janus-llm 4.3.5__py3-none-any.whl → 4.5.4__py3-none-any.whl

{janus_llm-4.3.5.dist-info → janus_llm-4.5.4.dist-info}/RECORD

@@ -1,4 +1,4 @@
-janus/__init__.py,sha256=2-o8OirYdtEMQhfO5X6nIzP0AsdZHGY4PtRjBg33AFo,361
+janus/__init__.py,sha256=XDTXq0kgLKa_aC6hDm1Zt_fmd5COyTAiSIAAre6lHkg,361
 janus/__main__.py,sha256=Z1-R163-Ryac2kY1sKYfflqBl40nm-o54tlPjGiOP98,68
 janus/_tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 janus/_tests/conftest.py,sha256=V7uW-oq3YbFiRPvrq15YoVVrA1n_83pjgiyTZ-IUGW8,963
@@ -7,28 +7,32 @@ janus/_tests/evaluator_tests/incose_tests/incose_large_test.json,sha256=_tiBnF_D
 janus/_tests/evaluator_tests/incose_tests/incose_small_test.json,sha256=KHizvtrEvRLrBw25q34I-qonDyFUSUpHpOpFhCmKjAo,2557
 janus/_tests/evaluator_tests/inline_comment_tests/mumps_inline_comment_test.m,sha256=i2U_YymEFxpX9w9_5wN_bV4ZHzk8THyVdvhH-2Xildk,3490
 janus/_tests/test_cli.py,sha256=Y1Gx17fBNTQWJGmjPff8bZgg5AnUY0fMWAHzQ0qwi08,4316
-janus/cli/aggregate.py,sha256=VLv32jMTNruCMOdnzMeNpSilu3h95HosrfGrh3YACPk,4142
-janus/cli/cli.py,sha256=-wBRRtjReFGyTUBZnXwGINFiWpi0X6prPQJWXVFt6bE,2684
-janus/cli/constants.py,sha256=hqQY-laRMArNCN0eXrQjpQbVn_-RfPoaBn9mTnWrfvA,1029
+janus/cli/aggregate.py,sha256=MlK1ZHrCLcwp8Pl4sronWZaB5Pp6AkWiCtHMriOkLgQ,4139
+janus/cli/cli.py,sha256=8n7Eo9-2-joVnCTDzrGu4RgemNtyuDaasaVGlhEiQXc,2820
+janus/cli/constants.py,sha256=4mb3YW18Q8bWAfKa05IJbXUxzQrmN81ELL5pR37PtCw,1206
 janus/cli/database.py,sha256=EkLv_fJNlG6oKvCcEzezdHIChaJlPUl3AgeejJU4rW0,9540
-janus/cli/diagram.py,sha256=qEJYGp66gs5v5BaC53eoqbRmxc5wecbqf0exS9JSDK4,5257
-janus/cli/document.py,sha256=jA7FVGQNmktG-qmTrAdixocEX9LhHTTOdyc9YCEolgQ,5425
+janus/cli/diagram.py,sha256=gOOneADH2klUzUx8CEM6qRtq2C5zDukzkF74R46DgWs,6254
+janus/cli/document.py,sha256=3tp85dIZ6sF59v-fEE1BLzk9Hkv4tL5CuFtNWvVzhBQ,5685
 janus/cli/embedding.py,sha256=WBNtcWPrXB4VfzKjeB_fOUm945gzgGjF2XbZkGltgYY,4215
-janus/cli/llm.py,sha256=LdtL0VmEMXS7usYRtFfsIe7q_OKyGziJZUykYtq8mSU,6343
-janus/cli/partition.py,sha256=D3w7s1w9GogXMOeIHzZZJ1MHMmTJupOqdPB80zmXAi0,3647
-janus/cli/self_eval.py,sha256=pZ7kDshISCfqOAqba5v56NhHnReXwxIsx0taRjAQIB4,4445
-janus/cli/translate.py,sha256=UodCvTv2_x-7XT7hqKq4inF5NLEI3zfbVLNAVJzVYxo,5683
-janus/converter/__init__.py,sha256=7oDRGUyVGhxyiZQDYoY7z6Vyokmu-06hm2RMMfo9adg,393
+janus/cli/llm.py,sha256=JfSPUfkGAQyg-chc18ZoBu8K8w0Q9OUbktHsG90wnsg,6537
+janus/cli/partition.py,sha256=AHpB0mfhoQzcD0lAQFObbbD2Pw3KE5Hk0r_2XapT6Fg,3898
+janus/cli/pipeline.py,sha256=nPQt0gUzJxW10v0rj1giaMxq6XPauU4Y8-a7WbLJu80,3820
+janus/cli/self_eval.py,sha256=oQo3ks3GptKV3Sjcp67ILpLv7VrWP55naK-tv_ehkJc,4683
+janus/cli/translate.py,sha256=Etob8z-SU0V8oEimUtYfPvYXHgLUP6pkf4IRDr4dbU0,5948
+janus/converter/__init__.py,sha256=j30j1moH4sEzIZhDcy-_WrP5XGncRWXHfppPTJcan34,501
 janus/converter/_tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-janus/converter/_tests/test_translate.py,sha256=1NxlQdWoKeMxmNCR4ka-asO6jcVbenJIv1VEpIDiSzU,5740
+janus/converter/_tests/test_translate.py,sha256=Sbhn-OjrKtB8CCtZz_CPjlEezEN3qwHcES1C-IeQtFc,5796
 janus/converter/aggregator.py,sha256=MuAXMKmq6PuUo_w6ljyiuDn81Gk2dN-Ci7FVeLc6vhs,1966
-janus/converter/converter.py,sha256=e7xWx2eXnv8TMRSm9jvhXOCggJMVjrAAQkKkquztLI8,27871
-janus/converter/diagram.py,sha256=-wktVBPrSBgNIQfHIfa2bJNg6L9CYJQgrr9-xU8DFPw,1646
-janus/converter/document.py,sha256=2eFWTrQvo9bhA9INLIwx7KJSgic1GtqO83IPREm5b_U,5156
-janus/converter/evaluate.py,sha256=EjZyqvuUfoDsmOv95Mv6As3BUiD5jUzuRSi_aX1LuqI,9514
-janus/converter/partition.py,sha256=ASvv4hAue44qHobO4kqr_tKr-eJsXCPPdD3NtNd9V-E,993
-janus/converter/requirements.py,sha256=9tvQ40FZJtG8niIFn45gPQCgKKHVPPoFLinBv6RAqO4,2027
-janus/converter/translate.py,sha256=64PouZ6nO95E-5YDRgZa5wA3TSgXkmHcND1qoSi1yzU,4232
+janus/converter/chain.py,sha256=XBNf2_S50SsZC8w-jMcGNyAmgYFOaphRVnazTzY7aq0,4138
+janus/converter/converter.py,sha256=Zkvxs-Lu9_wXm4gfEODrttugGIbPv3DRq-Q88KZouE0,43418
+janus/converter/diagram.py,sha256=eURspGgvVGyFioR1QC4EiD6jgss3uJemVpFN0IOQ59g,1898
+janus/converter/document.py,sha256=aPvALPjbo37FBMrXEjtcuoIvtMTE4OYMXR9K9PVuieE,5477
+janus/converter/evaluate.py,sha256=Sj0a0cKnHwMRjwQMtArwCzspMazkcFf76-r1nJDbDuo,11540
+janus/converter/partition.py,sha256=FWLFyC_7BUzoG5Rr-r8ATrtgSmsJI5p4Ul1mZRtuMTY,737
+janus/converter/passthrough.py,sha256=clVe3Cd00CaJncyCvoNL7JDE_rbe4jiYTSx4EC5ooQY,1116
+janus/converter/pool.py,sha256=Lylx97MSKLibjDbFLZhZ0ZX1nTqjPTOEg90hLqkxplQ,2973
+janus/converter/requirements.py,sha256=GWcyrOR0Q1XXKDKSq8u3nLZxcjPq5IxzWRyquoCv12M,781
+janus/converter/translate.py,sha256=jwuhSWIzhjuMJEbHnZS9Y2D8FXhfs6W8PLfpiAeRE6M,1973
 janus/embedding/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 janus/embedding/_tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 janus/embedding/_tests/test_collections.py,sha256=llg-JSuRRFhKkHFiWWSHEWV3iaT6Lwue0lp2tEml9io,2668
@@ -40,7 +44,7 @@ janus/embedding/embedding_models_info.py,sha256=ZV0Ve4_Zq_B_fnL3QohAQUHlRvQGg0mi
 janus/embedding/vectorize.py,sha256=s5DWrWuH0M9qYbLl4oqvwZzZo-ISjGU8Inc9KERQkSc,6449
 janus/language/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 janus/language/_tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-janus/language/_tests/test_combine.py,sha256=sjVVPUg4LYkAmazXGUw_S1xPrzWm67_0tCxhjemNdtI,1843
+janus/language/_tests/test_combine.py,sha256=_v8X82Fby50y1fX2_vggV0XglxUUqiUQBkZXxglZjpM,1871
 janus/language/_tests/test_splitter.py,sha256=Hqexa39LLEXlK3ZUw7Zot4PUIACvye2vkq0Jaox0T10,373
 janus/language/alc/__init__.py,sha256=j7vOMGhT1Vri6p8dsjSaY-fkO5uFn0sJ0nrNGGvcizM,42
 janus/language/alc/_tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -53,7 +57,7 @@ janus/language/binary/_tests/hello.bin,sha256=SRcqx55Vm9GhstlNSA1jDm0AJCCPhP0Xuq
 janus/language/binary/_tests/test_binary.py,sha256=cIKIxjj6kIY3rcxLwqUPESP9bxWrHqMHx9TNuICgfeQ,1724
 janus/language/binary/binary.py,sha256=PHsVa8jcM7sW9aTboGRWXj6ewQznz0kVPNWtP4B9YPU,6555
 janus/language/binary/reveng/decompile_script.py,sha256=veW51oJzuO-4UD3Er062jXZ_FYtTFo9OCkl82Z2xr6A,2182
-janus/language/block.py,sha256=ob2sblvzn06jKodkQ2LvPR9fXVyuXSR1nhmbmDWn6TA,10543
+janus/language/block.py,sha256=wB6m-sbTaVGNAtwvCnbZam3EmShLt18roFSLqBSpBwE,14054
 janus/language/combine.py,sha256=egZRl1xZXAFXa2ZjjfqnNckc9uxuo6e1MJgkRrCgvd8,3650
 janus/language/file.py,sha256=dh2S3owuDOAKaV-GopLmdezmZ4U_Fyp2pLyGmEf0-QU,581
 janus/language/mumps/__init__.py,sha256=-Ou_wJ-JgHezfp1dub2_qCYNiK9wO-zo2MlqxM9qiwE,48
@@ -78,8 +82,8 @@ janus/language/treesitter/_tests/languages/matlab.m,sha256=N29hh2dgjHh1kFHxeOMgS
 janus/language/treesitter/_tests/test_treesitter.py,sha256=fmr_mFSja7vaCVu0TVyLDua3A94jMjY4AqSC5NqnOdQ,2179
 janus/language/treesitter/treesitter.py,sha256=FdsBO8CEo6l9D77aHXns5jRSoZzkvrRGZFCW3oNw15c,7928
 janus/llm/__init__.py,sha256=TKLYvnsWKWfxMucy-lCLQ-4bkN9ENotJZDywDEQmrKg,45
-janus/llm/model_callbacks.py,sha256=cHRZBpYgAwiYbA2k0GQ7DBwBFQZJpEGMUBV3Q_5GTpU,7940
-janus/llm/models_info.py,sha256=BZu7dOl5qm_VqYHogs1-9PRwqIV7mevzfJ-vkpzS8po,11073
+janus/llm/model_callbacks.py,sha256=pNeCENgatzyLOPjgEXxcu7YaH-805VlqVs8wHIZ8W_k,8389
+janus/llm/models_info.py,sha256=Knm43qEuyl0QjKfcNsaJkLdjFKpzaapi6Q7SjqBWGJ0,11831
 janus/metrics/__init__.py,sha256=AsxtZJUzZiXJPr2ehPPltuYP-ddechjg6X85WZUO7mA,241
 janus/metrics/_tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 janus/metrics/_tests/asm_test_file.asm,sha256=5QXVhXVCZKiaLO0I58yFKGAChcSC-8wOESUCBWcLbmM,231
@@ -89,9 +93,8 @@ janus/metrics/_tests/target.py,sha256=hiaJPP9CXkvFBV_wL-gOe_BzELTw0nvB6uCxhxtIiE
 janus/metrics/_tests/test_bleu.py,sha256=k9hSSdGMITsTiXs-Aj4Q5t1_p2v2eD0O9m-vcRi2GKo,1652
 janus/metrics/_tests/test_chrf.py,sha256=I6AB323mSNj9_0dRIgQdslN0OcQH2fzYxdep68d1LZU,2214
 janus/metrics/_tests/test_file_pairing.py,sha256=8qB9xaZlaWmc6oAqQGYreRZLrZmrlVALcgtCz0Zp0uA,1892
-janus/metrics/_tests/test_llm.py,sha256=foKsYM12E4hq4cWjrUDN3WCl9-ViiREgLhudcqRol7g,2977
-janus/metrics/_tests/test_reading.py,sha256=iXu5SIo2-Opu7hgKcqCwfV-m6ZUSnEmHuXCXddOj1Vg,852
-janus/metrics/_tests/test_rouge_score.py,sha256=dnP99nry-U5wyE-CiC0eQwm78IyScnmGQH3BeIEdmLY,2032
+janus/metrics/_tests/test_reading.py,sha256=5RJRX0EmQG2ZPTLpM4pCAd0LnZ9dPgTZc-_nn8sRHFE,2301
+janus/metrics/_tests/test_rouge_score.py,sha256=4Jo1jox4YORYNsctN2zcG2WWP565k-UkujyUEH-xLCM,1855
 janus/metrics/_tests/test_similarity_score.py,sha256=tdzH_8hYb2h7fKxpd_a75di-GPnU_frZ0zn2aeYzkso,811
 janus/metrics/_tests/test_treesitter_metrics.py,sha256=sp_IorshEHjkbsyNeuWMEs-KZKABB4n7A4XnTCySErM,4356
 janus/metrics/bleu.py,sha256=UCrerEtEF5TadbY-vxbr5TQv67j8hrOCk8Q2C5OQXlw,1759
@@ -99,8 +102,7 @@ janus/metrics/chrf.py,sha256=c8AJLVUtzOezH0R7cJ9hwkLQCIHonm56TTYRTmYuBK4,1485
 janus/metrics/cli.py,sha256=Duuw2RF47Z-t1pal0cg3L_-N_91rx29krirqtIwjYLY,157
 janus/metrics/complexity_metrics.py,sha256=9sHxa9tY9IgdFC4grCmDSuu8Nkphm_FWbTecxgW78go,6574
 janus/metrics/file_pairing.py,sha256=b0848gbDTqKVge-uGiujtHdsgcbkpJ04nWF2ul_gbCw,3749
-janus/metrics/llm_metrics.py,sha256=nzzJMSnoZfgtzzltjoCu1l4-Qwuycd-V3z17AtStYdY,5700
-janus/metrics/metric.py,sha256=ZQXz2LLXA3_WW6BluF8Q2LdJKYVWZLYmhO4Ai116ZPY,17168
+janus/metrics/metric.py,sha256=CXnj6gM1LzMJ2QUPWc1N7bg3V36EdHlLo3Idu31o7E0,13709
 janus/metrics/prompts/clarity.txt,sha256=UTo7a_E28a9JIto6wskQSUANPGdO6oPxf_3B2sqhgZw,328
 janus/metrics/prompts/completeness.txt,sha256=5z4a_9a2ruToQnQiW6S02A_IYBIOgwg4KIWHXChA2Co,518
 janus/metrics/prompts/faithfulness.txt,sha256=UdvfuW99_OsT7D7GhVQpG1StwnC3PFZwNbENS_Gev_c,460
@@ -108,21 +110,21 @@ janus/metrics/prompts/hallucination.txt,sha256=CX0MUxkWBE5Yxupg3ypdXykte9mwAuoGf
 janus/metrics/prompts/quality.txt,sha256=JqjKboSd4ueyEE0sg21Y-V9bxxu2li8a9ooGTUf02Vk,328
 janus/metrics/prompts/readability.txt,sha256=shKvNxUZKtdoKkiA24XzE9XWseSCQFZDfxOGhUDBd-0,419
 janus/metrics/prompts/usefulness.txt,sha256=DvZxJAbaRZ9R0K5KqADTt4BaJ0WLgyC5mxQ66xhIsJw,520
-janus/metrics/reading.py,sha256=RyOSebENWPGD1m_-QfKM9v2vfNAQVkiZ2Oyynb2HrVI,3253
-janus/metrics/rouge_score.py,sha256=XnA2ABAceIzzA_9rIYDaMtyD4pphHxXVwxaYvMcqZWE,2878
+janus/metrics/reading.py,sha256=KL_Q4nvoX6KvtmNmkRjgVTPvcZZp-V7_z1240LIYU3U,3755
+janus/metrics/rouge_score.py,sha256=mDJ-fyluAqvL5go68nbMIFOkrO_yOmPT6OUXf3ESVuc,2468
 janus/metrics/similarity.py,sha256=NKd-m8hMB27i1_1CQkG5o7HrAK2wTr89B21Y36kqHiE,1630
 janus/metrics/splitting.py,sha256=610ScHRvALwdkqA6YyGI-tr3a18_cUofldBxGYX0SwE,968
 janus/parsers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 janus/parsers/_tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-janus/parsers/_tests/test_code_parser.py,sha256=3ay5QpUPcynX_EJ-YLl3PR28poutUkT7qvyWUSQ7Too,928
-janus/parsers/code_parser.py,sha256=m7iQgVO3f08JIux7EzG3oVDvdqpQkpU9SwnKSzn2aEo,857
+janus/parsers/_tests/test_code_parser.py,sha256=I3IyTDUjucjeOOdwd3hUv5W8FK2owieFxTAwiMA2V4I,922
+janus/parsers/code_parser.py,sha256=-eNEgycQBgrLUDhN9FyeCDwPexrpUFp3kK2wOG560AI,845
 janus/parsers/doc_parser.py,sha256=XVlzyMWYB_UUwNp5OQ0pxA-KP0ITCZT0CjpQN_mHbWQ,5957
 janus/parsers/eval_parser.py,sha256=Gjh6aTZgpYd2ASJUEPMo4LpCL00cBmbOqc4KM3hy8x8,2922
-janus/parsers/eval_parsers/incose_parser.py,sha256=udyK-24ocfrB1SzmggcERm73dBynrCj4MFSBV8k7YDM,4478
+janus/parsers/eval_parsers/incose_parser.py,sha256=xZii46LzaKxglSdhRL-FHHhQ8sdnA7QHZsW5n5N9P10,4458
 janus/parsers/eval_parsers/inline_comment_parser.py,sha256=QzKgzeWPhyIEkLxJBpeutSocSJjjXEcWRRS635bXEO8,3973
 janus/parsers/parser.py,sha256=YwkiFthesUaxHngrt4v2lb_HYgKpusnlVgTMwi3WttE,1874
 janus/parsers/partition_parser.py,sha256=2l4fERb7lf-RTKBTi-TZBys0kJXlzRJWeB8RHNzyTDs,5834
-janus/parsers/reqs_parser.py,sha256=NHoHdJ4F50YDWhYmBQgypP05u6aCPl8NyWTuMX94M7s,2504
+janus/parsers/reqs_parser.py,sha256=5kS3gtiofZLfnV4GaPEiSwxx3bAG4k-DBDc5wuGF6MQ,2523
 janus/parsers/uml.py,sha256=iB9j0gtaT4Zo4tYFCGQNRzXa6--wDCuw-sLeQk19kfc,3429
 janus/prompts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 janus/prompts/prompt.py,sha256=JPr6wvIu1ZpUtTa93WJxa3fbosswtIJqqOY5H8nE2XA,10586
@@ -131,6 +133,8 @@ janus/prompts/templates/basic_aggregation/human.txt,sha256=Aw2Jip8rYHoA_vYXJ3ve8
 janus/prompts/templates/basic_aggregation/system.txt,sha256=8QgUYtx51aPJk-e7kHLfXKPPp2Y1YYfBmZwoXG0l2GQ,126
 janus/prompts/templates/basic_refinement/human.txt,sha256=d_Yr8KKVD_xXpO4RzYKQzG_4T_Zce3qAiWl_roAF2H4,342
 janus/prompts/templates/basic_refinement/system.txt,sha256=odlLG_ZOqd9TyJJ6e4S-1b-fLusrxLO3pZBem7iR3hQ,115
+janus/prompts/templates/cyclic/human.txt,sha256=8LF07WXF4uVzNB77RQugrkgnYd7mObYg5-dBxydn2NA,597
+janus/prompts/templates/cyclic/system.txt,sha256=MLKpPIhg_q74K8V0MP1AnswT4nw9r-e_Qt66QYisE_w,209
 janus/prompts/templates/diagram/human.txt,sha256=P5WJd-_TzUMlaUjIZSH4o7pUCadmqWoY6GvZ-lv35hU,491
 janus/prompts/templates/diagram/system.txt,sha256=cGepMHpxI4PX9hTmH-mDsqKZDKxSqjKzMbbWpHOyUpE,121
 janus/prompts/templates/diagram_with_documentation/human.txt,sha256=_WeV70QDN3vS-4RVqSeri_vfxDmF_A-XGGG0GMAocIk,673
@@ -142,12 +146,14 @@ janus/prompts/templates/document_cloze/system.txt,sha256=w1SUmICn6zuO2MVw_CoYVkD
 janus/prompts/templates/document_cloze/variables.json,sha256=DB5N72JXk7AXKSI1kdoCbLHv2pbDJZmTWZkuWIq7G3Q,1647
 janus/prompts/templates/document_cloze/variables_asm.json,sha256=5wDJIG8adxbUGPj1_ol7H5Yh1qqDlQiXJOeLHgkaaa8,1065
 janus/prompts/templates/document_inline/human.txt,sha256=k-tfS4YitYUZNTP0lvcc5_m1ZfWopVNeSZyQR9nX4yw,311
-janus/prompts/templates/eval_prompts/incose/human.txt,sha256=LfEhRigC1ZJUKzBDQ5YOFjItS-kV_cxw_9V1_V0tzm4,3215
+janus/prompts/templates/eval_prompts/incose/human.txt,sha256=iWixpC3vZSQDqtC3e8N68SmxbJEWPb4DVz0gxRERZ20,3307
 janus/prompts/templates/eval_prompts/incose/system.txt,sha256=aXj9BsUsH2DFXrltgHl7xzBGvnCsh034oWyDHXVaA3c,96
 janus/prompts/templates/eval_prompts/incose/variables.json,sha256=c2gssz87ix-Sn5w5OL72TS22VE5T0Yd787L8qB0VW_w,3012
 janus/prompts/templates/eval_prompts/inline_comments/human.txt,sha256=6DUkmzLOr-VC4FzWALSeC2q0NI8hmRhoh8ZeTeh7CB8,2280
 janus/prompts/templates/eval_prompts/inline_comments/system.txt,sha256=VnKktVHYYMYrKroQpmG6EnykYO5qbosIvUFYZl14wsg,101
 janus/prompts/templates/eval_prompts/inline_comments/variables.json,sha256=dpRv25tcV2xeDwki5C1qTmkU_nZC-0yWe1RVFpqz2Sc,2099
+janus/prompts/templates/extract_variables/human.txt,sha256=EVqW6jAGsSA2ANgC8La_5Ij8VgHEt2gbwsjy1q4OYes,129
+janus/prompts/templates/extract_variables/system.txt,sha256=yH9S3nqiiDSWSoBKlS0PPM3c6s4Ck1zTNGnQQpHN4V0,120
 janus/prompts/templates/micromanaged_mumps_v1.0/human.txt,sha256=FCXlIlRYPnz8yFCFNIptlHjs5ZccoYO-xUay7VWph3s,1143
 janus/prompts/templates/micromanaged_mumps_v1.0/system.txt,sha256=S5M82T21RGqG9TLnKdzW3596GQDumPrXnvWIJJMjwLU,133
 janus/prompts/templates/micromanaged_mumps_v2.0/human.txt,sha256=aqVDRHzGBWzj1k-XhuNUcO5Yd4YCUdJbRJOJrbiw_nY,1433
@@ -203,8 +209,8 @@ janus/utils/enums.py,sha256=o26C6xIqYSiC2areAGSAB4alP_uHfpKxNn5TnlZzlTI,29656
 janus/utils/logger.py,sha256=vKofNjSvnXduvfkAWf1kkEES32tI7iI-bojfjIa3XoQ,2466
 janus/utils/pdf_docs_reader.py,sha256=beMKHdYrFwg0m_i7n0OTJrut3sf4rEWFd7P_80A76WY,5140
 janus/utils/progress.py,sha256=PIpcQec7SrhsfqB25LHj2CDDkfm9umZx90d9LZnAx6k,1469
-janus_llm-4.3.5.dist-info/LICENSE,sha256=_j0st0a-HB6MRbP3_BW3PUqpS16v54luyy-1zVyl8NU,10789
-janus_llm-4.3.5.dist-info/METADATA,sha256=IRLmrJ7U-Xb0Pota4K-u4esm6o6RQL8fSIE367sZdxA,4608
-janus_llm-4.3.5.dist-info/WHEEL,sha256=IYZQI976HJqqOpQU6PHkJ8fb3tMNBFjg-Cn-pwAbaFM,88
-janus_llm-4.3.5.dist-info/entry_points.txt,sha256=rzOrXUSS0SNN8I-fKV0-IBoYLTCMXnZfMtu4HetlCkU,43
-janus_llm-4.3.5.dist-info/RECORD,,
+janus_llm-4.5.4.dist-info/LICENSE,sha256=_j0st0a-HB6MRbP3_BW3PUqpS16v54luyy-1zVyl8NU,10789
+janus_llm-4.5.4.dist-info/METADATA,sha256=Pd0QN52fxzsTdlvdQ0HID-uwbIrsgcX6xnB577YSxnE,4695
+janus_llm-4.5.4.dist-info/WHEEL,sha256=XbeZDeTWKc1w7CSIyre5aMDU_-PohRwTQceYnisIYYY,88
+janus_llm-4.5.4.dist-info/entry_points.txt,sha256=rzOrXUSS0SNN8I-fKV0-IBoYLTCMXnZfMtu4HetlCkU,43
+janus_llm-4.5.4.dist-info/RECORD,,

{janus_llm-4.3.5.dist-info → janus_llm-4.5.4.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 2.0.1
+Generator: poetry-core 2.1.1
 Root-Is-Purelib: true
 Tag: py3-none-any

janus/metrics/_tests/test_llm.py

@@ -1,90 +0,0 @@
-import unittest
-from unittest.mock import patch
-
-import pytest
-
-from janus.llm.models_info import load_model
-from janus.metrics.llm_metrics import llm_evaluate_option, llm_evaluate_ref_option
-
-
-class TestLLMMetrics(unittest.TestCase):
-    def setUp(self):
-        self.bad_code = """
-        if __name__ == "__main__":
-            a1, a2, b3, b4 = 0, [1, 2000, "a"], 2, (1, 2)
-        for a in a2:
-            if b3:
-            elif not b3:
-                try:
-                    pass
-                except:
-                    raise ValueError
-            elif 1:
-                print(1)
-            else:
-                print(b4[0])
-                for (x, y) in range(a1, b3):
-                    for i in range(003300):
-                        for z in a2:
-                            printf(b4[2])
-        """
-        self.impressive_code = """
-        # This program prints out Hello, world!
-
-        print('Hello, world!')
-        """
-        self.impressive_code_reference = """
-        # An implementation of python Hello, world!
-
-        print("'Hello, world!")
-        """
-
-    @patch(".llm.models_info.load_model")
-    @patch("janus.metrics.llm_metrics.llm_evaluate")
-    @pytest.mark.llm_eval
-    def test_llm_self_eval_quality(self, mock_llm_evaluate, mock_load_model):
-        """Test that the quality llm self eval recognizes bad_code as bad code
-        (<5 on a scale of 1-10)"""
-        mock_llm_evaluate.return_value = 4  # return a value less than 5
-        mock_load_model.return_value = [None]  # return a dummy model
-
-        bad_code_quality = llm_evaluate_option(
-            self.bad_code,
-            self.bad_code,
-            metric="quality",
-            language="python",
-            llm=load_model("gpt-4o")[0],
-        )
-        self.assertLess(bad_code_quality, 5)
-
-        mock_llm_evaluate.return_value = 6  # return a value greater than 5
-        impressive_code_quality = llm_evaluate_option(
-            self.impressive_code,
-            self.impressive_code,
-            metric="quality",
-            language="python",
-            llm=load_model("gpt-4o")[0],
-        )
-        self.assertGreater(impressive_code_quality, 5)
-
-    @patch("janus.llm.models_info.load_model")
-    @patch("janus.metrics.llm_metrics.llm_evaluate")
-    @pytest.mark.llm_eval
-    def test_llm_self_eval_faithfulness(self, mock_llm_evaluate, mock_load_model):
-        """The two Hello, world! samples are more or less the same,
-        so the faithfulness score should be high"""
-        mock_llm_evaluate.return_value = 9  # return a high value
-        mock_load_model.return_value = [None]  # return a dummy model
-
-        faithfulness = llm_evaluate_ref_option(
-            self.impressive_code,
-            self.impressive_code_reference,
-            metric="faithfulness",
-            language="python",
-            llm=load_model("gpt-4o")[0],
-        )
-        self.assertGreater(faithfulness, 8)
-
-
-if __name__ == "__main__":
-    unittest.main()

janus/metrics/llm_metrics.py

@@ -1,202 +0,0 @@
-from pathlib import Path
-from typing import Any
-
-import click
-import typer
-from langchain_core.exceptions import OutputParserException
-from langchain_core.output_parsers import BaseOutputParser, JsonOutputParser
-from langchain_core.prompts import PromptTemplate
-from langchain_core.pydantic_v1 import BaseModel, Field
-from typing_extensions import Annotated
-
-from janus.metrics.metric import metric
-
-
-class LLMMetricOutput(BaseModel):
-    """The output of an LLM evaluation metric."""
-
-    thought: str = Field(
-        ...,
-        description=(
-            "The thought process that you took to reach your value determination."
-        ),
-    )
-    value: str | float | int = Field(
-        ..., description="The value of the metric described in the prompt."
-    )
-
-
-def load_prompt(path: Path, language: str, parser: BaseOutputParser) -> PromptTemplate:
-    """Load a default prompt from a file.
-
-    Arguments:
-        path: The path to the file.
-        language: The language of the prompt.
-        pydantic_model: The Pydantic model to use for parsing the output.
-
-    Returns:
-        The prompt text.
-    """
-    if not path.exists():
-        raise FileNotFoundError(f"File not found: {path}")
-    prompt = PromptTemplate.from_template(
-        path.read_text(),
-        template_format="f-string",
-        partial_variables={
-            "language": language,
-            "format_instructions": parser.get_format_instructions(),
-        },
-    )
-    return prompt
-
-
-def evaluate(
-    target: str,
-    language: str,
-    model: str,
-    prompt_path: Path,
-    reference: str | None = None,
-):
-    """Calculate the LLM self evaluation score.
-
-    Arguments:
-        target: The target text.
-        language: The language that the target code is written in.
-        prompt_path: The filepath of the prompt text
-        reference: The reference text.
-
-    Returns:
-        The LLM Evaluation score.
-    """
-    parser = JsonOutputParser(pydantic_object=LLMMetricOutput)
-    prompt = load_prompt(prompt_path, language, parser)
-    chain = prompt | model | parser
-    try:
-        output = (
-            chain.invoke(dict(target=target, reference=reference))
-            if reference
-            else chain.invoke(dict(target=target))
-        )
-        return output["value"]
-    except OutputParserException:
-        return False
-
-
-@metric(use_reference=False, name="llm", help="LLM self-evaluation on a target file")
-def llm_evaluate_option(
-    target: str,
-    metric: Annotated[
-        str,
-        typer.Option(
-            "--metric",
-            "-m",
-            help=("The pre-defined metric to use for evaluation."),
-            click_type=click.Choice(
-                [
-                    "quality",
-                    "clarity",
-                    "faithfulness",
-                    "completeness",
-                    "hallucination",
-                    "readability",
-                    "usefulness",
-                ]
-            ),
-        ),
-    ] = "quality",
-    prompt: Annotated[
-        str,
-        None,
-        typer.Option(
-            "--prompt",
-            "-P",
-            help=("A custom prompt in a .txt file to use for evaluation."),
-        ),
-    ] = None,
-    num_eval: Annotated[
-        int,
-        typer.Option(
-            "-n",
-            "--num-eval",
-            help="Number of times to run the evaluation",
-        ),
-    ] = 1,
-    **kwargs,
-) -> Any:
-    """CLI option to calculate the LLM self evaluation score.
-
-    Arguments:
-        target: The target text.
-        reference: The reference text.
-        metric: The pre-defined metric to use for evaluation.
-        prompt: The prompt text.
-
-    Returns:
-        The LLM Evaluation score.
-    """
-    prompt_path: Path = (
-        Path(prompt) if prompt else Path(__file__).parent / "prompts" / f"{metric}.txt"
-    )
-    if num_eval == 1:
-        return evaluate(target, kwargs["language"], kwargs["llm"], prompt_path)
-    else:
-        return [
-            evaluate(target, kwargs["language"], kwargs["llm"], prompt_path)
-            for _ in range(num_eval)
-        ]
-
-
-@metric(name="llm-ref", help="LLM self-evaluation on a target file and a reference file")
-def llm_evaluate_ref_option(
-    target: str,
-    reference: str,
-    metric: Annotated[
-        str,
-        typer.Option(
-            "--metric",
-            "-m",
-            help=("The pre-defined metric to use for evaluation."),
-            click_type=click.Choice(["faithfulness"]),
-        ),
-    ] = "faithfulness",
-    prompt: Annotated[
-        str,
-        None,
-        typer.Option(
-            "--prompt",
-            "-P",
-            help=("A custom prompt in a .txt file to use for evaluation."),
-        ),
-    ] = None,
-    num_eval: Annotated[
-        int,
-        typer.Option(
-            "-n",
-            "--num-eval",
-            help="Number of times to run evaluation for pair",
-        ),
-    ] = 1,
-    **kwargs,
-) -> Any:
-    """CLI option to calculate the LLM self evaluation score, for evaluations which
-    require a reference file (e.g. faithfulness)
-
-    Arguments:
-        target: The target text.
-        reference: The reference text.
-        metric: The pre-defined metric to use for evaluation.
-        prompt: The prompt text.
-
-    Returns:
-        The LLM Evaluation score.
-    """
-    prompt_path: Path = (
-        Path(prompt) if prompt else Path(__file__).parent / "prompts" / f"{metric}.txt"
-    )
-    if num_eval == 1:
-        return evaluate(target, kwargs["language"], kwargs["llm"], prompt_path, reference)
-    else:
-        return [
-            evaluate(target, kwargs["language"], kwargs["llm"], prompt_path, reference)
-            for _ in range(num_eval)
-        ]