Skip to content

[#262] Choose a model and prompt using evals #306

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

Open
wants to merge 18 commits into
base: listOfMed
Choose a base branch
from

Conversation

sahilds1
Copy link
Collaborator

@sahilds1 sahilds1 commented Jun 18, 2025

This PR supports choosing a model and prompt for med rules extractions per #262

@sahilds1 sahilds1 changed the title [#262] Choose a model and prompt [WIP] [#262] Choose a model and prompt Jun 18, 2025
@@ -2,7 +2,7 @@

import fitz

from server.api.services.openai_services import openAIServices
from ...services.openai_services import openAIServices
Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@sahilds1 sahilds1 self-assigned this Jun 19, 2025
sahilds1 added 5 commits June 19, 2025 15:12
… and improved defaults

evaluation/evals.py:

Removed unused Reference column from input requirements and function signature.

Added TODOs to improve flexibility and support defaults for instructions.

Suggested running the script with uv for dependency management.

llm_services.py:

Refactored GPT41NanoHandler:

Moved long prompt instructions into a class-level INSTRUCTIONS string.

Simplified and cleaned up the handle_request method.

Added default fallback behavior: uses INSTRUCTIONS if no query is provided.

Removed duplicate and commented-out prompt scaffolding.
@sahilds1 sahilds1 linked an issue Jul 7, 2025 that may be closed by this pull request
@sahilds1 sahilds1 requested a review from taichan03 July 16, 2025 00:37
@sahilds1 sahilds1 changed the title [WIP] [#262] Choose a model and prompt [#262] Choose a model and prompt Jul 16, 2025
@sahilds1 sahilds1 changed the title [#262] Choose a model and prompt [#262] Choose a model and prompt using evals Jul 16, 2025
@sahilds1 sahilds1 marked this pull request as ready for review July 16, 2025 01:02
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Generate an LLM evals reference file of the papers in the database
1 participant