mirror of
https://github.com/NicolasBohn/NexQuant.git
synced 2026-07-28 16:07:46 +00:00
you-n-g
f78175b37a
* refine ds modal for more cases: eval and es * update model template * prompts for model and ensemble * fix a bug * fix a bug * init: ds workflow evovingstrategy * Adding ensemble (#505) * Initial Draft * Updating logic for init * Revising * Successful Testing * Updating to use the latest & right class * bug: bug-fixing for testing * data science loop changes * data science loop base * ds loop feedback * fix * remove measure_time because it's duplicated (in LoopBase) * add the knowledge query for data_loader & feature * edit ds workflow evaluator * data_loader bug fix * stop evolving when all tasks completed * llm app change * fix break all complete strategy * Adding queried knowledge (#508) Co-authored-by: XianBW <36835909+XianBW@users.noreply.github.com> * fix loop bug * ds workflow evaluator; test; refine prompts * workflow spec * fix ci * feature task changes * ds loop change * fix a bug in feat * add query knowledge for model and workflow * llm_debug info(for show) using pickle instead of json * remove NextLoopException * loop change * coder raise CoderError when all sub_tasks failed * rename code_dict to file_dict in FBWorkspace * add CoSTEER unittest * now show self.version in Task.get_task_information(), simplify CoSTEER sub tasks definition * remove some properties in ModelTask, add model_type in it. * fix llm app bug * llm web app bug fix * ds loop bug fix * fix: give component code to feature&ens eval * loop catch error bug * rename load_from_raw_data to load_data * feat: Add debug data creation functionality for data science scenarios * support local folder (#511) * support local folder * remove unnecessary random * KaggleScen Subclass * small fix * use template for style description * update default scen to kaggle * update sample data script * make sure frac < 1 * fix a bug * feature spec changes * fix * changeimport order * clear unnecessary std outputs * fix a typo * create sample folder after unzip kaggle data * feature/model test script update * Align the data types across modules. * fix a bug in model eval * show line number * move sample entry point to app * spec & model prompt changes * Refine the competition specification to address the data type problem and the coherence issue. * fix some bugs * add file filter in FBworkspace.code property * support non-binary prediction * avoid too much warnings * fix a bug in ensemble module * filtered the knowledge query in all modules * delete RAG in idea proposal * refine the code in ensemble * show exp workspace in llm_st * exp_gen bug fix * feedback bug fix * use `feature` instead of `feat01` * Trace & method of judging if exp is completed change * fix a bug in package calling and execute ci * fix code * bug fix * bug fix * fix a bug * fix some bugs * fix a bug * refactor: Enhance error handling and feedback in data science loop * support different use_azure on chat and embedding models * multi-model proposal logic * fix a small syntax error * loopBase and some changes * ensemble scores change * fbworkspace.code -> .all_codes * use all model codes in workflow coder * check scores.csv's keys(model_names) * model name changes * add a todo in ensemble test * sota_exp changes * give model info in exp gen * add runner time limit * config using debug data or not in evals * exp to feedback base * add feature code when writing model task * small problem * copying during sampling * update * refactor: Simplify code handling and improve workspace management * model part output fix * print model's execution time * bug fix * ensemble test fix * ens small change * ens_test bug fix * Refine partial expansion logic to display only a few subfolders when their structure is uniform, improving readability in nested directories. * several update on prompts * sample subfolders * Filter the stdout after code execution to remove irrelevant information e.g. progress bars, whitespace characters, excessive line breaks. * Add some more prompts and comments * several update on the first init rounds * model timeout as error * fix pattern of getting model codes in workspace * small bux fix on model prompts * remove get_code_with_key since we have regex pattern * fix: Correct tqdm progress bar update logic in LoopBase class * feat: Add diff generation and enhance feedback mechanism in data science loop * update some fix to model and workflow prompts * refine the logic of progress bar filter * add last_successful_exp in exp_gen * fix a one line bug * add a hint in prompt * fix data sample for bms * fix data sample for bms * hypothesis small fix * crawler readme update * fix component gen * fix bug * annotation change * load description.md if it exists * refactor: Simplify SOTA description handling in feedback and prompts * refactor: Use shared templates for feedback and experiment descriptions * change webapp for model codes changes * update proposal * add timeout message for docker run output * fix * refine the code in docker time processing * use .shape instead of len() when do shape eval * won't change size during iteration * support bson sample * sample support jsonl and bson * add former_code to coder prompts * a little speed us in debug data creating * filter progress bar when eval ens and main * avoid costeer makes no change to former code * fix several log error * add timeout judge threshold * fix some bugs in the evaluation of component output shapes * File structure for supporting litellm (#517) Co-authored-by: Young <afe.young@gmail.com> * ignore submission and show processing * ignore submission and show processing * add efficiency notice * refactor: Enhance error message with detailed feedback summary * refactor: Simplify component handling in DSExpGen class * refactor: Update code structure and add docstring for clarity * reserve one sample to each label in data sampling * add Evaluation info * refine costeer code to avoid giving same code twice * use raw_description as plain text * add a prompt hint to avoid same dict key * model task name bug in first model exp gen * fix a typo * add some debug info in costeer tests * task init change * enhance data sampling * refine the code in data_loader * more reasonable loop * fix a bug in data folder description * add error msg & traceback to execution feedback * fix llm error msg detection * add task information to costeer eval & add cache to docker run(use zipfile to store the whole workspace) * fix CI first round * fix CI second round * use txt to store test script to avoid pytest * remove zipfile in requirements * add azure.identity to requirements * ignore debug web page * component test changes * remove redundent task_desc in model coder * feat: Add APE module and prompts for automated prompt engineering * fix: Update .gitignore and improve text formatting in eval.py * refactor: Update print output and improve code comments and imports * style: Fix string formatting and import order in ape.py and fmt.py * exclude ape * add a data folder notice * reduce unnecessary output to stdout * refine the code of describe_data_folder * fix ci * style: streamlit style update (#522) * streamlit style update * fix import * fix format * fix llm_st loop progress bar * debugapp small change * fix model str * refine some prompts * fix model str * fix CI * refine the logic associated with the data_folder * fix ci * small change * set filter_progress_bar as default in execute * model proposal with workflow * add submission check in workflow eval * fix bug * small change * fix CI * fix CI * refactor: Move generate_diff to utils and update DSExpGen logic * more reasonable prompt describing metric direction * fix a minor jinja2 bug * quick fix exp_gen bugs * fix the following bug * fix * fix some bugs * remove workflow from model * add pending_tasks_list in data science to enable coding model and workflow * refine the code for handling JSON-formatted data descriptions * assert with information * ensure correct csv file name * add logging to help record the output * log competition * add log tag for debug llm app * test: Test ds refactor ll (#523) * fix bugs to former scenario * fix a bug because coding in rdloop changed * fix the bug when feedback gets no hypothesis * fix trace structure * change all trace hist when merging hypothesis to experiments * ignore some error in ruff * fix kaggle scenario bugs * refine one line * another bug * another small bug * fix ui bugs * chage kaggle train.py path --------- Co-authored-by: Xu Yang <peteryang@vip.qq.com> * fix CI * Update rdagent/app/data_science/loop.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * add samplecsv into spec prompts * fix CI --------- Co-authored-by: TPLin22 <tplin2@163.com> Co-authored-by: yuanteli <1957922024@qq.com> Co-authored-by: Xisen Wang <118058822+xisen-w@users.noreply.github.com> Co-authored-by: Bowen Xian <xianbowen@outlook.com> Co-authored-by: Xu Yang <peteryang@vip.qq.com> Co-authored-by: XianBW <36835909+XianBW@users.noreply.github.com> Co-authored-by: Tim <illking@foxmail.com> Co-authored-by: 炼金术师华华 <37462254+YeewahChan@users.noreply.github.com> Co-authored-by: Linlang <30293408+SunsetWolf@users.noreply.github.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
123 lines
2.3 KiB
TOML
123 lines
2.3 KiB
TOML
[build-system]
|
|
build-backend = "setuptools.build_meta"
|
|
requires = [
|
|
"setuptools",
|
|
"setuptools-scm",
|
|
]
|
|
|
|
[project]
|
|
authors = [
|
|
{email = "xuyang1@microsoft.com", name = "MSRA-MIIC"},
|
|
]
|
|
classifiers = [
|
|
"Development Status :: 3 - Alpha",
|
|
"License :: OSI Approved :: MIT License",
|
|
"Operating System :: OS Independent",
|
|
"Programming Language :: Python :: 3.10",
|
|
"Programming Language :: Python :: 3.11",
|
|
]
|
|
description = "Research & Development Agent"
|
|
dynamic = [
|
|
"dependencies",
|
|
"optional-dependencies",
|
|
"version",
|
|
]
|
|
keywords = [
|
|
"Autonomous Agents",
|
|
"Large Language Models",
|
|
"Research and Development",
|
|
]
|
|
name = "rdagent"
|
|
readme = "README.md"
|
|
requires-python = ">=3.10"
|
|
|
|
[project.scripts]
|
|
rdagent = "rdagent.app.cli:app"
|
|
|
|
[project.urls]
|
|
homepage = "https://github.com/microsoft/RD-Agent/"
|
|
issue = "https://github.com/microsoft/RD-Agent/issues"
|
|
|
|
[tool.coverage.report]
|
|
fail_under = 80
|
|
|
|
[tool.coverage.run]
|
|
source = [
|
|
"rdagent",
|
|
]
|
|
|
|
[tool.isort]
|
|
color_output = true
|
|
profile = "black"
|
|
|
|
[tool.mypy]
|
|
check_untyped_defs = true
|
|
disallow_any_unimported = true
|
|
disallow_untyped_defs = true
|
|
enable_error_code = [
|
|
"ignore-without-code",
|
|
]
|
|
explicit_package_bases = true
|
|
warn_return_any = true
|
|
warn_unused_ignores = true
|
|
|
|
[[tool.mypy.overrides]]
|
|
ignore_missing_imports = true
|
|
module = "llama"
|
|
|
|
[tool.pytest.ini_options]
|
|
addopts = "-l -s --durations=0"
|
|
log_cli = true
|
|
log_cli_level = "info"
|
|
log_date_format = "%Y-%m-%d %H:%M:%S"
|
|
log_format = "%(asctime)s %(levelname)s %(message)s"
|
|
minversion = "6.0"
|
|
|
|
[tool.ruff]
|
|
fix = true
|
|
line-length = 120
|
|
src = ["rdagent"]
|
|
|
|
[tool.ruff.lint]
|
|
ignore = [
|
|
# https://docs.astral.sh/ruff/rules/#pydocstyle-d
|
|
"ANN401",
|
|
"D",
|
|
"ERA001",
|
|
"FIX",
|
|
"INP001",
|
|
"PGH",
|
|
"PLR0913",
|
|
"S101",
|
|
"S301",
|
|
"T20",
|
|
"TC003",
|
|
"TD",
|
|
]
|
|
select = ["ALL"]
|
|
|
|
[tool.ruff.lint.per-file-ignores]
|
|
"docs/conf.py" = ["INP001"]
|
|
"test/*" = ["S101"]
|
|
|
|
[tool.setuptools]
|
|
packages = ["rdagent"]
|
|
|
|
[tool.setuptools.dynamic]
|
|
dependencies = {file = ["requirements.txt"]}
|
|
|
|
[tool.setuptools.dynamic.optional-dependencies]
|
|
docs = {file = ["requirements/docs.txt"]}
|
|
lint = {file = ["requirements/lint.txt"]}
|
|
package = {file = ["requirements/package.txt"]}
|
|
test = {file = ["requirements/test.txt"]}
|
|
|
|
[tool.setuptools_scm]
|
|
local_scheme = "no-local-version"
|
|
version_scheme = "guess-next-dev"
|
|
|
|
[tool.tomlsort]
|
|
all = true
|
|
in_place = true
|
|
trailing_comma_inline_array = true
|