#15 Add pluggable backends and stop relying on every-ai #26
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
tm-kn
commented
Nov 16, 2023
| for param_key, param_val in self.llm_prompt_params.items(): | ||
| kwargs.setdefault(param_key, param_val) | ||
|
|
||
| return model.prompt(full_prompt, **kwargs) |
There was a problem hiding this comment.
Thought: We could have a separate backend that uses system prompt and one that does not.
tm-kn
force-pushed
the
feature/15-pluggable-backends
branch
from
c6262cf to
a4ee8dd
Compare
tm-kn
commented
Nov 16, 2023
| return self.response_iterator | ||
|
|
||
| def text(self) -> str: | ||
| return " ".join(self.response_iterator) |
There was a problem hiding this comment.
Thought: We could make sure the iterator content gets saved somewhere because I guess it'll get exhausted... We don't want weird side-effects even if it's a test backend.
tm-kn
changed the title
This was referenced Nov 16, 2023
tm-kn
force-pushed
the
feature/15-pluggable-backends
branch
from
a4ee8dd to
de4d985
Compare
tm-kn
changed the title
|
Closing in favour of #27. |
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Outdated suggestions cannot be applied.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.
May be easier to just review #27 as that PR includes all those changes and a few updates.
#15
I still have not considered how #17 and using non-OpenAI models would work but that'd be the next step. I think making this extensible/pluggable feels like a natural first step.