-
Notifications
You must be signed in to change notification settings - Fork 0
Baseline implementation for QUEST (vector similarity and LLM query decomposition) #49
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: dev
Are you sure you want to change the base?
Conversation
Updated README to clarify that results are not included.
tli2
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Overall this is nice -- however, I think we should work a little bit on the organization of the codebase. Instead of having multiple top-level .py that is invoked from the command line, we should probably have one entry point per experiment and organize the rest more explicitly as a library.
| print(f"Warning: Skipping malformed line in {path}") | ||
| continue | ||
|
|
||
| def main(): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
General nit: Maybe it's better to expose these functionalities as function calls rather than main().
| if line: | ||
| yield json.loads(line) | ||
|
|
||
| def retrieve(queries_path: str, output_path: str): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
What's the difference between this and decompose/retrieve.py?
All changes and workflow are detailed in the README file here: https://github.com/mitdbg/Carnot/blob/baseline/baseline_quest/README.md.
Thank you!