RD-Agent
RD-Agent copied to clipboard
microsoft
Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are committe...
:robot: I have created a release *beep* *boop* --- ## [0.4.0](https://github.com/microsoft/RD-Agent/compare/v0.3.0...v0.4.0) (2025-04-03) ### Features * (Kaggle) add base template for competition: tabular-playground-series-may-2022 ([#481](https://github.com/microsoft/RD-Agent/issues/481)) ([f3405ca](https://github.com/microsoft/RD-Agent/commit/f3405ca732eb0ddca8e18ea72f69cbd86055c4ab)) * a unified CoSTEER to fit...
## Description ## Motivation and Context ## How Has This Been Tested? - [ ] If you are adding a new feature, test on your own test scripts. ## Screenshots...
## Description Fix a bug in the data preparation for the RANZCR competition. ## Motivation and Context ## How Has This Been Tested? - [ ] If you are adding...
## 🌟 Feature Description We have a lot of retry logic scattered everywhere to ensure structured output. However, there are already some existing tools like: https://github.com/instructor-ai/instructor?tab=readme-ov-file#using-litellm After we merge https://github.com/microsoft/RD-Agent/pull/564,...
## 🌟 Feature Description Currently, only limited numbers of types of LLM is supported in RD-Agent. Maybe we can add support https://docs.litellm.ai/docs/ to the backend (even replace current implementation) to...
During the first loop, the implement of SMA10 is wrong, the wrong code is : df['daily_pct_change'] = df['$close'].pct_change() , which lead the whole following loops to a wrong direction. Can...
I'm encountering an issue where the program fails to create a chat completion after 10 retries. The error occurs when attempting to create an embedding using APIBackend().create_embedding(). Below is the...
## Description This PR provides the automation of experimentation and result collection. ## Motivation and Context This change is required to streamline the process of running experiments, reducing manual setup...
## Description Fix a bug in `KGFBWorkspace`. ## Motivation and Context ## How Has This Been Tested? - [ ] Pass the test by running: `pytest qlib/tests/test_all_pipeline.py` under upper directory...
## Description ## Motivation and Context ## How Has This Been Tested? - [ ] Pass the test by running: `pytest qlib/tests/test_all_pipeline.py` under upper directory of `qlib`. - [ ]...