isage-data 0.2.1.8__cp311-none-any.whl

isage_data-0.2.1.8.dist-info/METADATA

@@ -0,0 +1,135 @@
+Metadata-Version: 2.4
+Name: isage-data
+Version: 0.2.1.8
+Summary: SAGE Data - Unified data loaders for memory benchmark datasets (LongMemEval, Locomo, MemAgentBench, etc.)
+Author-email: IntelliStream Team <shuhao_zhang@hust.edu.cn>
+License: MIT
+Project-URL: Homepage, https://github.com/intellistream/sageData
+Project-URL: Repository, https://github.com/intellistream/sageData
+Project-URL: Documentation, https://github.com/intellistream/sageData/blob/main/README.md
+Project-URL: Issues, https://github.com/intellistream/sageData/issues
+Keywords: dataset,benchmark,memory,ai,longmemeval,locomo,memagentbench,sage
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+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
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: ==3.11.*
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: isage-common>=0.2.0
+Requires-Dist: pandas>=2.0.0
+Requires-Dist: numpy<2.3.0,>=1.26.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: datasets>=2.14.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: ruff>=0.1.0; extra == "dev"
+Requires-Dist: mypy>=1.0.0; extra == "dev"
+Dynamic: license-file
+
+# SAGE Data ��
+
+**Dataset management module for SAGE benchmark suite**
+
+Provides unified access to multiple datasets through a two-layer architecture:
+- **Sources**: Physical datasets (qa_base, bbh, mmlu, gpqa, locomo, orca_dpo)
+- **Usages**: Logical views for experiments (rag, libamm, neuromem, agent_eval)
+
+## Quick Start
+
+```bash
+./quickstart.sh
+source .venv/bin/activate
+```
+
+Or manual steps:
+
+```python
+from sage.data import DataManager
+
+manager = DataManager.get_instance()
+
+# Access datasets by logical usage profile
+rag = manager.get_by_usage("rag")
+qa_loader = rag.load("qa_base")  # already instantiated
+queries = qa_loader.load_queries()
+
+# Or fetch a specific data source directly
+bbh_loader = manager.get_by_source("bbh")
+tasks = bbh_loader.get_task_names()
+```
+
+## 🛠️ CLI 使用方式（精简版）
+
+安装后可直接使用 `sage-data` 命令：
+
+```bash
+sage-data list               # 显示数据源状态（已下载/缺失/远程）
+sage-data usage rag          # 查看某个 usage 的数据映射
+sage-data download locomo    # 下载指定数据源（仅支持部分源）
+
+# 选项
+sage-data list --json        # JSON 输出，便于脚本处理
+sage-data --data-root /path  # 指定自定义数据根目录
+```
+
+当前支持自动下载的源：`locomo`, `longmemeval`, `memagentbench`, `mmlu`。
+其他如 `gpqa`, `orca_dpo` 采用按需在线加载（Hugging Face），`qa_base`/`bbh` 等随包内置。
+
+## Available Datasets
+
+| Dataset | Description | Download Required | Storage |
+|---------|-------------|-------------------|---------|
+| **qa_base** | Question-Answering with knowledge base | ❌ No (included) | Local files |
+| **locomo** | Long-context memory benchmark | ✅ Yes (`python -m locomo.download`) | Local files (2.68MB) |
+| **bbh** | BIG-Bench Hard reasoning tasks | ❌ No (included) | Local JSON files |
+| **mmlu** | Massive Multitask Language Understanding | 📥 Optional (`python -m mmlu.download --all-subjects`) | On-demand or Local (~160MB) |
+| **gpqa** | Graduate-Level Question Answering | ✅ Auto (Hugging Face) | On-demand (~5MB cached) |
+| **orca_dpo** | Preference pairs for alignment/DPO | ✅ Auto (Hugging Face) | On-demand (varies) |
+
+See `examples/` for detailed usage examples.
+
+## 📖 Examples
+
+```bash
+python examples/qa_examples.py            # QA dataset usage
+python examples/locomo_examples.py        # LoCoMo dataset usage
+python examples/bbh_examples.py           # BBH dataset usage
+python examples/mmlu_examples.py          # MMLU dataset usage
+python examples/gpqa_examples.py          # GPQA dataset usage
+python examples/orca_dpo_examples.py      # Orca DPO dataset usage
+python examples/integration_example.py    # Cross-dataset integration
+```
+
+## License
+
+MIT License - see [LICENSE](LICENSE) file.
+
+## 🔗 Links
+
+- **Repository**: https://github.com/intellistream/sageData
+- **Issues**: https://github.com/intellistream/sageData/issues
+
+## ❓ Common Issues
+
+**Q: Where's the LoCoMo data?**  
+A: Run `python -m locomo.download` to download it (2.68MB from Hugging Face).
+
+**Q: How to download MMLU for offline use?**  
+A: Run `python -m mmlu.download --all-subjects` to download all subjects (~160MB).
+
+**Q: GPQA access error?**  
+A: You need to accept the dataset terms on Hugging Face: https://huggingface.co/datasets/Idavidrein/gpqa
+
+**Q: How to use Orca DPO for alignment research?**  
+A: Use `DataManager.get_by_source("orca_dpo")` to get the loader, then use `format_for_dpo()` to prepare data for training.
+
+---
+
+**Version**: 0.1.0 | **Last Updated**: December 2025

isage_data-0.2.1.8.dist-info/RECORD

@@ -0,0 +1,132 @@
+isage_data-0.2.1.8.dist-info/licenses/LICENSE,sha256=8UV2hDddmN5Fm-v7EgDBMiHHtVlo04tzmbX70Ab13NU,1080
+sage/data/__init__.py,sha256=JAIeBEs85Flu5CSt3cCz3B5t-5a8DXw4XUfEp0MnL-Y,803
+sage/data/__init__.pyc,sha256=Hymb6L7SEX5DpbBgah6qqqbgm7vAr45oT-aeQKovCvA,1171
+sage/data/cli.pyc,sha256=yT_3FR6oP0mBJ04k0E7-SDU98idPMJAzul90wowuJpU,15327
+sage/data/manager.pyc,sha256=DZAOVwD27AQHmtTTwDtArg0LDjExtBmebniROEsD3xo,21527
+sage/data/__pycache__/__init__.cpython-311.pyc,sha256=KOjVYD_gB-APFNOx7kJEINlpk0w4SX8P-jQRVg0mNH4,1203
+sage/data/__pycache__/__init__.cpython-312.pyc,sha256=87nvnChTg2ncREvb8hron_NA5v22Cek1yjlyKMvkR4c,1059
+sage/data/__pycache__/cli.cpython-311.pyc,sha256=F-cYpmGU5-eZGqOLrtM_4XlmuQq_y-OnIkB-58U3FLw,15359
+sage/data/__pycache__/cli.cpython-312.pyc,sha256=8YFLF02PpZJYNuTcSfeX0EVBc8I3WXIusvAVED83dws,12834
+sage/data/__pycache__/manager.cpython-311.pyc,sha256=6IHUzw3lKXjD_fSlgPwxPyIL_4fxAxTTMZf2iDuWGe0,21559
+sage/data/__pycache__/manager.cpython-312.pyc,sha256=fMPGOHfjdG160B_GrvQNFP6cbRFKeIAF368Ts1iWRcc,19330
+sage/data/sources/__init__.py,sha256=FuaXfYc4GX3MP9StEpARDfbo5aJxe8SI_L_bIcemkuo,567
+sage/data/sources/__init__.pyc,sha256=matZe2Y3N5klDR-Yi67sjTVgVlT_B8bnYYK0RosdDIU,731
+sage/data/sources/__pycache__/__init__.cpython-311.pyc,sha256=6J6kZLo5acaf0nqky81dAxrQMNSiRCZVF36t2Xq2BAk,763
+sage/data/sources/__pycache__/__init__.cpython-312.pyc,sha256=PtzTCNLFzXwXz7DVGBpXAquaJnvTDWtCdpnkO7Blh3o,752
+sage/data/sources/agent_benchmark/__init__.py,sha256=3QMdQ2xKOqgqpjiEfr0YgDIhcaS27JeWEOGAuwhJyqU,876
+sage/data/sources/agent_benchmark/__init__.pyc,sha256=-ztFyvH-bO2kMJ93MnLQqu4sPcShcZrwbTdbaC17D60,1027
+sage/data/sources/agent_benchmark/dataloader.pyc,sha256=DDDGXzQUXWb_L8hS9a7z6xK0vBeBbnJHnQfvE4lE_dY,22776
+sage/data/sources/agent_benchmark/dataset.yaml,sha256=QpU2qb7m90BrteXlXAIaT7CC-Fwphsnt2a0YtOhIIi0,1143
+sage/data/sources/agent_benchmark/fix_tool_references.pyc,sha256=jy0j2tf260SGEH25XLLD_fUzoatH2b47GRbxREZzXkg,9877
+sage/data/sources/agent_benchmark/generate_data.pyc,sha256=TOMQXUkRZ2KqM14HnZeXPCTz1YqerJiypSaxQarSoYI,12316
+sage/data/sources/agent_benchmark/prepare_planning_data.pyc,sha256=jC-9mYlQN7yhepVm67W0hBzYndM4EvjF2A3ECpzYid8,26682
+sage/data/sources/agent_benchmark/prepare_runtime_data.pyc,sha256=vJhavn-yedF1-lEOCTc50cglu2Wr2NU4VU2KF3TUcfE,23769
+sage/data/sources/agent_benchmark/prepare_timing_data.pyc,sha256=VRWZHeqq1xcdrwft0XNPgmK_28ig4_HwX8M0-NN5lF8,27276
+sage/data/sources/agent_benchmark/test_integration.py,sha256=o5b6zcxzjbVQNdO2HDm-l0xl7U62xul46gdVD2tGXlw,2890
+sage/data/sources/agent_benchmark/validate_cross_task.pyc,sha256=OSCft6fCkiB0GzfBIbCDfYzNnNYrztXA4D0fRThmfZA,8246
+sage/data/sources/agent_benchmark/validate_data.pyc,sha256=6ly30q7Uarjoop0-X-K3slhvtAxwUOFax2AL_AkODiY,15587
+sage/data/sources/agent_benchmark/external_benchmarks/__init__.py,sha256=TbcZ7BAxM98mJMgiDC7VjBYhGZ01KLH538MCovD4FsM,665
+sage/data/sources/agent_benchmark/external_benchmarks/__init__.pyc,sha256=U_rYEx3oMlJDDGOu5s-Zk3wWcgHxXHLUB3u9OyVXfV4,870
+sage/data/sources/agent_benchmark/external_benchmarks/converters.pyc,sha256=ifLYhufKTmaNAGe7_CnE83N4vAONY_gBKBjpzwTCHAE,22570
+sage/data/sources/agent_benchmark/external_benchmarks/download_all.pyc,sha256=rupmuv2R-EKVmY_oHZeJVo6KG2oaUFMtTnFcQSvWVLE,7066
+sage/data/sources/agent_benchmark/external_benchmarks/download_apibank.pyc,sha256=xmOzVaRR01IxN1o6zojFFhmoqvYyoWrapqxu6oQ_3ak,26225
+sage/data/sources/agent_benchmark/external_benchmarks/download_bfcl.pyc,sha256=bDlsfkiisUqr2zd5RyXwczVfE78TEpPdN32e0QcVycA,6239
+sage/data/sources/agent_benchmark/external_benchmarks/download_toolalpaca.pyc,sha256=92tVhXVKcd_c2tS6JWKdRABLcIycdPGqkTGUgMPmVTE,30759
+sage/data/sources/agent_benchmark/external_benchmarks/download_toolbench.pyc,sha256=4kLLVjjGxO5NVTXYis-lJV8vDZkFZ4_jVrS9_60OoEs,6422
+sage/data/sources/agent_benchmark/external_benchmarks/loader.pyc,sha256=Cf4KcGb0433t7LRA2JE-FYgZGFiArOsHRutSskA4R10,14374
+sage/data/sources/agent_benchmark/tests/test_agent_benchmark_loader.py,sha256=YjJ4LV6Ui0d_hDUQJU0CfMMrLAE8z8oaQdAR00bJMMw,13130
+sage/data/sources/agent_sft/__init__.py,sha256=GYiOa-F46Ulg7u3B4FdBQay1B_tFdLw_mXLHhptSMDk,250
+sage/data/sources/agent_sft/__init__.pyc,sha256=y8Fcax2VijAPG4gLeuq5A-hCsw6W3UqMDlSB1bjCPF4,433
+sage/data/sources/agent_sft/dataloader.pyc,sha256=C1uYp0Ab5htHfwAEwobs9cVZCqpG9wooPihOmgUZ6jw,14036
+sage/data/sources/agent_sft/dataset.yaml,sha256=87cfmcXyPDKkR_3ZMjd81Tol8JOm4fSanpehh7sltgo,227
+sage/data/sources/agent_sft/fix_tool_ids.pyc,sha256=lARrp92Gi8gPEFtOW_IjKES7MwMAGSEYiz_QRsKWd7Q,8666
+sage/data/sources/agent_sft/schemas.pyc,sha256=US-L1dfqMzLlRleHXpm0eqTXNj2XDRrNQgZmXEG-EfU,10473
+sage/data/sources/agent_sft/data/generate_data.pyc,sha256=RQqQ_51ETTseCCjcHsT4lyHFVW3Wl-RpE7DX_X_oiS4,8823
+sage/data/sources/agent_sft/data/prompts_template.yaml,sha256=McR-U4QkLEjezQ_BZXcgPI8UqBJmGUtcVaqFa049w-Y,2281
+sage/data/sources/agent_sft/tests/test_agent_sft_loader.py,sha256=1CJkbQEmu6zWEQJB3Pcbtyr_bd8MxHQ7J8DCtpwdpjk,11468
+sage/data/sources/agent_tools/__init__.py,sha256=kBjgRB9m5sOMhsYmTSJvI95DnjFB9wBbpqui7nMAVa0,257
+sage/data/sources/agent_tools/__init__.pyc,sha256=C8uu0Kwf71TlvSJlq-e1ECSmWk935RH-Zq5Dfzxtv38,457
+sage/data/sources/agent_tools/dataloader.pyc,sha256=j8qWlRhYbzNktloV4Z2lQWgmzCSNsEAglqv8s-Rl0wU,21285
+sage/data/sources/agent_tools/dataset.yaml,sha256=1B8tq5CCVi9I4hX5Jt4keyom1tqw5U9q_dxzLmviCJ0,283
+sage/data/sources/agent_tools/generate_tools.pyc,sha256=c0W0Uh28hYbk3dGFh_pX-rFilPqtEiW6JuYx1QPWLZY,18474
+sage/data/sources/agent_tools/schemas.pyc,sha256=DduHEV2VCWav51DDvmilzBQTO2-493hmaEx8GqXcpto,16007
+sage/data/sources/agent_tools/test_integration.py,sha256=aQndSqJxc5O4IZXAalTCVhdFZZcdz0iTZ2LcJz-mB88,3809
+sage/data/sources/agent_tools/validate_data.pyc,sha256=7AhZxvfG3T0Rb2mxP9rm1ny5SshmDB0CCTU1KUHKKMw,13955
+sage/data/sources/agent_tools/tests/test_agent_tools_loader.py,sha256=oG8Kpc70KtgOgNNFJLE6kfOyb94Sc-_-yohritFVmGk,11020
+sage/data/sources/bbh/__init__.py,sha256=MBsn0xDOs52ixaEY2TrE7yPdTfw2u_CamjSEzergL3U,102
+sage/data/sources/bbh/__init__.pyc,sha256=MxeqnPFPywfTJVQWTZmjeHY3yq2bfChGegms2prbiRM,278
+sage/data/sources/bbh/dataloader.pyc,sha256=_xmAP3YP8hm9dyrH4MQNZDGtFO59x-GP2kCUEZ-ewoY,13158
+sage/data/sources/bbh/dataset.yaml,sha256=APyN8KQasC2ytDF7WKrg-hpzkjm5T-cV8wIvCmLgHFA,245
+sage/data/sources/control_plane_benchmark/__init__.py,sha256=ZfGJ0XLpBDe-iwZCpEyU4LxaYsM5Vg2-K1NVnUiNFD4,1109
+sage/data/sources/control_plane_benchmark/__init__.pyc,sha256=VwucBBIGNbmC4PYhXfd9neWIKf_uTd_jzlaUnKZS8kM,1290
+sage/data/sources/control_plane_benchmark/dataloader.pyc,sha256=w0-oqgF0N1Xed0IPjM6Rg9dzslQ7gElT8D6iV8vanMA,27997
+sage/data/sources/control_plane_benchmark/dataset.yaml,sha256=ihLtPNU0YqGNsTFf3DoQZMTg50YsIFJBv1qJaQ-F1PQ,2597
+sage/data/sources/gpqa/__init__.py,sha256=JGY29_Vh-Kq1x471soBxFWjx9nQdDbC9KmW6v3sn8Rs,105
+sage/data/sources/gpqa/__init__.pyc,sha256=ZBXW5wTWnNlZmM_D7YnQjbSChp0rA6btea1h1r1VF2U,281
+sage/data/sources/gpqa/dataloader.pyc,sha256=h5mqui44FdtvBUKcE6mAGQaWJ5IqjV2iLkgqPDNM0i0,12309
+sage/data/sources/gpqa/dataset.yaml,sha256=_EkpdX8rtF-c4W9_E3UsZVyspYBfUKo9zp6JKcWD0Mc,361
+sage/data/sources/libamm_benchmark/__init__.py,sha256=eQkaHZ8BbiIezfLOI4ntVwj_PSKTRyLLd7I6cklLsqA,277
+sage/data/sources/libamm_benchmark/__init__.pyc,sha256=7oCyvdcr5eEPN1Tck4k7OA_mMYMSZKWUSwX3Q7a8TEM,322
+sage/data/sources/libamm_benchmark/dataset.yaml,sha256=rMO8Ajycf8Zp3z2puQIEARH7mwd1HU92_ZAFq2G3PiQ,301
+sage/data/sources/locomo/__init__.py,sha256=qvJdedYm2ly123Tca_BcQq_B1N6vrUS4_p7zzw5R_f8,111
+sage/data/sources/locomo/__init__.pyc,sha256=ypZv6IlQj1t1ZKLiEDvSzMCBLcQ1hBrp0UmEfsV3b7g,287
+sage/data/sources/locomo/dataloader.pyc,sha256=4YEBmv2tOmNCU8SZjsbUIrCl6j465CWkqnNHCehncF0,25683
+sage/data/sources/locomo/dataset.yaml,sha256=ckxVU5A8DVAc8feeVtsVx5mtlTSN4Rd7WNCqLdlsT84,320
+sage/data/sources/locomo/download.pyc,sha256=M7mO9oA4SsWmktFh1qk1RanxG1lt2Phy5XCj9k-8ylk,4640
+sage/data/sources/locomo/locomo10.json,sha256=efqH6Q8ECBNDuMjevsuAqaaEK3anqlN9yf32Ueppj_Q,2805274
+sage/data/sources/locomo/__pycache__/__init__.cpython-311.pyc,sha256=klg-8glD1-YPNSoA2o-u2fsPC3ZsI6aK3nfGg7kqtNs,319
+sage/data/sources/locomo/__pycache__/__init__.cpython-312.pyc,sha256=YpvvVZVDYx8V3GURGEn1p_lGaP1rnr3uL4zZdbFFN90,295
+sage/data/sources/locomo/__pycache__/dataloader.cpython-311.pyc,sha256=heWVnkohmJW3_sLsU2YezM3rq6HHkTPDWR-SIf-yK6w,22724
+sage/data/sources/locomo/__pycache__/dataloader.cpython-312.pyc,sha256=FbY09jfsLV3VMRv-VEO_wpazeG1jhWPFJkY6rWb16NE,21880
+sage/data/sources/locomo/__pycache__/download.cpython-311.pyc,sha256=OVYEDkXd0dzVIvoOcOKuOgFxeyvlywuOhTFT7lT6w5I,4672
+sage/data/sources/longmemeval/__init__.py,sha256=8xdgmUEbDmoQ_492iKe_WHjNguqH0jYqC36d15nbmCc,129
+sage/data/sources/longmemeval/__init__.pyc,sha256=al86XCpBE-m8xhtUV0YK-fm8v_6Vu8Qlk60M4KWarkw,302
+sage/data/sources/longmemeval/compose.pyc,sha256=qfhXrZyY_qd3cx0ihKoEWi-l4ocslR1DzVHU8im0Y-0,8191
+sage/data/sources/longmemeval/dataloader.pyc,sha256=j87OhZYVR_SwimmiMizHMuU5YctnoWgB1HcBLjVJxWc,22591
+sage/data/sources/longmemeval/dataset.yaml,sha256=4hr1HNtNgpxJdc4uvGHanS4x1fILGwoidzz-lWSvsoM,358
+sage/data/sources/longmemeval/download.pyc,sha256=Rdc9QgqZK_YZnkkn_NbgJoYdH7uuN6v27p0R_TtJTQ0,4929
+sage/data/sources/longmemeval/config/longmemeval_groups.yaml,sha256=hzL5BQSsNuya_h_fkDq0fIZDD7WtyS_KoU14KnajH1o,6355
+sage/data/sources/memagentbench/Conflict_Resolution.parquet,sha256=JNXD8JzgzhViXLn4qY9E8NhkymyU17StBOtpfKOl_0U,1491588
+sage/data/sources/memagentbench/__init__.py,sha256=RIdteSNTrSr5S78whC4Tq-Qw-bYPESwVyA51qjMSEcw,487
+sage/data/sources/memagentbench/__init__.pyc,sha256=k31EFhpJLM1iPqgMu4j5TB2SKnQmRFFtROE7Oe6zU90,665
+sage/data/sources/memagentbench/conflict_resolution_loader.pyc,sha256=DyYZd_JFGOHo_0nLU6Kc00QclNoSe6peE5mP_p7-74s,15748
+sage/data/sources/memagentbench/conflict_resolution_loader_test.py,sha256=e-AsKQG90zCG9L1APln4cc6L0e6y8XTd5gGUKS2hv0U,6278
+sage/data/sources/memagentbench/dataset.yaml,sha256=Jma6JDkMA2L_TPEgqVWdK7P02LcYPDwZg8j1eH5iniA,363
+sage/data/sources/memagentbench/download.pyc,sha256=eOW11Pa1E47-xtHyHsNBBOprYc26EXG2xLbqA6FsI-4,5227
+sage/data/sources/memagentbench/__pycache__/__init__.cpython-312.pyc,sha256=Qv1RkDlR5T19PsZc4oyQtFyeSd9MOyhUoPLYTLnPZbA,671
+sage/data/sources/memagentbench/__pycache__/conflict_resolution_loader.cpython-312.pyc,sha256=gMfjsLq07y_wffn8caYtfNOr1vAuy_voZpSyhK-2d-A,13775
+sage/data/sources/memagentbench/__pycache__/download.cpython-312.pyc,sha256=NBTTBlLzw1K85254-swGreYxhiQj1dftt1bQ0ePAmzs,4544
+sage/data/sources/mmlu/__init__.py,sha256=ZiTx_rmQA0M5z4U8vhZ5uRivldYhGNoxKeFeJVcGxPk,105
+sage/data/sources/mmlu/__init__.pyc,sha256=bU64BMe3SQX63ERfxSszrqhO5CgJbgjOGRERCOl2Km4,281
+sage/data/sources/mmlu/dataloader.pyc,sha256=RxXA9k1m9sxXulaBO0fEtG9W75IyenLsPH9CfHghORo,12790
+sage/data/sources/mmlu/dataset.yaml,sha256=MjyP64sMOzuPdsIft_Z3oCRWFKJ12PKFXy6ruMs539w,365
+sage/data/sources/mmlu/download.pyc,sha256=zhLKNiqSV-4qcYoc7CSNNkfOpSuqYS18PZrWZsllWbY,14197
+sage/data/sources/orca_dpo/__init__.py,sha256=LN1evirvfo7ZZN0hHzg_YSdm5m3ADxMHsNi-jL8IC6s,139
+sage/data/sources/orca_dpo/__init__.pyc,sha256=pNeWRFaR2TIKa7YL1T5u3lQ31cQYZVFrmQN8DbBkRjQ,316
+sage/data/sources/orca_dpo/dataloader.pyc,sha256=Y5b5eCQy015KQSTUX9ZYfXEZsAJ3oFd2wN6ckfEIIZA,13973
+sage/data/sources/qa_base/__init__.py,sha256=VUdivRVm5NVYlC-RfkQinmZ-Goz2kusfI5LUbX1OuyI,104
+sage/data/sources/qa_base/__init__.pyc,sha256=Vq0YqoGnaATWlDHtjtkcC9VjKI274l0Fiesw50JUQ8Y,285
+sage/data/sources/qa_base/dataloader.pyc,sha256=XoUlfhXF3vLrjbDOOV7lzV5X4R0ApxpHmqZY8REi3UU,13358
+sage/data/sources/qa_base/dataset.yaml,sha256=3Wm5JVoSZ2Bi9SA9uD3Lzh1EI2YlI_AudAz49zFjPok,259
+sage/data/sources/qa_base/qa_knowledge_base.txt,sha256=MrTjFQBYyv-QvxyO91dgoDB8k_Zf50V8xfmE8DQezc4,1360
+sage/data/sources/qa_base/qa_knowledge_chromaDB.txt,sha256=7NKnW06tuOyngh98cOjo3c4R0Du2QTy_J5UZVdAMtW0,580
+sage/data/sources/qa_base/sample/one_question.txt,sha256=W7xWZlO1xhfAt9W53NIl48q-TH5jnABT8xR_H9Ak5oE,87
+sage/data/sources/qa_base/sample/question.txt,sha256=VjX0DuAz4BzlpExlPawK57dIQuhFquoclqXgvMPE2gg,29984
+sage/data/sources/qa_base/sample/question1.txt,sha256=GSB3Gq63t1lBKFPX9CyqkhfqE_bKe_VmUyjXUVxi4qs,23
+sage/data/usages/__init__.py,sha256=jHd4op-nfNtvAjr0RekGzlfzODt-RS6pZwkcZ3Zea6k,84
+sage/data/usages/__init__.pyc,sha256=2k6UBW-oED5nZJJ8U49_BC3xZ2m9Em5nlYW3RYcq-tA,230
+sage/data/usages/agent_eval/__init__.py,sha256=0LvUWT-WRMiUwUm14LobIcDkydd0-DTnJ3rj2doPPe0,6117
+sage/data/usages/agent_eval/__init__.pyc,sha256=y1cKUK4dKEopbjVpw4CYarUU9u3SyYKS86alsom3Qj8,8152
+sage/data/usages/agent_eval/config.yaml,sha256=wD1GZoNmnBGMARohvGa1ABjkDCTEnoM-ksOb3LksIjw,459
+sage/data/usages/agent_eval/usage.yaml,sha256=m9j0RPnSm7AJ-_quIDw2SfN7Z0fC0zD35klDw1-esrc,203
+sage/data/usages/agent_eval/profiles/full_eval.yaml,sha256=zKQkGRB3cPtFJJ-416FjDwgSOckl6DSNTwtPcKkQlGY,330
+sage/data/usages/agent_eval/profiles/quick_eval.yaml,sha256=zcnCI-c1oga4vI5xryW8tZGqeZsfF20AXTGmw-p0BpU,235
+sage/data/usages/agent_eval/profiles/sft_training.yaml,sha256=OfsWnUNC0qY98nhG5ZgmLgi4lph6FqU3hSm98RFCn4o,229
+sage/data/usages/libamm/config.yaml,sha256=HorGUurHUMqtwPs8UbXm_N0dOmY61ABJy8nzzE7DSXI,409
+sage/data/usages/neuromem/config.yaml,sha256=A7E7fNYAaeZDzKj76Bpyh6sIKqqvTRzv14MSIX9TuZY,225
+sage/data/usages/rag/config.yaml,sha256=lhxfqBy3X3Y52NkgsJ-w4Hk_ZaAQxEDJFpTByNpN5O0,251
+isage_data-0.2.1.8.dist-info/METADATA,sha256=A1RfNU6fowsWICnjXGnw-sLqktQhEIIuS78p5Bua880,5136
+isage_data-0.2.1.8.dist-info/WHEEL,sha256=27snaH8EChr9VGIQt_981R5IOTPR-vQPuJNW-WzhNJA,93
+isage_data-0.2.1.8.dist-info/entry_points.txt,sha256=8ZU2OS18xxsbtaHiDnvuHutBT73yldAJp4gURFcwx6E,49
+isage_data-0.2.1.8.dist-info/top_level.txt,sha256=hibFyzQHiLOMK68qL1OWsNKaXOmSXqZjeLTBem6Yy7I,5
+isage_data-0.2.1.8.dist-info/RECORD,,

isage_data-0.2.1.8.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (80.9.0)
+Root-Is-Purelib: true
+Tag: cp311-none-any
+

isage_data-0.2.1.8.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+sage-data = sage.data.cli:main

isage_data-0.2.1.8.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024-2026 IntelliStream Team
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

isage_data-0.2.1.8.dist-info/top_level.txt

@@ -0,0 +1 @@
+sage

sage/data/__init__.py

@@ -0,0 +1,37 @@
+"""SAGE Data - Shared dataset library with two-layer architecture."""
+
+from importlib import metadata as _metadata
+
+
+def _resolve_version() -> str:
+    """Return installed package version with graceful fallbacks."""
+    for distribution in ("sage-data", "sage-benchmark"):
+        try:
+            return _metadata.version(distribution)
+        except _metadata.PackageNotFoundError:
+            continue
+    return "0.0.0-dev"
+
+
+__version__ = _resolve_version()
+
+from .manager import (
+    DataManager,
+    DatasetMetadata,
+    SourceRegistry,
+    UsageProfile,
+    UsageRegistry,
+    get_usage_view,
+    load_dataset,
+)
+
+__all__ = [
+    "DataManager",
+    "DatasetMetadata",
+    "SourceRegistry",
+    "UsageProfile",
+    "UsageRegistry",
+    "get_usage_view",
+    "load_dataset",
+    "__version__",
+]

sage/data/sources/__init__.py

@@ -0,0 +1,13 @@
+"""Dataset source registry for SAGE data marketplace.
+
+This package contains one subpackage per physical dataset. Each dataset remains in its
+original location under ``sage.data``; these wrappers expose them through the new
+"sources" layer without changing existing imports.
+
+Example:
+    from sage.data.sources.qa_base import QADataLoader
+    from sage.data.sources.agent_benchmark import AgentBenchmarkDataLoader
+    from sage.data.sources.control_plane_benchmark import ControlPlaneBenchmarkDataLoader
+"""
+
+__all__ = ["agent_benchmark", "control_plane_benchmark"]

sage/data/sources/agent_benchmark/__init__.py

@@ -0,0 +1,35 @@
+"""
+Agent Benchmark Dataset Module
+
+This module provides tools for loading and managing the Agent Benchmark dataset,
+which evaluates AI agent capabilities in tool selection, task planning, and timing judgment.
+
+Usage:
+    from agent_benchmark import AgentBenchmarkDataLoader
+
+    loader = AgentBenchmarkDataLoader()
+    stats = loader.get_stats()
+    
+    for sample in loader.iter_split("tool_selection", split="dev"):
+        print(sample.instruction)
+"""
+
+from .dataloader import (
+    AgentBenchmarkDataLoader,
+    AgentBenchmarkSample,
+    GroundTruthTaskPlanning,
+    GroundTruthTimingJudgment,
+    GroundTruthToolSelection,
+    PlanStep,
+    SampleMetadata,
+)
+
+__all__ = [
+    "AgentBenchmarkDataLoader",
+    "AgentBenchmarkSample",
+    "GroundTruthToolSelection",
+    "GroundTruthTaskPlanning",
+    "GroundTruthTimingJudgment",
+    "SampleMetadata",
+    "PlanStep",
+]

sage/data/sources/agent_benchmark/dataset.yaml

@@ -0,0 +1,44 @@
+name: "agent_benchmark"
+description: "Task packs for tool picking, planning, and timing evaluation"
+type: "benchmark"
+format: "jsonl"
+version: "0.1.0"
+maintainer: "SAGE Agent Benchmark Team"
+tags: ["agent", "benchmark", "planning", "tool_selection", "reasoning"]
+license: "CC-BY-SA-4.0"
+size: "~20MB"
+
+tasks:
+  - name: "tool_selection"
+    description: "Evaluate agent's ability to select appropriate tools"
+    samples: 500
+    splits: ["train", "dev", "test"]
+  
+  - name: "task_planning"
+    description: "Evaluate agent's task decomposition and sequencing"
+    samples: 300
+    splits: ["train", "dev", "test"]
+  
+  - name: "timing_judgment"
+    description: "Evaluate when to use tools vs. direct answers"
+    samples: 300
+    splits: ["train", "dev", "test"]
+
+statistics:
+  total_samples: 1100
+  train_samples: 770
+  dev_samples: 165
+  test_samples: 165
+  
+  difficulty_distribution:
+    easy: "~35%"
+    medium: "~45%"
+    hard: "~20%"
+
+citation: |
+  @dataset{agent_benchmark_2025,
+    title={Agent Benchmark: Evaluating Tool Selection, Planning, and Timing},
+    author={SAGE Team},
+    year={2025},
+    publisher={SAGE Framework}
+  }

sage/data/sources/agent_benchmark/external_benchmarks/__init__.py

@@ -0,0 +1,32 @@
+"""
+External Benchmarks for Agent Evaluation
+
+This module provides unified access to external public benchmarks for
+tool selection, task planning, and timing judgment evaluation.
+
+Supported benchmarks:
+- BFCL (Berkeley Function Calling Leaderboard)
+- ToolBench
+- API-Bank
+- ToolAlpaca
+- TaskBench
+- MetaTool
+"""
+
+from .converters import (
+    APIBankConverter,
+    BFCLConverter,
+    MetaToolConverter,
+    TaskBenchConverter,
+    ToolBenchConverter,
+)
+from .loader import ExternalBenchmarkLoader
+
+__all__ = [
+    "ExternalBenchmarkLoader",
+    "BFCLConverter",
+    "ToolBenchConverter",
+    "APIBankConverter",
+    "TaskBenchConverter",
+    "MetaToolConverter",
+]

sage/data/sources/agent_benchmark/test_integration.py

@@ -0,0 +1,94 @@
+"""
+Integration test for Agent Benchmark
+
+Tests the complete end-to-end workflow including:
+- Module import
+- DataLoader initialization
+- Data iteration
+- Statistics generation
+- Sample validation
+"""
+
+from sage.data.sources.agent_benchmark import (
+    AgentBenchmarkDataLoader,
+    GroundTruthTaskPlanning,
+    GroundTruthTimingJudgment,
+    GroundTruthToolSelection,
+)
+
+
+def test_basic_workflow():
+    """Test basic workflow."""
+    print("=" * 70)
+    print("AGENT BENCHMARK INTEGRATION TEST")
+    print("=" * 70)
+
+    # Initialize loader
+    print("\n1. Initializing loader...")
+    loader = AgentBenchmarkDataLoader()
+    print("   ✅ Loader initialized")
+
+    # Get statistics
+    print("\n2. Getting statistics...")
+    stats = loader.get_stats()
+    print(f"   ✅ Total samples: {stats['total_samples']}")
+    print(f"   ✅ Task types: {len(stats['by_task_type'])}")
+
+    # Test each task type
+    print("\n3. Testing task types...")
+
+    # Tool Selection
+    print("   Testing tool_selection...")
+    ts_samples = list(loader.iter_split("tool_selection", "dev"))
+    sample = ts_samples[0]
+    gt = sample.get_typed_ground_truth()
+    assert isinstance(gt, GroundTruthToolSelection)
+    assert len(gt.top_k) > 0
+    print(f"      ✅ Loaded {len(ts_samples)} samples")
+    print(f"      ✅ Sample: {sample.sample_id}")
+    print(f"      ✅ Tools: {gt.top_k}")
+
+    # Task Planning
+    print("   Testing task_planning...")
+    tp_samples = list(loader.iter_split("task_planning", "dev"))
+    sample = tp_samples[0]
+    gt = sample.get_typed_ground_truth()
+    assert isinstance(gt, GroundTruthTaskPlanning)
+    assert 5 <= len(gt.plan_steps) <= 10
+    print(f"      ✅ Loaded {len(tp_samples)} samples")
+    print(f"      ✅ Sample: {sample.sample_id}")
+    print(f"      ✅ Steps: {len(gt.plan_steps)}")
+
+    # Timing Judgment
+    print("   Testing timing_judgment...")
+    tj_samples = list(loader.iter_split("timing_judgment", "dev"))
+    sample = tj_samples[0]
+    gt = sample.get_typed_ground_truth()
+    assert isinstance(gt, GroundTruthTimingJudgment)
+    assert isinstance(gt.should_call_tool, bool)
+    print(f"      ✅ Loaded {len(tj_samples)} samples")
+    print(f"      ✅ Sample: {sample.sample_id}")
+    print(f"      ✅ Should call tool: {gt.should_call_tool}")
+
+    # Test sample retrieval
+    print("\n4. Testing sample retrieval...")
+    sample = loader.get_sample("ts_000001")
+    assert sample is not None
+    print(f"   ✅ Retrieved sample: {sample.sample_id}")
+
+    # Test validation
+    print("\n5. Testing validation...")
+    errors = loader.validate_sample(sample)
+    assert len(errors) == 0
+    print("   ✅ Sample validation passed")
+
+    print("\n" + "=" * 70)
+    print("✅ ALL INTEGRATION TESTS PASSED")
+    print("=" * 70)
+
+    return True
+
+
+if __name__ == "__main__":
+    success = test_basic_workflow()
+    exit(0 if success else 1)