dslighting 1.3.9__py3-none-any.whl

dslighting-1.3.9.dist-info/METADATA

@@ -0,0 +1,554 @@
+Metadata-Version: 2.4
+Name: dslighting
+Version: 1.3.9
+Summary: Simplified API for Data Science Agent Automation
+Author: DSLighting Team
+License: AGPL-3.0
+Project-URL: Homepage, https://github.com/usail-hkust/dslighting
+Project-URL: Documentation, https://luckyfan-cs.github.io/dslighting-web/
+Project-URL: Repository, https://github.com/usail-hkust/dslighting
+Project-URL: Bug Tracker, https://github.com/usail-hkust/dslighting/issues
+Keywords: data-science,agent,automation,machine-learning,ai
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: GNU Affero General Public License v3
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: pandas>=1.5.0
+Requires-Dist: pydantic>=2.0
+Requires-Dist: python-dotenv>=1.0.0
+Requires-Dist: openai
+Requires-Dist: anthropic
+Requires-Dist: litellm>=1.80.0
+Requires-Dist: rich
+Requires-Dist: transformers
+Requires-Dist: torch
+Requires-Dist: scikit-learn
+Requires-Dist: nbformat
+Requires-Dist: nbclient
+Provides-Extra: full
+Requires-Dist: openai>=1.0.0; extra == "full"
+Requires-Dist: anthropic>=0.34.0; extra == "full"
+Requires-Dist: litellm>=1.0.0; extra == "full"
+Requires-Dist: rich>=13.0.0; extra == "full"
+Requires-Dist: transformers>=4.30.0; extra == "full"
+Requires-Dist: torch>=2.0.0; extra == "full"
+Requires-Dist: scikit-learn>=1.0.0; extra == "full"
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.21; extra == "dev"
+Requires-Dist: black>=23.0; extra == "dev"
+Requires-Dist: mypy>=1.0; extra == "dev"
+Requires-Dist: ruff>=0.1.0; extra == "dev"
+Requires-Dist: build>=0.10.0; extra == "dev"
+Requires-Dist: twine>=4.0.0; extra == "dev"
+
+<div align="center">
+
+<img src="assets/dslighting.png" alt="DSLIGHTING Logo" width="180" style="border-radius: 15px;">
+
+# DSLIGHTING：全流程数据科学智能助手
+
+[![Python](https://img.shields.io/badge/Python-3.10%2B-3776AB?style=flat-square&logo=python&logoColor=white)](https://www.python.org/downloads/)
+[![FastAPI](https://img.shields.io/badge/FastAPI-0.100%2B-009688?style=flat-square&logo=fastapi&logoColor=white)](https://fastapi.tiangolo.com/)
+[![React](https://img.shields.io/badge/React-19-61DAFB?style=flat-square&logo=react&logoColor=black)](https://react.dev/)
+[![Next.js](https://img.shields.io/badge/Next.js-16-000000?style=flat-square&logo=next.js&logoColor=white)](https://nextjs.org/)
+[![License](https://img.shields.io/badge/License-AGPL--3.0-blue?style=flat-square)](LICENSE)
+
+<p align="center">
+  <a href="#快速开始"><img src="https://img.shields.io/badge/🚀-快速开始-green?style=for-the-badge" alt="Quick Start"></a>
+  &nbsp;&nbsp;
+  <a href="#核心功能"><img src="https://img.shields.io/badge/⚡-核心功能-blue?style=for-the-badge" alt="Core Features"></a>
+  &nbsp;&nbsp;
+  <a href="https://luckyfan-cs.github.io/dslighting-web/"><img src="https://img.shields.io/badge/📚-文档-orange?style=for-the-badge" alt="Documentation"></a>
+  &nbsp;&nbsp;
+  <a href="https://luckyfan-cs.github.io/dslighting-web/guide/getting-started.html"><img src="https://img.shields.io/badge/📖-使用指南-purple?style=for-the-badge" alt="User Guide"></a>
+  &nbsp;&nbsp;
+  <a href="https://github.com/usail-hkust/dslighting/stargazers"><img src="https://img.shields.io/github/stars/usail-hkust/dslighting?style=for-the-badge" alt="Stars"></a>
+  &nbsp;&nbsp;
+  <img src="https://komarev.com/ghpvc/?username=usail-hkust&repo=dslighting&style=for-the-badge" alt="Profile views">
+</p>
+
+[English](docs/README_EN.md) · [日本語](docs/README_JA.md) · [Français](docs/README_FR.md)
+
+</div>
+
+<div align="center">
+
+🎯 **智能Agent工作流** &nbsp;•&nbsp; 📊 **交互式数据可视化**<br>
+🤖 **自动化代码生成** &nbsp;•&nbsp; 📈 **全流程任务评估**
+
+[💬 加入微信交流群](#-微信交流群) &nbsp;•&nbsp; [⭐ 给我们Star](https://github.com/usail-hkust/dslighting/stargazers)
+
+</div>
+
+---
+
+## 📸 Web界面预览
+
+### 主页面
+![主页面](assets/web_ui_main_page.png)
+
+### 数据探索 (EDA)
+![数据探索](assets/web_ui_eda.png)
+
+### 自定义任务
+![自定义任务](assets/web_ui_user_custome_task.png)
+
+### 模型训练
+![模型训练](assets/web_ui_model_training.png)
+
+### 报告生成
+![报告生成](assets/web_ui_report.png)
+
+---
+
+## 📖 项目简介
+
+DSLIGHTING 是一个全流程数据科学智能助手系统，采用Agent式工作流和可复用的数据布局，为数据科学任务提供端到端的执行、评估和迭代能力。
+
+### ✨ 核心特性
+
+- 🤖 **多种Agent工作流**：集成aide、automind、dsagent等多种智能体风格
+- 🔄 **元优化框架**：支持AFlow元优化，自动选择最优工作流
+- 📊 **Web可视化界面**：基于Next.js + FastAPI的交互式Dashboard
+- 📝 **完整日志追踪**：记录每次运行的artifacts和摘要
+- 🧩 **可扩展架构**：灵活的任务注册和数据准备流程
+
+---
+
+## 🚀 快速开始
+
+> 📖 **查看完整文档**：https://luckyfan-cs.github.io/dslighting-web/
+>
+> 💡 **需要详细配置步骤？** 查看 [完整配置指南](SETUP_GUIDE.md)
+
+### 系统要求
+
+- **Python**: 3.10 或更高版本
+  ```bash
+  # 检查Python版本
+  python --version
+  # 或
+  python3 --version
+  ```
+- **Node.js**: 18.x 或更高版本
+- **npm**: 9.x 或更高版本（随Node.js一起安装）
+- **Git**: 用于版本控制
+
+### 1. 环境准备
+
+```bash
+git clone https://github.com/usail-hkust/dslighting.git
+cd dslighting
+python3.10 -m venv dslighting
+source dslighting/bin/activate  # Windows: dslighting\Scripts\activate
+```
+
+### 2. 安装依赖
+
+**标准安装**（推荐）：
+```bash
+pip install -r requirements.txt
+```
+
+**备选方案**（如果标准安装出错）：
+```bash
+pip install -r requirements_local.txt
+```
+
+> 💡 **说明**：
+> - `requirements.txt`：锁定具体版本，适合生产环境
+> - `requirements_local.txt`：不锁定版本，依赖更灵活，适合开发环境
+
+### 3. (可选) 安装 Python API 包
+
+> 🎉 **新功能！** DSLighting 现在提供简化的 Python API，让使用像 scikit-learn 一样简单！
+
+**快速安装 Python API 包**：
+```bash
+pip install -e .
+```
+
+**一行代码运行数据科学任务**：
+
+```python
+import dslighting
+
+# 快速运行
+result = dslighting.run_agent("data/competitions/bike-sharing-demand")
+
+# 查看结果
+print(f"得分: {result.score}, 成本: ${result.cost:.4f}")
+
+# 或者更多控制
+data = dslighting.load_data("data/competitions/bike-sharing-demand")
+agent = dslighting.Agent(workflow="aide", model="gpt-4o-mini", temperature=0.7)
+result = agent.run(data)
+```
+
+📖 **详细文档**：[Python API 快速上手指南](docs/python-api-guide.md) | [API 完整文档](dslighting/README.md)
+
+> ✨ **特点**：
+> - 🚀 **超简单**：1-3 行代码完成复杂任务
+> - 🤖 **智能检测**：自动识别任务类型和推荐工作流
+> - 🔧 **完全兼容**：与现有 DSAT API 100% 兼容
+> - 📊 **开箱即用**：合理的默认配置，环境变量驱动
+
+### 4. 配置API密钥
+
+```bash
+cp .env.example .env
+# 编辑.env文件，设置你的API密钥
+```
+
+DSLighting支持多种LLM提供商：
+
+**国内API提供商**（推荐）：
+- **智谱AI** (https://bigmodel.cn/) - GLM系列模型
+  - API Base: `https://open.bigmodel.cn/api/paas/v4`
+  - 获取密钥: https://open.bigmodel.cn/usercenter/apikeys
+- **硅基流动** (https://siliconflow.cn/) - DeepSeek、Qwen等多种模型
+  - API Base: `https://api.siliconflow.cn/v1`
+  - 获取密钥: https://siliconflow.cn/account/ak
+
+**国际API提供商**：
+- **OpenAI** (https://openai.com/) - GPT系列模型
+  - API Base: `https://api.openai.com/v1`
+  - 获取密钥: https://platform.openai.com/api-keys
+
+支持通过 `API_KEY`/`API_BASE` 或 `LLM_MODEL_CONFIGS` 配置不同模型。
+
+> 💡 **配置示例**: 查看 `.env.example` 文件获取详细的多模型配置示例，包括API密钥轮换、温度设置等。
+
+### 5. 准备数据
+
+DSLighting支持多种数据来源。目前支持以下数据准备方式：
+
+#### 方式1：通过MLE-Bench下载（推荐）
+
+[MLE-Bench](https://github.com/openai/mle-bench)是OpenAI提供的机器学习评估基准数据集。
+
+```bash
+# 1. 克隆MLE-Bench仓库
+git clone https://github.com/openai/mle-bench.git
+cd mle-bench
+
+# 2. 安装依赖
+pip install -e .
+
+# 3. 下载所有数据集
+python scripts/prepare.py --competition all
+
+# 4. 将数据链接到DSLighting项目
+# MLE-Bench数据默认在 ~/mle-bench/data/
+# 可以创建符号链接或复制到 dslighting 项目
+ln -s ~/mle-bench/data/competitions /path/to/dslighting/data/competitions
+```
+
+> 📖 **详细信息**: 查看 [MLE-Bench文档](https://github.com/openai/mle-bench) 了解更多数据集详情。
+
+#### 方式2：自定义数据集
+
+您也可以使用自己的数据集，只需按照DSLighting的数据布局结构组织：
+
+```
+data/competitions/
+  <竞赛ID>/
+    config.yaml           # 竞赛配置文件
+    prepared/
+      public/            # 公开数据（训练集、样本提交）
+      private/           # 私有数据（测试标签，用于评分）
+```
+
+> 💡 **提示**: 更多数据类型和预训练模型支持正在陆续开放中，敬请期待！
+
+> 📖 **详细数据准备指南**: 查看 [数据准备文档](docs/DATA_PREPARATION.md) 了解更多详情。
+
+### 6. 运行单个任务
+
+```bash
+python run_benchmark.py \
+  --workflow aide \
+  --benchmark mle \
+  --data-dir data/competitions \
+  --task-id bike-sharing-demand \
+  --llm-model gpt-4
+```
+
+### 7. 使用Web UI（推荐）
+
+我们提供了基于 Next.js + FastAPI 的Web界面，让数据上传和任务执行更加便捷。
+
+#### 6.1 后端环境配置
+
+后端依赖主项目的dslighting环境，只需额外安装Web框架依赖：
+
+```bash
+source dslighting/bin/activate
+# 安装后端依赖
+pip install -r web_ui/backend/requirements.txt
+```
+
+#### 6.2 启动后端服务
+
+```bash
+# 进入后端目录
+cd web_ui/backend
+
+# 启动后端（默认端口8003）
+python main.py
+```
+
+或者使用uvicorn直接启动：
+
+```bash
+cd web_ui/backend
+uvicorn app.main:app --reload --host 0.0.0.0 --port 8003
+```
+
+> 📖 **详细文档**：查看 [后端README](web_ui/backend/README.md) 了解API端点和配置说明
+
+> 💡 **提示**：后端默认运行在 **8003端口**。如果端口被占用，修改 `main.py` 中的端口号。
+
+#### 6.3 启动前端服务
+
+```bash
+cd web_ui/frontend
+npm install  # 首次运行时安装依赖
+npm run dev  # 启动开发服务器
+```
+
+> 📖 **详细文档**：查看 [前端README](web_ui/frontend/README.md) 了解更多前端开发细节
+
+#### 6.4 访问Dashboard
+
+打开浏览器访问：[http://localhost:3000](http://localhost:3000)
+
+---
+
+## 🏗️ 核心功能
+
+### Agent工作流
+
+- **`aide`**：迭代式代码生成和审查循环
+- **`automind`**：带记忆和任务分解的规划+推理
+- **`dsagent`**：结构化操作符流程的规划/执行循环
+- **`data_interpreter`**：快速代码执行和调试循环
+- **`autokaggle`**：SOP风格的Kaggle工作流
+- **`aflow`**：工作流的元优化
+- **`deepanalyze`**：专注分析型执行工作流
+
+### 数据布局
+
+```
+data/competitions/
+  <竞赛ID>/
+    config.yaml           # 竞赛配置文件
+    prepared/
+      public/            # 公开数据
+      private/           # 私有数据
+```
+
+### 配置说明
+
+#### 基础配置
+
+`config.yaml` 会被基准测试运行器和LLM服务读取：
+
+- `competitions`：MLEBench的默认竞赛列表
+- `sciencebench_competitions`（可选）：ScienceBench的默认列表
+- `custom_model_pricing`：LiteLLM的按模型token定价覆盖
+- `run`：轨迹日志记录开关
+
+#### 自定义模型价格配置
+
+**默认行为**：
+- DSLighting 使用 LiteLLM 的内置默认价格
+- 如果没有 `config.yaml`，系统会正常工作，**不会报错**
+- 价格配置是**可选的**，仅在需要覆盖默认价格时使用
+
+**自定义价格配置**：
+
+如果需要为自定义模型设置价格，可以在项目目录创建 `config.yaml` 文件：
+
+**位置**：
+```bash
+# 对于 pip 安装
+/path/to/your/project/config.yaml
+
+# 示例：测试项目中
+/Users/liufan/Applications/Github/dslighting_test_project/config.yaml
+```
+
+> 📖 **参考示例**：查看 [config.yaml.example](config.yaml.example) 获取完整配置示例
+
+**配置示例**：
+```yaml
+custom_model_pricing:
+  openai/Qwen/Qwen3-Coder-480B-A35B-Instruct:
+    input_cost_per_token: 6.0e-07
+    output_cost_per_token: 1.8e-06
+  openai/Qwen/Qwen3-Coder-30B-A3B-Instruct:
+    input_cost_per_token: 6.0e-07
+    output_cost_per_token: 1.8e-06
+  o4-mini-2025-04-16:
+    input_cost_per_token: 1.1e-06
+    output_cost_per_token: 4.4e-06
+  openai/deepseek-ai/DeepSeek-V3.1-Terminus:
+    input_cost_per_token: 5.55e-07
+    output_cost_per_token: 1.67e-06
+```
+
+**价格参数说明**：
+- `input_cost_per_token`：输入 token 价格（每次请求）
+- `output_cost_per_token`：输出 token 价格（每次响应）
+- 单位：美元/token（通常为科学计数法）
+
+**注意事项**：
+- 💡 价格配置是**可选的**，没有 config.yaml 也不会报错
+- 💡 只需要覆盖需要自定义的模型，其他模型使用默认价格
+- 💡 价格配置会影响成本计算和预算控制
+
+---
+
+## 📂 日志和Artifacts
+
+默认日志写入路径：
+
+```
+runs/benchmark_results/<workflow>_on_<benchmark>/<model_name>/
+```
+
+可以通过 `--log-path` 参数覆盖基础目录。
+
+---
+
+## ❓ 常见问题
+
+查看 `docs/FAQ.md` 获取更多详细信息。
+
+---
+
+## ⭐ Star History
+
+<div align="center">
+
+<p>
+  <a href="https://github.com/usail-hkust/dslighting/stargazers"><img src="assets/roster/stargazers.svg" alt="Stargazers"/></a>
+  &nbsp;&nbsp;
+  <a href="https://github.com/usail-hkust/dslighting/network/members"><img src="assets/roster/forkers.svg" alt="Forkers"/></a>
+</p>
+
+<a href="https://www.star-history.com/#usail-hkust/dslighting&type=timeline&legend=top-left">
+  <picture>
+    <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=usail-hkust/dslighting&type=timeline&theme=dark&legend=top-left" />
+    <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=usail-hkust/dslighting&type=timeline&legend=top-left" />
+    <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=usail-hkust/dslighting&type=timeline&legend=top-left" />
+  </picture>
+</a>
+
+</div>
+
+---
+
+## 💬 微信交流群
+
+欢迎加入我们的微信交流群，与其他用户和开发者交流经验！
+
+<div align="center">
+
+<img src="assets/wechat_group.jpg" alt="微信交流群" width="300" style="border-radius: 10px; border: 2px solid #e0e0e0;">
+
+**扫描上方二维码加入DSLighting用户交流群**
+
+</div>
+
+在群内您可以：
+- 🤝 与其他用户交流使用经验
+- 💡 提出功能建议和反馈
+- 🐛 报告Bug并获得帮助
+- 📢 了解最新开发动态
+
+---
+
+## 🤝 贡献指南
+
+<div align="center">
+
+我们希望 DSLIGHTING 能成为社区的一份礼物。🎁
+
+<a href="https://github.com/usail-hkust/dslighting/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=usail-hkust/dslighting" />
+</a>
+
+**核心贡献者**：
+- [luckyfan-cs](https://github.com/luckyfan-cs)（项目负责人，前端和后端开发）
+- [canchengliu](https://github.com/canchengliu)（工作流贡献）
+
+查看 `docs/CONTRIBUTING.md` 了解如何参与贡献。
+
+</div>
+
+---
+
+## 🔗 社区
+
+<div align="center">
+
+**[DSLIGHTING 社区](https://github.com/luckyfan-cs)**
+
+[💬 微信交流群](#-微信交流群) · [⭐ 给我们Star](https://github.com/usail-hkust/dslighting/stargazers) · [🐛 报告Bug](https://github.com/usail-hkust/dslighting/issues) · [💬 参与讨论](https://github.com/usail-hkust/dslighting/discussions)
+
+</div>
+
+---
+
+## 📄 许可证
+
+本项目采用 AGPL-3.0 许可证。
+
+---
+
+## 🙏 致谢
+
+感谢你关注 DSLIGHTING！
+
+---
+
+## 📊 项目统计
+
+![](https://komarev.com/ghpvc/?username=usail-hkust&repo=dslighting&style=for-the-badge)
+![](https://img.shields.io/github/issues/usail-hkust/dslighting?style=for-the-badge)
+![](https://img.shields.io/github/forks/usail-hkust/dslighting?style=for-the-badge)
+![](https://img.shields.io/github/stars/usail-hkust/dslighting?style=for-the-badge)
+
+---
+
+## 📚 引用 (Citation)
+
+如果你在研究中使用了 DSLIGHTING，请使用以下 BibTeX 格式进行引用：
+
+```bibtex
+@software{dslighting2025,
+  title = {DSLIGHTING: An End-to-End Data Science Intelligent Assistant System},
+  author = {Liu, F. and Liu, C. and others},
+  year = {2025},
+  publisher = {GitHub},
+  url = {https://github.com/usail-hkust/dslighting},
+  version = {1.0.0}
+}
+```
+
+或者使用 plain text 格式：
+
+```
+Liu, F., Liu, C., et al. (2025). DSLIGHTING: An End-to-End Data Science Intelligent Assistant System.
+GitHub repository. https://github.com/usail-hkust/dslighting
+```

dslighting-1.3.9.dist-info/RECORD

@@ -0,0 +1,80 @@
+dsat/__init__.py,sha256=wHgtKWECmb5KQyVGqxvQ5mAl_yPg8RkZY4n929SIhi4,105
+dsat/config.py,sha256=revgOB4NHSl-MEvn8nwvaL0Nn3AaJI4uqsWtZzvJdn8,3062
+dsat/runner.py,sha256=y10bjs8pM4TKQjR5oCH7YSgwOh4OG20qI7PJClWuTEM,26486
+dsat/benchmark/__init__.py,sha256=p-wt40WdlZM_--ha5wuYVOEmsD820jFQB-GZnju1Fi4,24
+dsat/benchmark/benchmark.py,sha256=8sVyovMKD2Zrazq-2-7jgfzOJNnWKjsUjOgYQIGeCBA,8002
+dsat/benchmark/datasci.py,sha256=z8dzyXt_F8_0xRg2rfrIkN24rYw0o1yKdoutKlQgpmo,10864
+dsat/benchmark/mle.py,sha256=ppRyaY8e2lZ2VU2fHcKTsavXhfvnu56yK9fDmcP22VU,33365
+dsat/benchmark/sciencebench.py,sha256=Jgmw9nS35nMz86M_v8ZBCJxgzYLwlB5OhvyM-lKWW30,12467
+dsat/common/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+dsat/common/constants.py,sha256=CQVYDiKWvAmVRG-TR8teI-C_7c407hmezhducsG69Fk,277
+dsat/common/exceptions.py,sha256=1FYk8IXnfmk2JkUEjnR8IH0A6Cvq_FHmhnndJCoPScc,1957
+dsat/common/typing.py,sha256=R6FipaTSxj2DBG0WaU7IOu2pvbXavDoL4b2rlcc2h90,1074
+dsat/models/__init__.py,sha256=5GSGpTROhsSb8AQc9FMdXmWk8FpQyoNNzyiFjTeZOfg,91
+dsat/models/candidates.py,sha256=OyKiGk-DfrdDB-h7oIyksWQQqao43j64_y2p4ks1oH0,754
+dsat/models/formats.py,sha256=lUV3SlkO5Qe_xvNbtrrSvn__slGjzTB7YbSxbElr9Po,3536
+dsat/models/task.py,sha256=3lroC5SOjMzjz-IkyHS-PogHFi79Ek1gVNxbnSf0hDY,2569
+dsat/operators/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+dsat/operators/aflow_ops.py,sha256=JrMb-FaSdTVKr6ClOeEHtRI2aUUkAA6fSi0bpHkHhLA,4166
+dsat/operators/autokaggle_ops.py,sha256=eMPt3d66-EsFT5xBRyVrTLeLCH7E0dBH4IAuIGKTdck,7177
+dsat/operators/automind_ops.py,sha256=aoNz2FE-8kmclUeNN3X92mxA7MPTc0O4PYKreJA4bjY,2127
+dsat/operators/base.py,sha256=7ELfrnSkJPyoqiG8l9rDpHWQdjv_lqBOppx8jxAwCYA,746
+dsat/operators/code.py,sha256=fy1wGYOLwbybHGvV1OGpk8N__pHr6hGisAiA5e7WXL0,1881
+dsat/operators/dsagent_ops.py,sha256=XcIpcUHg5jCXkqLR6MImi3ZwMSQLKzenKk6QsHSGT_Q,6010
+dsat/operators/llm_basic.py,sha256=lTgOsPyjCijycVK1Fb9ZGDM3JgNfmPB1jI6zq64Okb4,3755
+dsat/prompts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+dsat/prompts/aflow_prompt.py,sha256=AAMPbyHDWcgMpEHVrMGwYfzvh56rkCjTMfTEEzCJZJM,3940
+dsat/prompts/aide_prompt.py,sha256=RK2B8jWThypyXjUYti2trlj_d57TaVX5SrfQvaGT0VA,3235
+dsat/prompts/autokaggle_prompt.py,sha256=BIf6hgnwSPaIReyYaTTYyzwAlHNHIILXVuS2mlWC9Zs,10574
+dsat/prompts/automind_prompt.py,sha256=zogMhiccjaVfTCYfz65DVmgs6iNCifAhdIP7tR8viEA,1938
+dsat/prompts/common.py,sha256=3N9B8-eEaXV41m1U_h50ym0I4ryug5KPrXyHP8kA5PA,2743
+dsat/prompts/data_interpreter_prompt.py,sha256=YB3mKHU61dAouPKJRNytQlZd8hoCL1SUtmZckV_IQc8,2384
+dsat/prompts/dsagent_prompt.py,sha256=fNlGQQs6EKwfqlzhfbusv6f7OYPQiaFHxOR9_cYtke4,2295
+dsat/services/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+dsat/services/data_analyzer.py,sha256=cSOnYnUDsU2D5sL3tYQ32RWryJ6dnJs7y2PNd3aWvO8,16059
+dsat/services/llm.py,sha256=lDyxGmaP-pfz1vRc3beOjLWhgs1NS2fUOxNoI_0stcM,21412
+dsat/services/llm_single.py,sha256=R6_FfpyPYnLXjecxEBbaQZaEAtamIGQ5RFrsLdFLK6Q,18137
+dsat/services/sandbox.py,sha256=hq6jy2fXMzwa8Mh-4zYpLVl9X0dHcbRJamTOC0_gu2Q,16334
+dsat/services/vdb.py,sha256=WEbuP7S0QRkEUQk9Wtn9cyUzOiF4pAIp9DdwzYrRpeI,3241
+dsat/services/workspace.py,sha256=ly4uRC4BHcyU-Jf6ptZpjYrp79UaWYFlxKguU1gYATQ,7320
+dsat/services/states/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+dsat/services/states/autokaggle_state.py,sha256=fGKPnQs-WGf0-UPfQ69aFV6OO_CqYVRTy7vh5GAbdMI,1724
+dsat/services/states/base.py,sha256=9Kfy1IUOCmp2-4r5IQ334PTUchqWaaTkpZFH3Gb3Yy8,420
+dsat/services/states/dsa_log.py,sha256=f0SpyKn-RzeuyVg1-G6ynow8PasYUWKz-nrMvixaMHk,411
+dsat/services/states/experience.py,sha256=HEJ0z_QtzdDayomyM7jKs86YFwzNfNLwS3N4QDncqcQ,9908
+dsat/services/states/journal.py,sha256=ZR_1LVaqQGPJYnIISN6mojRAAfrq66mFX1quL85o8Y4,5736
+dsat/services/states/operator_library.py,sha256=D4FNKamO6jqZTpbl-Ptz-1BcwLWECaJHI4-0HIa8tW0,10166
+dsat/tasks/__init__.py,sha256=CDHinKWr8SLctx6LGTtl7tL3o_VX5urcUWB2vUcgSF0,83
+dsat/tasks/handlers.py,sha256=ncPxgrCPOyXAu8n2Nj0dd8EIi4_D1z9SthZXeNTt4v4,15598
+dsat/templates/open_ended/grade_template.py,sha256=rb9xmEzJOJlgbX7MFiEfGuXoXJ8t4WjtSD6ZB0ZYyyc,4041
+dsat/tools/__init__.py,sha256=c-x4m_NvU0q5nrz4YcbH3vBUcaxGUS7YIKsL_ni4BRI,59
+dsat/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+dsat/utils/context.py,sha256=7PDSOBZzCGQ9N4qaOgcEM-DiAf4hbtq4RlQ_mK31k6s,6174
+dsat/utils/dynamic_import.py,sha256=LhkKH6yRGUJyJn5oP4NfYCvEn1LnZs6ncgkQQv1AMSE,2980
+dsat/utils/parsing.py,sha256=OYAihoZEYR-flGdLGUdExZM1EocE6VANijJUfbqGWaA,1174
+dsat/workflows/__init__.py,sha256=vCq3ExTxnHpEHkYY4vFNBsIGMNKVA25O0_h2WPrRglY,318
+dsat/workflows/base.py,sha256=P9LjPtJ5gXYQHComBsNAWuYxdMMkQy1u0b2FW1bUqAQ,2292
+dsat/workflows/factory.py,sha256=JTx0lKwZsYe6gGv04zRQpu-NBaQ-K9MrpQ9AadKxDTk,18187
+dsat/workflows/manual/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+dsat/workflows/manual/autokaggle_workflow.py,sha256=7In3YLqEVK35n6g_brNRFzJDKMV7PQgJA92XZi2tk1I,7891
+dsat/workflows/manual/data_interpreter_workflow.py,sha256=TSnRpMgjOcoFDEyVHM-yRxO1UcdQTgLtz0Fqp1oLk4E,7666
+dsat/workflows/manual/deepanalyze_workflow.py,sha256=DJFJnEQjYUL9eK-rKMCVS9v_7Mr1BJM0KnDGnP9tonk,21672
+dsat/workflows/manual/dsagent_workflow.py,sha256=zn3y_14bkKRqSCzaV3iQNzbk2VknEBQ7fP32brqo2wg,3156
+dsat/workflows/search/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+dsat/workflows/search/aflow_workflow.py,sha256=7l1q92z7S96EZwqq4Un8pk2-Nuu94_pjyfvWxVN4ffY,17137
+dsat/workflows/search/aide_workflow.py,sha256=mxIGXcueZGXpv1RXsQJ0YPWtvzICaFQeJowcaZ2krYc,13321
+dsat/workflows/search/automind_workflow.py,sha256=b2JzqUDnDOt_SQdtAvC0fBCJzgTadLylbpgmpaS63Ls,12573
+dsat/workflows/templates/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+dsat/workflows/templates/basic_kaggle_loop.py,sha256=e6YLEpCArgWfKViwoti7SdygHsHp43sqP6VyMqnOJaA,3128
+dslighting/__init__.py,sha256=X2VBmzH5-yDSQMK6JJIa7KZqxMItCHDm5Gt0LRfvalE,5060
+dslighting/core/__init__.py,sha256=T4yYs0RQoz6DBarjOk12PeZq9YoPYrfl3Os0CPlzcB0,252
+dslighting/core/agent.py,sha256=8UGRhri9k2qXJyau3BduwQYSpj-DsW4EzaX2601dBzw,22941
+dslighting/core/config_builder.py,sha256=O6pSYAAwlRoITFuLeKB2BaahK5Zq_0R9NdVGHWZTBXE,10288
+dslighting/core/data_loader.py,sha256=sUVkGmZjQlCaTLoEBiJH2sc44vVoM4rP4ksrew7NjIY,13636
+dslighting/core/task_detector.py,sha256=xOYAV9yiboC8lDeDIEtxvucaGi6fENfeycrowWs-kP0,16300
+dslighting/utils/__init__.py,sha256=SjWP1V1ghRKI6bZ-CO7-eumCQbMfHGwIvrFPLCE_1OY,364
+dslighting/utils/defaults.py,sha256=TMwQJgabA-OrHYhP6VAlYFCbDsP5i-BIFM-U_9mqq8M,4425
+dslighting-1.3.9.dist-info/METADATA,sha256=syV2luI_p0-J6Jf90h_Cf_dgQztPU_Zz41mLifYX0tI,17273
+dslighting-1.3.9.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dslighting-1.3.9.dist-info/top_level.txt,sha256=okQQRxSSVfD73jJSZJ5PxsZV_z8rFLBoP5b80pjJ2FY,16
+dslighting-1.3.9.dist-info/RECORD,,

dslighting-1.3.9.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (80.9.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

dslighting-1.3.9.dist-info/top_level.txt

@@ -0,0 +1,2 @@
+dsat
+dslighting