ragbits-evaluate 0.0.30.dev29302392__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 (59) hide show
  1. ragbits/evaluate/__init__.py +0 -0
  2. ragbits/evaluate/agent_simulation/__init__.py +87 -0
  3. ragbits/evaluate/agent_simulation/context.py +140 -0
  4. ragbits/evaluate/agent_simulation/conversation.py +333 -0
  5. ragbits/evaluate/agent_simulation/deepeval_evaluator.py +92 -0
  6. ragbits/evaluate/agent_simulation/logger.py +165 -0
  7. ragbits/evaluate/agent_simulation/metrics/__init__.py +19 -0
  8. ragbits/evaluate/agent_simulation/metrics/builtin.py +221 -0
  9. ragbits/evaluate/agent_simulation/metrics/collectors.py +142 -0
  10. ragbits/evaluate/agent_simulation/models.py +37 -0
  11. ragbits/evaluate/agent_simulation/results.py +200 -0
  12. ragbits/evaluate/agent_simulation/scenarios.py +129 -0
  13. ragbits/evaluate/agent_simulation/simulation.py +245 -0
  14. ragbits/evaluate/cli.py +150 -0
  15. ragbits/evaluate/config.py +11 -0
  16. ragbits/evaluate/dataloaders/__init__.py +3 -0
  17. ragbits/evaluate/dataloaders/base.py +95 -0
  18. ragbits/evaluate/dataloaders/document_search.py +61 -0
  19. ragbits/evaluate/dataloaders/exceptions.py +25 -0
  20. ragbits/evaluate/dataloaders/gaia.py +78 -0
  21. ragbits/evaluate/dataloaders/hotpot_qa.py +95 -0
  22. ragbits/evaluate/dataloaders/human_eval.py +70 -0
  23. ragbits/evaluate/dataloaders/question_answer.py +56 -0
  24. ragbits/evaluate/dataset_generator/__init__.py +0 -0
  25. ragbits/evaluate/dataset_generator/pipeline.py +141 -0
  26. ragbits/evaluate/dataset_generator/prompts/__init__.py +0 -0
  27. ragbits/evaluate/dataset_generator/prompts/corpus_generation.py +21 -0
  28. ragbits/evaluate/dataset_generator/prompts/qa.py +83 -0
  29. ragbits/evaluate/dataset_generator/tasks/__init__.py +0 -0
  30. ragbits/evaluate/dataset_generator/tasks/corpus_generation.py +67 -0
  31. ragbits/evaluate/dataset_generator/tasks/filter/__init__.py +0 -0
  32. ragbits/evaluate/dataset_generator/tasks/filter/base.py +43 -0
  33. ragbits/evaluate/dataset_generator/tasks/filter/dont_know.py +34 -0
  34. ragbits/evaluate/dataset_generator/tasks/text_generation/__init__.py +0 -0
  35. ragbits/evaluate/dataset_generator/tasks/text_generation/base.py +66 -0
  36. ragbits/evaluate/dataset_generator/tasks/text_generation/qa.py +96 -0
  37. ragbits/evaluate/dataset_generator/utils.py +43 -0
  38. ragbits/evaluate/evaluator.py +244 -0
  39. ragbits/evaluate/factories/__init__.py +42 -0
  40. ragbits/evaluate/metrics/__init__.py +3 -0
  41. ragbits/evaluate/metrics/base.py +89 -0
  42. ragbits/evaluate/metrics/document_search.py +90 -0
  43. ragbits/evaluate/metrics/gaia.py +84 -0
  44. ragbits/evaluate/metrics/hotpot_qa.py +51 -0
  45. ragbits/evaluate/metrics/human_eval.py +105 -0
  46. ragbits/evaluate/metrics/question_answer.py +205 -0
  47. ragbits/evaluate/optimizer.py +210 -0
  48. ragbits/evaluate/pipelines/__init__.py +37 -0
  49. ragbits/evaluate/pipelines/base.py +64 -0
  50. ragbits/evaluate/pipelines/document_search.py +106 -0
  51. ragbits/evaluate/pipelines/gaia.py +249 -0
  52. ragbits/evaluate/pipelines/hotpot_qa.py +342 -0
  53. ragbits/evaluate/pipelines/human_eval.py +323 -0
  54. ragbits/evaluate/pipelines/question_answer.py +96 -0
  55. ragbits/evaluate/py.typed +0 -0
  56. ragbits/evaluate/utils.py +160 -0
  57. ragbits_evaluate-0.0.30.dev29302392.dist-info/METADATA +58 -0
  58. ragbits_evaluate-0.0.30.dev29302392.dist-info/RECORD +59 -0
  59. ragbits_evaluate-0.0.30.dev29302392.dist-info/WHEEL +4 -0
@@ -0,0 +1,59 @@
1
+ ragbits/evaluate/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
2
+ ragbits/evaluate/cli.py,sha256=vP8l2DyNXpR6jQP83wXKP_RRnGjEXjKnTVBg9RPbDKo,4505
3
+ ragbits/evaluate/config.py,sha256=2WSmbVxyQi893L2FSjRFQoXkWZp1GetcNmR2GCDe0tA,339
4
+ ragbits/evaluate/evaluator.py,sha256=-VcO61r340lt6KWTjkl8DdHmU78WygBP7wfYLT2hu9k,8319
5
+ ragbits/evaluate/optimizer.py,sha256=RqYgoiCIEhjXO0HEN6uwldblHyoPuT3qUdncuHPZgCg,8485
6
+ ragbits/evaluate/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
7
+ ragbits/evaluate/utils.py,sha256=w-hbvKRHI9tEva9wKDTVla0Wm2eCHT2MxVkof27Sqfw,4831
8
+ ragbits/evaluate/agent_simulation/__init__.py,sha256=Cf867LFsLLnDRwDO8rGFQFxvrLemR8qkSqkk5zYyxT0,2971
9
+ ragbits/evaluate/agent_simulation/context.py,sha256=0dGaDmCezH5xlDBrqOnjf0B9rhk0pWyLIhFycJCtldU,5550
10
+ ragbits/evaluate/agent_simulation/conversation.py,sha256=nQr3EHlaBu066rFdWXacyPNXtte6PEDoJnVXjymEifQ,14087
11
+ ragbits/evaluate/agent_simulation/deepeval_evaluator.py,sha256=WDtrApfLS1W5-mB86Yg2xlFgPYVzLtvJV8wCiJs5y2w,3453
12
+ ragbits/evaluate/agent_simulation/logger.py,sha256=47lxIRM-DMvP3Cw4XGUVHSNxqjGOk9ozSgxCY6DOIIQ,6948
13
+ ragbits/evaluate/agent_simulation/models.py,sha256=tOjEzK2Iv1_Nu-jT-soORgd15oqJ2zb8g3EXN7ZKn0c,719
14
+ ragbits/evaluate/agent_simulation/results.py,sha256=EJcpJq-86NYPcY8KMNsmxH9aLXTWGoXZY5aig1fbdP4,6925
15
+ ragbits/evaluate/agent_simulation/scenarios.py,sha256=FU0Z9eZUA7yMAZyAUJ3e5SxZR6XwWdZrbEsLz_GHbhI,4364
16
+ ragbits/evaluate/agent_simulation/simulation.py,sha256=OiYyK63DirjgYioz9K-9DDTpAAGyjJwXcFqk_kTRP78,9772
17
+ ragbits/evaluate/agent_simulation/metrics/__init__.py,sha256=3Gtix1JRAGyLe6JHQTGNr2gIrvEsErY7ys2UkPwdBVU,499
18
+ ragbits/evaluate/agent_simulation/metrics/builtin.py,sha256=ZSK_cBpk1J_bnDes8mbjqw6cW4oml5BAGM7_EOgx6CE,7481
19
+ ragbits/evaluate/agent_simulation/metrics/collectors.py,sha256=fTTYrYimyF0i6KsWagiU12XV0n7AeNaLYqy1n_faWdI,4796
20
+ ragbits/evaluate/dataloaders/__init__.py,sha256=UFJFjmvi3GUQFsx6A5sYD01HH2f7TXcHRW2VNM1pmIA,83
21
+ ragbits/evaluate/dataloaders/base.py,sha256=x8rEl5utNOziF_9urL0grkqoXwMgaDWYSM5akw3Kt9Y,3213
22
+ ragbits/evaluate/dataloaders/document_search.py,sha256=c9Bc4ZtFEKAiG9B70JFiBZlZDkBSGNWFRKabF7PMTU0,2495
23
+ ragbits/evaluate/dataloaders/exceptions.py,sha256=xUOBLj1JuCkcqzRVnu0A0I_i1THxbDt2MEDVdDGjDyY,735
24
+ ragbits/evaluate/dataloaders/gaia.py,sha256=B0XnQ-K2ZW8oNOOwTeUYSok7Yj7JNP4ZERKqEZZE4zQ,2918
25
+ ragbits/evaluate/dataloaders/hotpot_qa.py,sha256=UJmgK9XgUpSt3-iq6FKmLvPQx9aUt-vCDB5qAcGAqfo,3698
26
+ ragbits/evaluate/dataloaders/human_eval.py,sha256=eJM-l1Xkf73_gj1mUv8XTz8LiWvQu2UmkJyYPK_bRY8,2626
27
+ ragbits/evaluate/dataloaders/question_answer.py,sha256=PvG2n9zSy5bH4NJKgSxgxqHjNozLHPJijuBvryiCq_o,1964
28
+ ragbits/evaluate/dataset_generator/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
29
+ ragbits/evaluate/dataset_generator/pipeline.py,sha256=dgnV-Qm0Z7S1Y6ga9-9RscXxxr3krOKsIj7E9WS4ANk,4940
30
+ ragbits/evaluate/dataset_generator/utils.py,sha256=zD-ksXlX62kkIgzBefE4ILsP7He9bHimnZ63LLsMKCA,1325
31
+ ragbits/evaluate/dataset_generator/prompts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
32
+ ragbits/evaluate/dataset_generator/prompts/corpus_generation.py,sha256=QbjB6ZPtVw0_lCF7340XIt9G4nqdY_DbLZs_iM6QsNs,704
33
+ ragbits/evaluate/dataset_generator/prompts/qa.py,sha256=KlVWAvJ0vKvH5WWdBbRe_zSY4ifidtsOcY3cAksZ2eA,3652
34
+ ragbits/evaluate/dataset_generator/tasks/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
35
+ ragbits/evaluate/dataset_generator/tasks/corpus_generation.py,sha256=7CWydp6brrLb_GiT34m3fjQP-ZMw4JHgj4GuDVD1GeI,2118
36
+ ragbits/evaluate/dataset_generator/tasks/filter/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
37
+ ragbits/evaluate/dataset_generator/tasks/filter/base.py,sha256=vKSBOaVC5hLzZe2NMS0LrGZwhN07x0M2WcrijXoh5iY,1146
38
+ ragbits/evaluate/dataset_generator/tasks/filter/dont_know.py,sha256=ydMHyI0JrWZfZZqY1EFAZ38SsdYCiXyvrvcDsxJPOBg,988
39
+ ragbits/evaluate/dataset_generator/tasks/text_generation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
40
+ ragbits/evaluate/dataset_generator/tasks/text_generation/base.py,sha256=bSNsswe2AMskmlctslTo0cJSz_cTc5EW1WW7kshIJPQ,2135
41
+ ragbits/evaluate/dataset_generator/tasks/text_generation/qa.py,sha256=vVk2U3KgnutkqtJOKGoQKxMFD9YLbx4IR7jBIm2a2RE,3848
42
+ ragbits/evaluate/factories/__init__.py,sha256=7nh0J80EfqMWRGtHx4hkfHNMztfC6FMhH8gHumwcH9w,1727
43
+ ragbits/evaluate/metrics/__init__.py,sha256=Mr83ytGyvdXtBlr7Bbo0-5auE0530xsd3wffKSIf8cE,95
44
+ ragbits/evaluate/metrics/base.py,sha256=bOscQ_nJXLGWmP2ls9jncrUoeghNBnKDJsab71pFEjo,2519
45
+ ragbits/evaluate/metrics/document_search.py,sha256=MfvMwEPenqiJdKYuW6WLvmtMch9ZVYb0T6ibpOF3vGI,3189
46
+ ragbits/evaluate/metrics/gaia.py,sha256=Q1oZPVAxRsQkyctJLE95fsGNewmDhzTJ5vjNoXvu10E,3086
47
+ ragbits/evaluate/metrics/hotpot_qa.py,sha256=Tw4gKDbua60fbE7BbxKV08-yp0PbQKTHlnk87GULNe8,1776
48
+ ragbits/evaluate/metrics/human_eval.py,sha256=ud4G-xaMi0f1tkzYb1V2uSgYDF-ymnKxiN6CdOWGZqU,4285
49
+ ragbits/evaluate/metrics/question_answer.py,sha256=369lOoY76KY-wUxBKl0lSQlJSF0JhmPpehNQYeiWNHg,7072
50
+ ragbits/evaluate/pipelines/__init__.py,sha256=PZ2477OqOV622QMC-3iwW5ThC-nYRS9KBe_nlyas3Zs,1573
51
+ ragbits/evaluate/pipelines/base.py,sha256=QV3fjPnbJjeCgcbt8yV1Ho3BamEUc3wSca3MAzaBlV0,1739
52
+ ragbits/evaluate/pipelines/document_search.py,sha256=tgk-I21eshdBbWVsuNa1zWK_fWuDNXhhMCn1_Fdu_Ko,3840
53
+ ragbits/evaluate/pipelines/gaia.py,sha256=DkVAlNI-a9chQGPyOFtjrXWGoPSWogrSfSxxgxanAb8,9686
54
+ ragbits/evaluate/pipelines/hotpot_qa.py,sha256=eHDQ7e_Pa1YRWkc-7oxarYHnZKKvEv_Q8gCBBvo_iss,13629
55
+ ragbits/evaluate/pipelines/human_eval.py,sha256=o2q3O3-OcdRBESwRFUKVU2dQt0TIMDXqxFitdKEw_fw,12406
56
+ ragbits/evaluate/pipelines/question_answer.py,sha256=3CYVHDLnOy4z7kgYPMluiJ8POulHo-w3PEiqvqsF4Dc,2797
57
+ ragbits_evaluate-0.0.30.dev29302392.dist-info/METADATA,sha256=eSd9Xzk1oSIjoLbCda4Ry-ve45U2aK84sPU4H_adEZI,2362
58
+ ragbits_evaluate-0.0.30.dev29302392.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
59
+ ragbits_evaluate-0.0.30.dev29302392.dist-info/RECORD,,
@@ -0,0 +1,4 @@
1
+ Wheel-Version: 1.0
2
+ Generator: hatchling 1.28.0
3
+ Root-Is-Purelib: true
4
+ Tag: py3-none-any