Skip to content

Conversation

@peteryang1
Copy link
Collaborator

@peteryang1 peteryang1 commented Jul 17, 2025

Description

Motivation and Context

How Has This Been Tested?

  • If you are adding a new feature, test on your own test scripts.

Screenshots of Test Results (if appropriate):

  1. Your own tests:

Types of changes

  • Fix bugs
  • Add new feature
  • Update documentation

📚 Documentation preview 📚: https://RDAgent--1083.org.readthedocs.build/en/1083/

# query their versions dynamically.
# ---------------------------------------------------------------------

def _package_query(self, scenario_desc: str) -> list[str]:
Copy link
Collaborator Author

Choose a reason for hiding this comment

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

move this function to rdagent/scenarios/data_science/proposal/exp_gen/utils.py

Copy link
Collaborator

Choose a reason for hiding this comment

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

I have now moved the functionality of this function to rdagent/scenarios/data_science/proposal/exp_gen/proposal.py, achieving it through one interaction with the Backend API. Therefore, I deem it unnecessary to implement it separately.

)

def get_runtime_environment(self) -> str:
def get_runtime_environment(self, pkgs: list[str] | None = None) -> str:
Copy link
Collaborator Author

Choose a reason for hiding this comment

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

make this function callable from docker

Copy link
Collaborator

Choose a reason for hiding this comment

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

This function wasn’t docker-callable before my changes.
Do we really need Docker support here, or can we just keep it simple for now?

Jensen246 and others added 2 commits July 17, 2025 08:55
…ment

- Remove pkg_query modifications from draft components
- Add package declaration requirement in task_gen prompts
- Add optional packages field to CodingSketch model
- Cache runtime_environment in scenario object for loop-wide reuse
- Parse packages from LLM response and generate runtime environment dynamically
"torch",
"tensorflow",
"pandas",
"numpy",
Copy link
Collaborator Author

Choose a reason for hiding this comment

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

list(set(A) + set(B))

@Jensen246 Jensen246 marked this pull request as ready for review July 17, 2025 10:20
@Jensen246 Jensen246 merged commit 19869ea into main Jul 17, 2025
9 checks passed
@Jensen246 Jensen246 deleted the qzli/dependency_check branch July 17, 2025 10:35
licong01-cloud pushed a commit to licong01-cloud/RD-Agent that referenced this pull request Dec 13, 2025
* feat: add package query in draft.py (not yet enabled)

* feat: integrate package query into task_gen and cache runtime environment

- Remove pkg_query modifications from draft components
- Add package declaration requirement in task_gen prompts
- Add optional packages field to CodingSketch model
- Cache runtime_environment in scenario object for loop-wide reuse
- Parse packages from LLM response and generate runtime environment dynamically

* some refinement

* feat: merge default packages with CLI args in package_info.py

* fix: code style

---------

Co-authored-by: Qizheng Li <[email protected]>
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.

3 participants