accuracy (#2444)

2023-04-06 22:32:41 -07:00

eval_chain.py

Adding an in-context QA evaluation chain + chain of thought reasoning chain for improved accuracy (#2444)

2023-04-06 22:32:41 -07:00

eval_prompt.py

Improve eval chain prompt (#2798)

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

generate_chain.py

Harrison/evaluation notebook (#426)

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

generate_prompt.py

Removed duplicate BaseModel dependencies (#2471)

2023-04-06 12:45:16 -07:00