chore: import upstream snapshot with attribution
CI / ci (3.11) (push) Has been cancelled
CI / ci (3.10) (push) Has been cancelled
CI / dependabot (push) Has been cancelled
Release / release_and_publish (push) Has been cancelled

This commit is contained in:
wehub-resource-sync
2026-07-13 13:36:15 +08:00
commit e64161ec32
892 changed files with 116950 additions and 0 deletions
+10
View File
@@ -0,0 +1,10 @@
# 1. Pull down your Azure Container Registry image
FROM rdagentappregistry.azurecr.io/rd-agent-mle:20250623
# 2. (Optional) install any additional tools you need
# e.g. git, bash-completion, etc.
# RUN apt update && \
# apt install -y git bash-completion && \
# rm -rf /var/lib/apt/lists/*
RUN apt update && \
apt install -y git bash-completion
+39
View File
@@ -0,0 +1,39 @@
# Introduction
!!!!!This dev container is not for public development!!!!!!
!!!!!Please don't use it if you are just a public open-source user.!!!!!!
# Steps to run the dev container (for internal use only)
Prerequisites(this is the reason why this dev container is not for public use):
- Make sure you have the `rdagentappregistry.azurecr.io/rd-agent-mle:20250623` image locally & DevContainer is installed in your IDE
- The kaggle dataset is located at `/home/shared/RD-Agent/kaggle`
1. Open the project and select "Open In DevContainer"
2. Set up your Kaggle Key (do not share this; other internal URLs are hardcoded in the config files)
```bash
export KAGGLE_USERNAME=
export KAGGLE_KEY=
```
3. Run: python rdagent/app/data_science/loop.py --competition nomad2018-predict-transparent-conductors
# Additional Notes
- Please install and use this Dev Container in VS Code.
- You **must open VS Code remotely and enter the `RD-Agent` directory before running the DevContainer configuration (`.devcontainer/devcontainer.json`)**. Otherwise, the workspace and path mappings will not work as expected.
- To open the DevContainer correctly in VS Code:
1. Remotely connect to the machine and open the `RD-Agent` folder in VS Code.
2. Press `Ctrl+Shift+P` (or `Cmd+Shift+P` on Mac), type and select **"Dev Containers: Reopen in Container"**.
# How to grade your submission in the DevContainer
1. save your submission file in `./sumission.csv`
2. Run evaluation
DS_COMPETITION=<your competition name>
conda run -n mlebench mlebench grade-sample submission.csv $DS_COMPETITION --data-dir /tmp/kaggle/zip_files/
+29
View File
@@ -0,0 +1,29 @@
{
"name": "rd-agent-mle DevContainer",
"build": {
"dockerfile": "Dockerfile",
"context": ".."
},
"workspaceFolder": "/workspace/RD-Agent",
"workspaceMount": "source=${localWorkspaceFolder},target=/workspace/RD-Agent,type=bind,consistency=cached",
"remoteUser": "root",
"settings": {
"terminal.integrated.shell.linux": "/bin/bash"
},
"mounts": [
"source=/home/shared/RD-Agent/kaggle,target=/tmp/kaggle,type=bind,consistency=cached,readonly"
],
"extensions": [
"ms-python.python",
"ms-python.vscode-pylance",
"ms-toolsai.jupyter"
],
"runArgs": [
"--init",
"--shm-size=1g",
"--env-file", "${localWorkspaceFolder}/.devcontainer/env",
"--network=host",
"--gpus=all"
],
"postCreateCommand": "make dev"
}
+47
View File
@@ -0,0 +1,47 @@
# Global configs:
MAX_RETRY=12000
RETRY_WAIT_SECONDS=5
TIMEOUT_FAIL_LIMIT=100
# litellm
# CHAT_MODEL=gpt-4o
# CHAT_TEMPERATURE=0.7
CHAT_STREAM=False
CHAT_TEMPERATURE=1
CHAT_MODEL=o1-preview
SYSTEM_PROMPT_ROLE=user
BACKEND=rdagent.oai.backend.LiteLLMAPIBackend
OPENAI_API_KEY=sk-1234
OPENAI_API_BASE=http://ep14.213428.xyz:38881
# amc chat model configs:
EMBEDDING_MODEL=text-embedding-ada-002
# Cache Setting (Optional):
DUMP_CHAT_CACHE=True
USE_CHAT_CACHE=False
DUMP_EMBEDDING_CACHE=True
USE_EMBEDDING_CACHE=False
LOG_LLM_CHAT_CONTENT=True
DS_LOCAL_DATA_PATH=/tmp/kaggle
DS_IF_USING_MLE_DATA=True
PICKLE_CACHE_FOLDER_PATH_STR=./log/pickle_cache
CACHE_WITH_PICKLE=False
ENABLE_CACHE=False
PROMPT_CACHE_PATH=./log/prompt_cache.db
DS_CODER_COSTEER_ENV_TYPE=conda
# DS_PROPOSAL_VERSION=v2 deprecated
DS_CODER_ON_WHOLE_PIPELINE=True
COSTEER_V2_QUERY_FORMER_TRACE_LIMIT=3
# export PYTHONPATH=. # this is for running researcher branch;