Open
Conversation
Implement a dev folder that allows to work on the models separately. it contains duplicates of the agents where the dependencies to git and trello have been removed... The agents have their lab notebook and the input/output of the models are pointed toward the data folder.
just a quick fix on the example .env file...
Collaborator
|
Love it! Will take a look later today :) |
This file contains hidden or 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Hi all,
Here's my Idea behind the dev Space.
The goal of the dev space is to ease contribution to the dspy models. As of now, if you want to work on the models you have to deal with the integrations with git and trello (+the coming complexities not implemented yet)..
I want each model to be isolated and the inputs/outputs of the models to point toward a common data dir.
I also want a lab notebook to play around the models.
In this PR I show an example of a dev space that I find convenient
I thought of different ways to achieve that and I'd like to have your feedback on those.
With a lite refactoring of the code, we can build a dev dir that just clone the relevant modules (containing the models) in a from src to dev. That way we can easily build the dev dir from the src dir. (This make the duplication of code maintainable)
The other way I found is to isolate the models and create a API around the model. This way we don't have to deal with code duplication and the model are isolated and can be called from anywhere including your little notebook space in your branch...
We can create a branch with a very simplified version of the app.. Basically containing what's needed for the models (like the folder in my PR). This method is pretty much like the first method I describe because we also need to make sure this branch mirrors the main...
Let me know your thoughts!