sdg-hub 0.2.2__py3-none-any.whl → 0.3.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (35) hide show
  1. sdg_hub/_version.py +2 -2
  2. sdg_hub/core/blocks/llm/client_manager.py +37 -25
  3. sdg_hub/core/blocks/llm/llm_chat_block.py +12 -9
  4. sdg_hub/core/blocks/llm/text_parser_block.py +88 -21
  5. sdg_hub/core/blocks/transform/__init__.py +2 -0
  6. sdg_hub/core/blocks/transform/json_structure_block.py +142 -0
  7. sdg_hub/core/flow/base.py +199 -56
  8. sdg_hub/core/utils/datautils.py +27 -2
  9. sdg_hub/core/utils/flow_metrics.py +261 -0
  10. sdg_hub/core/utils/logger_config.py +50 -9
  11. sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/__init__.py +0 -0
  12. sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/detailed_summary/__init__.py +0 -0
  13. sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/detailed_summary/detailed_summary.yaml +11 -0
  14. sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/detailed_summary/flow.yaml +159 -0
  15. sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/extractive_summary/__init__.py +0 -0
  16. sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/extractive_summary/extractive_summary.yaml +65 -0
  17. sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/extractive_summary/flow.yaml +161 -0
  18. sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/generate_answers.yaml +15 -0
  19. sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/generate_multiple_qa.yaml +21 -0
  20. sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/generate_question_list.yaml +44 -0
  21. sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/key_facts/__init__.py +0 -0
  22. sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/key_facts/flow.yaml +104 -0
  23. sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/key_facts/key_facts_summary.yaml +61 -0
  24. sdg_hub/flows/text_analysis/__init__.py +2 -0
  25. sdg_hub/flows/text_analysis/structured_insights/__init__.py +6 -0
  26. sdg_hub/flows/text_analysis/structured_insights/analyze_sentiment.yaml +27 -0
  27. sdg_hub/flows/text_analysis/structured_insights/extract_entities.yaml +38 -0
  28. sdg_hub/flows/text_analysis/structured_insights/extract_keywords.yaml +21 -0
  29. sdg_hub/flows/text_analysis/structured_insights/flow.yaml +153 -0
  30. sdg_hub/flows/text_analysis/structured_insights/summarize.yaml +21 -0
  31. {sdg_hub-0.2.2.dist-info → sdg_hub-0.3.0.dist-info}/METADATA +3 -1
  32. {sdg_hub-0.2.2.dist-info → sdg_hub-0.3.0.dist-info}/RECORD +35 -13
  33. {sdg_hub-0.2.2.dist-info → sdg_hub-0.3.0.dist-info}/WHEEL +0 -0
  34. {sdg_hub-0.2.2.dist-info → sdg_hub-0.3.0.dist-info}/licenses/LICENSE +0 -0
  35. {sdg_hub-0.2.2.dist-info → sdg_hub-0.3.0.dist-info}/top_level.txt +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: sdg_hub
3
- Version: 0.2.2
3
+ Version: 0.3.0
4
4
  Summary: Synthetic Data Generation
5
5
  Author-email: Red Hat AI Innovation <abhandwa@redhat.com>
6
6
  License: Apache-2.0
@@ -53,6 +53,7 @@ Requires-Dist: sentence-transformers; extra == "examples"
53
53
  Requires-Dist: instructor; extra == "examples"
54
54
  Requires-Dist: fastapi; extra == "examples"
55
55
  Requires-Dist: nest-asyncio; extra == "examples"
56
+ Requires-Dist: ipykernel; extra == "examples"
56
57
  Provides-Extra: dev
57
58
  Requires-Dist: pre-commit<4.0,>=3.0.4; extra == "dev"
58
59
  Requires-Dist: pylint<4.0,>=2.16.2; extra == "dev"
@@ -63,6 +64,7 @@ Requires-Dist: pytest-cov; extra == "dev"
63
64
  Requires-Dist: pytest-html; extra == "dev"
64
65
  Requires-Dist: tox<5,>=4.4.2; extra == "dev"
65
66
  Requires-Dist: ruff; extra == "dev"
67
+ Requires-Dist: pytest-env; extra == "dev"
66
68
  Dynamic: license-file
67
69
 
68
70
  # `sdg_hub`: Synthetic Data Generation Toolkit
@@ -1,5 +1,5 @@
1
1
  sdg_hub/__init__.py,sha256=Tw-6R5a8_W1kJcTAsW3R9ltBDP1dy5-fe7Tvt3cSyCQ,550
2
- sdg_hub/_version.py,sha256=o3ZTescp-19Z9cvBGq9dQnbppljgzdUYUf98Nov0spY,704
2
+ sdg_hub/_version.py,sha256=5zTqm8rgXsWYBpB2M3Zw_K1D-aV8wP7NsBLrmMKkrAQ,704
3
3
  sdg_hub/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
4
4
  sdg_hub/core/__init__.py,sha256=NwqB4fwhC29W50VW7QXZssLxx122YvgO9LHDLdgAnrI,496
5
5
  sdg_hub/core/blocks/__init__.py,sha256=9sCkCvDQzJGSedaePVlEIpbNwrkBz_K500VW_6FLhuE,1601
@@ -22,35 +22,50 @@ sdg_hub/core/blocks/evaluation/verify_question_block.py,sha256=LKoIHdxUuTVO24n_M
22
22
  sdg_hub/core/blocks/filtering/__init__.py,sha256=isxSVSvDqkMjG8dQSl3Q2M4g5c1t9fTjBSA21icf-yA,275
23
23
  sdg_hub/core/blocks/filtering/column_value_filter.py,sha256=H8Gif0q9Wc_d1TnVow8Zpsg7blJOFGN1EZmV6OPpkcg,5971
24
24
  sdg_hub/core/blocks/llm/__init__.py,sha256=N6-Prgd4X85oWbMQzhYMrq7OX-NTJm57cghowK-val0,844
25
- sdg_hub/core/blocks/llm/client_manager.py,sha256=PDf07t2s68WQaoU-LTRke6nQUDWDKwiV4ptAT7Cbn18,14047
25
+ sdg_hub/core/blocks/llm/client_manager.py,sha256=IpMUwECL9_oNFC3yxg9A6BRqMcdg0Wdpzx28BhX45Xo,14742
26
26
  sdg_hub/core/blocks/llm/config.py,sha256=gc4xp5D20MSlKMFEos0QAaKUwgbZpBtMGXmn6LsIk78,11289
27
27
  sdg_hub/core/blocks/llm/error_handler.py,sha256=7T-019ZFB9qgZoX1ybIiXyaLjPzrF96qcKmUu6vmO6g,12178
28
- sdg_hub/core/blocks/llm/llm_chat_block.py,sha256=J-iDJTY-txuduFXx-NUhyohWpRnEaYIg4f0VsSgpjVw,22641
28
+ sdg_hub/core/blocks/llm/llm_chat_block.py,sha256=9ytjxjADM0FydkLapZPSQPfzjjrFIdFONs3EJEoKnaw,23007
29
29
  sdg_hub/core/blocks/llm/llm_chat_with_parsing_retry_block.py,sha256=H7LqYpEiFO1g2cxncAl4vkLhQxAYgGpV6cUyQTSG03k,27628
30
30
  sdg_hub/core/blocks/llm/prompt_builder_block.py,sha256=fkJd718X1oYlMY1cjo_8WCO16Gl8Tm0bUPWR78E_uws,13935
31
- sdg_hub/core/blocks/llm/text_parser_block.py,sha256=uYcof6cy1tgMG_mHpFBW4xhVXg40rNhTerM5EqAvcEo,14187
32
- sdg_hub/core/blocks/transform/__init__.py,sha256=Y_3izPCtgnMbFK-gBMeLHZspSrNLgbGheAJXU57XfFw,746
31
+ sdg_hub/core/blocks/llm/text_parser_block.py,sha256=8oRlXEkw8ULA8XVa7WtQZUojodl_ihs1omZpvbwoJQE,17165
32
+ sdg_hub/core/blocks/transform/__init__.py,sha256=lF9InjOzA6p_mjiwV-a2Kwstq9kqRiQ-dEwbsmR9yQs,825
33
33
  sdg_hub/core/blocks/transform/duplicate_columns.py,sha256=SaP7rIF4ZFEFFa50aU2xGNIuddXaEZrKxdWfHjzFpVI,2833
34
34
  sdg_hub/core/blocks/transform/index_based_mapper.py,sha256=XC_a7Skbd3mu7f4ra8fGWPxMwqUMSjJkQ7Ag7vflwJA,8235
35
+ sdg_hub/core/blocks/transform/json_structure_block.py,sha256=hm-0M0NAyUREgJRPyV1u-laorgX6MZ1o17E9rNBhN78,5010
35
36
  sdg_hub/core/blocks/transform/melt_columns.py,sha256=vaYa5Taq6GhNZYWFL4uPK3-SfN2BsKEm-wvjd2EYYoI,4382
36
37
  sdg_hub/core/blocks/transform/rename_columns.py,sha256=qeB5L2utqDQnutUetH1VKZSqDiJSH_yUp5EFCV-XCVI,1998
37
38
  sdg_hub/core/blocks/transform/text_concat.py,sha256=_-B__Hob1WwgwkILPIZvTnsDzuwtoX1hKviyzHlnnes,3149
38
39
  sdg_hub/core/blocks/transform/uniform_col_val_setter.py,sha256=XnjiT29z3PzIPy8M-mmE2w-Miab6Ed5ahy32SaxTCTE,3263
39
40
  sdg_hub/core/flow/__init__.py,sha256=N2NZGngvd7qpT5FI_knKukUFM0IkD9K5jdTi-gDeUI4,475
40
- sdg_hub/core/flow/base.py,sha256=eneLS9GR21q9nK3M8qZzIyJ-OeFF2Lp6ZwzQjBVnbyk,50364
41
+ sdg_hub/core/flow/base.py,sha256=8Xacytg9M82Mbv8r2GLbQgNltH-hCtFS1Fa1WpfFlSw,56488
41
42
  sdg_hub/core/flow/checkpointer.py,sha256=stm5ZtjjEiLk9ZkAAnoQQn5Y8Yl_d7qCsQLZTrCXR48,11867
42
43
  sdg_hub/core/flow/metadata.py,sha256=h9jpvAzWsF5n4ztZMzwa9ZNgnzKTHmFWdn7YbyJLHCw,12977
43
44
  sdg_hub/core/flow/migration.py,sha256=6and-RBqV0t2gRipr1GiOOVnyBJdtyyjw1kO08Z--d4,7558
44
45
  sdg_hub/core/flow/registry.py,sha256=DzCqEEgwhvwnCBAGLogoMVdwXh4pCHrxOWqoxam7O8I,12162
45
46
  sdg_hub/core/flow/validation.py,sha256=pUJvgaUjLpKNwvW6djcqVOF-HShOjegEmGOnUnoX4BA,9722
46
47
  sdg_hub/core/utils/__init__.py,sha256=C2FzLn3dHprwGJDEgI4fyFS3aoCJR-9PhHsunxropJ8,351
47
- sdg_hub/core/utils/datautils.py,sha256=vvZSNZ94vMQMh9Bs99X92UPwSNzyyYwO3V4w3O3QYoA,2801
48
+ sdg_hub/core/utils/datautils.py,sha256=q94NzBEtNwRFhzpk3FHofgJJU0gVRgAV3AAWZ1MroFk,3860
48
49
  sdg_hub/core/utils/error_handling.py,sha256=yku8cGj_nKCyXDsnb-mHCpgukkkAMucJ4iAUrIzqysc,5510
49
50
  sdg_hub/core/utils/flow_id_words.yaml,sha256=5QHpQdP7zwahRuooyAlJIwBY7WcDR7vtbJXxVJqujbg,2317
50
51
  sdg_hub/core/utils/flow_identifier.py,sha256=aAHfK_G9AwEtMglLRMdMpi_AI1dciub5UqBGm4yb2HE,2841
51
- sdg_hub/core/utils/logger_config.py,sha256=MPYdpyNXh_pxFUOAvSCHa98LGjxjaLXoUoqWekqTG4s,422
52
+ sdg_hub/core/utils/flow_metrics.py,sha256=VOdreUzP0kPgnkPjuQk87tZsK5f1u6XGEPM8ugCt0CY,8824
53
+ sdg_hub/core/utils/logger_config.py,sha256=6_cnsIHtSAdq1iTTZ7Q7nAJ1dmldlxSZ0AB49yLiQ20,2034
52
54
  sdg_hub/core/utils/path_resolution.py,sha256=yWof4kGNpQ5dKcrVHg0h9KfOKLZ6ROjdfsLAZsQT5rM,2000
53
55
  sdg_hub/core/utils/yaml_utils.py,sha256=tShCd-FFkp0xlKnLe7dXsMOR4AvT9d2qRUmu4ZnPSEY,1458
56
+ sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
57
+ sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/generate_answers.yaml,sha256=THRT3cY44KGI_69B2wqt2Q89EknnOSE7B4A_jdnxlIU,330
58
+ sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/generate_multiple_qa.yaml,sha256=Cs-yeiXs4yac3dZsurdXBZj-kkwWdK-xBywjvBlgtGI,669
59
+ sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/generate_question_list.yaml,sha256=qHOgUNrQz2vjUjJiEHNGWxDDXwjJlP1kofTxeGgLyPI,1461
60
+ sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/detailed_summary/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
61
+ sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/detailed_summary/detailed_summary.yaml,sha256=Ik6gAml0O-jPq8jpXBAkURzYkQuFOnDZb4LDwjmfAiE,381
62
+ sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/detailed_summary/flow.yaml,sha256=va9ESTlEaZozy8pXTJ8OICjRg08KSP4l305YUKFuGAE,4417
63
+ sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/extractive_summary/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
64
+ sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/extractive_summary/extractive_summary.yaml,sha256=SeapWoOx3fhN5SvWYuHss_9prLE8xSkOic7JkbDHSR0,4081
65
+ sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/extractive_summary/flow.yaml,sha256=Iv4AlbE9PFtTn6teekgiNtrTiYio_nYWS8gyD6eFLUA,4580
66
+ sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/key_facts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
67
+ sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/key_facts/flow.yaml,sha256=Rv0c4s5vim2I5jKzQgjcUfVMdla6czzmZUU67hlTAbg,2898
68
+ sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/key_facts/key_facts_summary.yaml,sha256=YKMX_CuvcThG_bdNCAIXdVBkMvB72I89RGq2ltSSgc8,3298
54
69
  sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/instructlab/README.md,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
55
70
  sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/instructlab/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
56
71
  sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/instructlab/atomic_facts.yaml,sha256=xgUNY793y4lcpdtuWm5Ah1CmbU2gvvPQCpZMMa6kPXU,2447
@@ -61,8 +76,15 @@ sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/instructlab/ev
61
76
  sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/instructlab/extractive_summary.yaml,sha256=fcMV7LaCFZo4D29nwhGJXqFFuZMYVLo9XYjv8zcU6zs,364
62
77
  sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/instructlab/flow.yaml,sha256=oyrLRjEnmioMa_G_sd9yQK_nBt4arwWV5fvKgzYE2ds,6090
63
78
  sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/instructlab/generate_questions_responses.yaml,sha256=yX8aLY8dJSDML9ZJhnj9RzPbN8tH2xfcM4Gc6xZuwqQ,2596
64
- sdg_hub-0.2.2.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
65
- sdg_hub-0.2.2.dist-info/METADATA,sha256=OHIiUh4AqSHVW-asGQdUp67TXL_dCRV7NVC0E14IwM0,9647
66
- sdg_hub-0.2.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
67
- sdg_hub-0.2.2.dist-info/top_level.txt,sha256=TqI7d-HE1n6zkXFkU0nF3A1Ct0P0pBaqI675uFokhx4,8
68
- sdg_hub-0.2.2.dist-info/RECORD,,
79
+ sdg_hub/flows/text_analysis/__init__.py,sha256=WStks4eM_KHNTVsHglcj8vFghmI0PH9P1hUrijBLbwc,125
80
+ sdg_hub/flows/text_analysis/structured_insights/__init__.py,sha256=_DT4NR05JD9CZoSWROPr2lC6se0VjSqQPZJJlEV79mk,274
81
+ sdg_hub/flows/text_analysis/structured_insights/analyze_sentiment.yaml,sha256=1YGPypFJYS8qfYFj2J6ERTgodKJvMF4YHNGt_vOF5qc,1000
82
+ sdg_hub/flows/text_analysis/structured_insights/extract_entities.yaml,sha256=Q_SDy14Zu-qS2sbKfUBmGlYj3k7CUg6HzzXlFCXRKuU,1169
83
+ sdg_hub/flows/text_analysis/structured_insights/extract_keywords.yaml,sha256=_nPPMdHnxag_lYbhYUjGJGo-CvRwWvwdGX7cQhdZ1S0,847
84
+ sdg_hub/flows/text_analysis/structured_insights/flow.yaml,sha256=2HuGTyNwYe6a8Ev-QdKZXwe29NL4wOkq4ecEV9a7NDg,4221
85
+ sdg_hub/flows/text_analysis/structured_insights/summarize.yaml,sha256=WXwQak1pF8e1OwnOoI1EHu8QB6iUNW89rfkTdi1Oq54,687
86
+ sdg_hub-0.3.0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
87
+ sdg_hub-0.3.0.dist-info/METADATA,sha256=eVLM1fK2-9uD_eWhSRW5VTbdUs-XIn_Va3Z-rY31Utk,9735
88
+ sdg_hub-0.3.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
89
+ sdg_hub-0.3.0.dist-info/top_level.txt,sha256=TqI7d-HE1n6zkXFkU0nF3A1Ct0P0pBaqI675uFokhx4,8
90
+ sdg_hub-0.3.0.dist-info/RECORD,,