isa-model 0.4.0__py3-none-any.whl → 0.4.3__py3-none-any.whl

isa_model-0.4.3.dist-info/RECORD

@@ -0,0 +1,193 @@
+isa_model/__init__.py,sha256=lYYKstKw33oavW6xS0-9cpsdYq-h0cfV_ZlGAwICRaU,868
+isa_model/client.py,sha256=7OUA6yi0G94I8U4GOFcoXvCjWxk2ds1-3CDCivJXA6M,67628
+isa_model/core/config.py,sha256=9OL8_EkBcnAH-RgyWUi3jblKo42m7K1JDeHa9C5CPL4,19519
+isa_model/core/dependencies.py,sha256=2ZgGDjtYitBEVy8H3UppQSb_BId3--f2kQw-Lm4Umh8,10050
+isa_model/core/pricing_manager.py,sha256=NWQLhNIzUDqS5_jBfVcJGrdOdRasFyifSNCliaIDvqU,17122
+isa_model/core/types.py,sha256=jdO_q0FDuzvWURXZtxMV1Zj1XgARX9kopTviWFuq_FU,8713
+isa_model/core/cache/redis_cache.py,sha256=J_A4OcVENsbc6RMOnXn6O-i320egM5hCQXTR7RlYz6s,14111
+isa_model/core/config/__init__.py,sha256=SLeHQtYGDHl64NDVyb3ECQXOKepGM8YNHEoM8CVEWus,350
+isa_model/core/config/config_manager.py,sha256=tF6EyNr_y6Jm0easV9aNHgBce4Ddamf0acaFlz7yToA,32289
+isa_model/core/database/__init__.py,sha256=E2lp9te05QgdQfMeUq702t_23fv4Y7be_P2QU60Yqzs,18
+isa_model/core/database/direct_db_client.py,sha256=jHp5AWyrXcYDRvrPvBRGH89FmPRAhgzL8MQsSt4zkTQ,4273
+isa_model/core/database/migration_manager.py,sha256=GxSJtngsbK8oA8kAKkquLQby_DdXLTwU795NGGHMH8c,21748
+isa_model/core/database/migrations.py,sha256=RpM1eqt7Chu736K0ij_42gKMYHg2HPR_qSt70xfJ_co,12626
+isa_model/core/database/supabase_client.py,sha256=waY0VQLy9VM6FMIoViDe5yAgNW78qJaI3Jb2ohTNj98,11124
+isa_model/core/discovery/__init__.py,sha256=U7YzSNqsyPYmT_TdMlLy9QMAotdfaFlDE-c9XgKk8-4,380
+isa_model/core/discovery/consul_discovery.py,sha256=UziTVGVbejh0zUvayhISkiRJ5KeFcxUkw8t4gTK0UVw,6631
+isa_model/core/logging/__init__.py,sha256=9PA5MJvn7y73aCUUqCgv5r2it2nNb38YXSG31oxNIDA,1213
+isa_model/core/logging/influx_logger.py,sha256=TsPnWeKgV6pl2cz9NoqM0OV9z9jI1_uVbn6nTblfM94,19483
+isa_model/core/logging/loki_logger.py,sha256=pFkKFK5ouKNa9dPehC_kV6af0urnAvzfvbYE5IFiwD0,4706
+isa_model/core/models/__init__.py,sha256=bDzyE0KHIJxxoN3q08pvW_hHBeHux2aMdeKY4GlDzmU,1286
+isa_model/core/models/config_models.py,sha256=Gy0oNndDsKVQ92Bz6aZp1JMqr4Z0jdoEJCCscIrpogI,22955
+isa_model/core/models/deployment_billing_tracker.py,sha256=hW2e3vUkASvCycYhBdrZcsEtBjYo3TLTVpfwfVkaXnQ,16406
+isa_model/core/models/model_billing_tracker.py,sha256=er35dsoKAGt8bjkQwO9f3MQ6U_NI6OIuhIn4PEOPEWU,17302
+isa_model/core/models/model_manager.py,sha256=vjFYWxmhRGUDlrHkwySjN5d0hfCx-VqBKiMhgTXjs8Y,17093
+isa_model/core/models/model_metadata.py,sha256=C6ubW12qmXAuqKmE_2BaO4HMB7WJqBkYDVXYCINsc-4,25148
+isa_model/core/models/model_repo.py,sha256=1018Qi8fMfgXtU8DKfWvf-0hBE16Q7wJIzmEZa7x6bw,19868
+isa_model/core/models/model_statistics_tracker.py,sha256=4KoKawwtEDAx8FV9ysmZS4nvRqZAgRSSIa-32f_Jhwk,10561
+isa_model/core/models/model_storage.py,sha256=gpW7R_wDQh0WUo4CYkrQen9GMKn8Z8ys5iGQenaMmCM,4473
+isa_model/core/models/model_version_manager.py,sha256=20BwNbCg1NlcmHmCxK_zMvpPmVFHg0B6ZCFnPLY6Yj8,37563
+isa_model/core/models/system_models.py,sha256=I52nTi0UVft8tkJdb2LZrJ_Qxax-JE00_YKqnSa-P4E,32525
+isa_model/core/repositories/__init__.py,sha256=RRERY7mWZxhSAZa4m6493l6sFl3CPlyL2bW6qJMEzD8,172
+isa_model/core/repositories/config_repository.py,sha256=QlL22r_bGEV6mHfmztEIY5Zw3wIFoiR5IQJyIj36wXU,37428
+isa_model/core/resilience/circuit_breaker.py,sha256=Ccoh3O31xVFJO2A0flnc9SI-sRqQ3sGKbwv3WbgJxBc,12435
+isa_model/core/security/secrets.py,sha256=kzRjpSiGwY9z47NUlurK29uY_uMsA5lqk8_6Ywu8Zvw,13319
+isa_model/core/services/__init__.py,sha256=TEE58Vk8JKIaQx8ELeAaWo-WPz0hjck9x-ZK7pbfiIE,422
+isa_model/core/services/intelligent_model_selector.py,sha256=PPUWiMcV8DkCPMHhnIlsBgksUY8hKB4SjlFDW1zhLYY,29205
+isa_model/core/storage/hf_storage.py,sha256=k271Rg5G7qUJAJ6VXQBTUHGU6y2NYBNWKVeBJm02DRo,14736
+isa_model/core/storage/local_storage.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+isa_model/deployment/__init__.py,sha256=Y3IUEOriJYVZ-3ZEamMs4n6_X0OwtD2eguwBas5zgtg,345
+isa_model/deployment/core/__init__.py,sha256=TRJ4tNjNFub_ObhZy61iZZpqC0CYsnv1HV1Qp_XWhVI,119
+isa_model/deployment/core/deployment_manager.py,sha256=In2e5EuXwVJfg6ENjigOrgQyy19DCWX5uuwSa--Czzc,58337
+isa_model/deployment/local/__init__.py,sha256=Ld1QbaDHIHnbW2IkSXVTZeDcxnmUXBa074uOSLRu5t0,904
+isa_model/deployment/local/config.py,sha256=Kft5EORBcsO2HVizD0ct6VFIIs9sVBN-CjRnOrcm00g,9246
+isa_model/deployment/local/gpu_gateway.py,sha256=be6d9eSWRufXvJH9GyklBWlXhOukITY1lnXTM6RPcQs,21954
+isa_model/deployment/local/health_checker.py,sha256=_u2vwiwEGCbFA6laUu1JX6GfE6prrOSHiy6PclimGys,16392
+isa_model/deployment/local/provider.py,sha256=6E1WfTUvI32aeEQs13TIyuy9xQmZqJeaJULfE2KLe4E,22763
+isa_model/deployment/local/tensorrt_service.py,sha256=f05BkJMw2NhiMp18xW1RwRED4bIjZ0gmUS5OgEAGnk0,23026
+isa_model/deployment/local/transformers_service.py,sha256=pdC3KppUzSVrWd-CKA8fXPC1uzy45S8FTtQj9odAWpM,23937
+isa_model/deployment/local/vllm_service.py,sha256=zVuBopgzG6ulSvHnRE8h_dLQQpNqTDwHbXo88IKXrwk,18849
+isa_model/deployment/modal/__init__.py,sha256=ZBcToGNtL6ztWY5pvqM1YMiL_F-S1xx9b-uZd8cuajc,380
+isa_model/deployment/modal/config.py,sha256=8XhBMIbx6oDTf-P9ipQ58xmBYDbNZekZ4gixorBDIpw,4267
+isa_model/deployment/modal/deployer.py,sha256=YNCtbO8FTVstz8OG6Kh8p3AM05dtbg5i73-JsuNy4KM,31961
+isa_model/deployment/modal/services/__init__.py,sha256=m9D6jZ-RH3fohn5pNDLEfFQWj18LDlq565I2t8tTIAk,61
+isa_model/deployment/modal/services/audio/__init__.py,sha256=YhBTWmI0k8onSU6K0MzW9NIS1d7uedPT_9U6G0Qmfio,41
+isa_model/deployment/modal/services/audio/isa_audio_chatTTS_service.py,sha256=w3s4hj78HedQ0g2X8_PJbXPBGcMmwnZeV1LHS_Auy_o,18637
+isa_model/deployment/modal/services/audio/isa_audio_fish_service.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+isa_model/deployment/modal/services/audio/isa_audio_openvoice_service.py,sha256=2OE_J5KTglEh7iVnTb-2_phghvQKkTD7OIsHZ9fKfZI,33515
+isa_model/deployment/modal/services/audio/isa_audio_service_v2.py,sha256=TMF-TXKcRsNT6vq6U-45PSvKfdJ-SBbpAD-lCC9x_zI,40832
+isa_model/deployment/modal/services/embedding/__init__.py,sha256=uwKfvNrVTO_AvRKlONGCVaXwmSIs-lDNfF2gef_Clb0,45
+isa_model/deployment/modal/services/embedding/isa_embed_rerank_service.py,sha256=K6TdCWD-Ko-vmKi03tVfpjZpX2Folv5EW79yPqJzT_U,10182
+isa_model/deployment/modal/services/llm/__init__.py,sha256=dDp1ekrBb6E1cMwpE4kMFswlIxfs5G0M_LuTLvCAtKk,39
+isa_model/deployment/modal/services/llm/isa_llm_service.py,sha256=-GVcBMRiKezT0oGkqirmwuKb0Oo2GsMrL-AFEwp5Ik8,14108
+isa_model/deployment/modal/services/video/__init__.py,sha256=IehlRWhB0X-IOY1-rGXugY-BzOLr1jhMPQTLAZZTj_c,41
+isa_model/deployment/modal/services/video/isa_video_hunyuan_service.py,sha256=slxEZxFFnFkOBlxdOdNu7JRXJMWwl-gaOUHFQr5stZ0,15208
+isa_model/deployment/modal/services/vision/__init__.py,sha256=JzkcYOTBIJ4vUUpZwwjYCpzyh1VtUOa-RSlymOzKdHU,42
+isa_model/deployment/modal/services/vision/isa_vision_ocr_service.py,sha256=1Y6s6mLRFLPhpItFLS61mbqGggR1UNd1rNtAluIzQrk,18501
+isa_model/deployment/modal/services/vision/isa_vision_qwen25_service.py,sha256=Ldy0VvO7CGiPGDmPXWQCbCLUZgCGg3aBqWOA66Lvt5I,26797
+isa_model/deployment/modal/services/vision/isa_vision_table_service.py,sha256=UhQinNRda0b11g3dYFjDCNaR0850IgCl1WtRghrFNu0,24827
+isa_model/deployment/modal/services/vision/isa_vision_ui_service.py,sha256=BwoMhJQiQe2vGFteTsbbeVsemJZszjce9ech39Z0cWQ,34296
+isa_model/deployment/modal/services/vision/isa_vision_ui_service_optimized.py,sha256=xy3IOEDifi2aMvJFB2_u4qfdD3YdXfgWW3_0z_BLNuo,25665
+isa_model/deployment/modal/services/vision/simple_auto_deploy_vision_service.py,sha256=rfXsv9mh_w5cXHVYxA4fBD5ppyNY4HplsH34xp4WpY8,9882
+isa_model/deployment/models/org-org-acme-corp-tenant-a-service-llm-20250825-225822/tenant-a-service_modal_service.py,sha256=3MHnvm6TFDycULcFaEdX95Rl0jY2VWYHDGzjDSJNCm0,1388
+isa_model/deployment/models/org-test-org-123-prefix-test-service-llm-20250825-225822/prefix-test-service_modal_service.py,sha256=IfmIal7OfSdbnGeyGy-zMee2WAf5zteXJ0zAZiCZxSQ,1400
+isa_model/deployment/models/test-llm-service-llm-20250825-204442/test-llm-service_modal_service.py,sha256=nQEhzFDU2dsAQkHApyeQpZHu0VLWtG3Ilhuv498wRLA,1388
+isa_model/deployment/models/test-monitoring-gpt2-llm-20250825-212906/test-monitoring-gpt2_modal_service.py,sha256=yx3xiXyzskiVjwdr54favQ48UYO3hXzt2bQM9iR_irM,1404
+isa_model/deployment/models/test-monitoring-gpt2-llm-20250825-213009/test-monitoring-gpt2_modal_service.py,sha256=fjPAVAtdcxOnEA252E4KPjTNkJq-_4UlG9Qj7eEF6tw,1404
+isa_model/deployment/storage/__init__.py,sha256=TPxs4prCYb2AJ9NqNk9nh3kc6EFDkAkDmrqxq1ERWzo,138
+isa_model/deployment/storage/deployment_repository.py,sha256=F6eFQjDXL4AAhw6F1hDMiU1rlnCL1zhZ_cMssVVEtHY,33168
+isa_model/deployment/triton/__init__.py,sha256=TrsBOxzGeESj_GrVWUd3jsScFUQ5Cd266NXvwRbuAJ8,330
+isa_model/deployment/triton/config.py,sha256=H7VemDvdLpREfSvD0DK86CXFg46l-eHnGf_vo8lOrH4,7319
+isa_model/deployment/triton/provider.py,sha256=ZtpgF2kaHGtPO2EuXQEHMtwobMW025sliogkBtqjbe0,17391
+isa_model/deployment/triton/configs/__init__.py,sha256=bxiam68sNO8eFutXKK9yaaKS-5MulIuhgusN_mdwz2A,50
+isa_model/deployment/triton/scripts/__init__.py,sha256=fE3HxpLG9_wvXWIN27Tj-B9IEvtp_aZ0bUS3GzfRHqY,31
+isa_model/deployment/triton/templates/__init__.py,sha256=rWtBQzM6kpC2yXcc3yCjrnWSj7W3jxbfXXZe2Rr1GL8,33
+isa_model/inference/__init__.py,sha256=gmrJV1cdSyDpBZdfm8r0kPZsbnqogth0rXf_wT5fIFY,1381
+isa_model/inference/ai_factory.py,sha256=ztTllV58ovfuO208aYQA_yT7iq88F7wdiPZr1TvW1_I,28716
+isa_model/inference/base.py,sha256=qwOddnSGI0GUdD6qIdGBPQpkW7UjU3Y-zaZvu70B4WA,1278
+isa_model/inference/legacy_services/__init__.py,sha256=H0RTKKE3UOqmpjc3S3GfysbhZZl6CnZd9_I38KTXg1E,563
+isa_model/inference/legacy_services/model_evaluation.py,sha256=GbhcNM8uO0AnI59yuCYaTqDEdmh0pS4YxJVgJGL8Vjs,27964
+isa_model/inference/legacy_services/model_service.py,sha256=9xEaLJWW1B2lLFL5-eP_uPFpfg8iYnqrAphpJnMTn2A,24751
+isa_model/inference/legacy_services/model_serving.py,sha256=XQ7j6B02MsjUWKeeSVovKg0kljwMCLbRLeCuckmjtM8,28255
+isa_model/inference/legacy_services/model_training.py,sha256=g0rfzSKGXzoJbNgEh8wDJlfdhHxh6-jXN0fv_B3-1C8,24036
+isa_model/inference/models/__init__.py,sha256=FJ6goyHRf4RCnqbq75qAigL0FMKXulDOns-ebHWCgP8,579
+isa_model/inference/models/inference_config.py,sha256=1ITGWOtQ3cVyucQq9Rih-Ab5uqaAGf31UfCYyJMY_DI,19529
+isa_model/inference/models/inference_record.py,sha256=oHidCa9-lHSonOSoc24tAbrsSPBgm3bb8-cqzWOqzcU,24840
+isa_model/inference/models/performance_models.py,sha256=KZWC8fEslhTohL2y-nz8S39P9RZ9SgJ6piQ9pMXh04E,26434
+isa_model/inference/repositories/__init__.py,sha256=SYTQX1E5L6zTuo_p_KnDjYefoCKw4p1m4pW_FDb_sgM,191
+isa_model/inference/repositories/inference_repository.py,sha256=QnfSzkcLQ5CPcABTmSYBRAv_5SVk0ayjVW6B1Q0SKaQ,31718
+isa_model/inference/services/__init__.py,sha256=yfLz0YGl8ixk6LfTRL6cRTvZMb9F_Pv1QRgGyNc9xYM,386
+isa_model/inference/services/base_service.py,sha256=NJIvq7YpGw55ah-axDR2hcu40B2gm6L_WYXyfX0rSaE,5816
+isa_model/inference/services/custom_model_manager.py,sha256=HUHSDOWArJYMfdvaI-gfCJkVRVFdftScOw7BgS-h3zo,10829
+isa_model/inference/services/audio/__init__.py,sha256=Hgtk3j5H4U3YxNlfG8UaU2eUNOWgrpSA8LN_tKEFWMk,616
+isa_model/inference/services/audio/base_realtime_service.py,sha256=hSP89_hnzLBnmBvFOQlU_tW8UT2QKWKVR9Z7fwsVPa8,8125
+isa_model/inference/services/audio/base_stt_service.py,sha256=qahYTLpf8gruvhEtS5bWDXPiYbgxXF3nYnqTq3Ckc0E,13361
+isa_model/inference/services/audio/base_tts_service.py,sha256=PgctcV98Pe9I2kSjScsm8epRwdaEU-vAGCIfdd2P8us,6924
+isa_model/inference/services/audio/isa_tts_service.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+isa_model/inference/services/audio/openai_realtime_service.py,sha256=vo4ow8CULZJXz4nSepMTq7_uKufWvRmcoezhmX2Q16s,22101
+isa_model/inference/services/audio/openai_stt_service.py,sha256=2UBBrRP8PXYTlDz9gEh4_mOqTSIdCewG8Ptu9aT2nCo,13476
+isa_model/inference/services/audio/openai_tts_service.py,sha256=C4vIRvCKoySs4-zBEteI_DZYZsATS84W_ZUwbxjJjpA,8253
+isa_model/inference/services/audio/replicate_tts_service.py,sha256=kCG_bBNgW7GQwt5-ZdwPSqsMiTV54-FhSowFwNWGvg0,10292
+isa_model/inference/services/embedding/__init__.py,sha256=xeWeq3jighDBCUzgveTiH11VLkkhk-J6z5cq9sf1mEk,311
+isa_model/inference/services/embedding/base_embed_service.py,sha256=V57nDU_VzWXjw3dqyaTXBr3ntxT2VI1my6uSAX-vvxY,10382
+isa_model/inference/services/embedding/isa_embed_service.py,sha256=AQ3yuGas64SRW8jlB0rvXhq2cyD5NMlCekodPCuN8dw,11242
+isa_model/inference/services/embedding/ollama_embed_service.py,sha256=7OZMMrDO4eePNJXSjNB5E4j0rtX0HVq3RgNSzzqU1nA,7291
+isa_model/inference/services/embedding/openai_embed_service.py,sha256=CaoNtepIreMA0wo5i0lUgJHUjVp4vdHQ59eT_gan3s4,8321
+isa_model/inference/services/embedding/resilient_embed_service.py,sha256=26HPaWmVKQ_fPClTNew1VZeAX5vy4ncKxp1HR04yAYw,11735
+isa_model/inference/services/embedding/helpers/text_splitter.py,sha256=6AbvcQ7H6MS54B9d9T1XBGg4GhvmKfZqp00lKp9pF-U,1635
+isa_model/inference/services/embedding/tests/test_embedding.py,sha256=_Syrgt2sYCS8oNCqaJMuzck_FRqeSx0Nnk9B1j3OJBk,10200
+isa_model/inference/services/img/__init__.py,sha256=moVvATbOEEqzKRtu2A9E7eBzlrkbr5oY1bGyH_3PebY,577
+isa_model/inference/services/img/base_image_gen_service.py,sha256=3BYoUo9ASw02ZPl2T9Pwvu4uVD-GOZIFEaGsrnuKCrM,8101
+isa_model/inference/services/img/replicate_image_gen_service.py,sha256=mspkdRh_snMUPQxRccpfzcAXO3TAxZsNzei0c45G7YA,6447
+isa_model/inference/services/img/services/replicate_face_swap.py,sha256=Q6SiWJN9eNvD1nv4kWXnvvPnm9A1DLb7Gsb_vwUfUJw,7385
+isa_model/inference/services/img/services/replicate_flux.py,sha256=BUIkuBUMZCH5ChvbIhmJ_1pJVNo0CjY7q7hgvsaFJO0,8008
+isa_model/inference/services/img/services/replicate_flux_kontext.py,sha256=3DEwruobN7JL6-3LNMOJVOtorjlqV7ykD2ul4NTQ9Fs,7786
+isa_model/inference/services/img/services/replicate_sticker_maker.py,sha256=9D_IISOpFfC2MWlP1BFohuIwHcI1H_b95zQU52Nl-Mw,8528
+isa_model/inference/services/img/tests/test_img_client.py,sha256=r6lYybP_ty3A55LoaE_GRuXvXSh35KXOVbODGskLza0,11313
+isa_model/inference/services/llm/__init__.py,sha256=aiNdB692nopCy8QaopVDB0e-J7mg22LrRzk4ytlu2iQ,769
+isa_model/inference/services/llm/base_llm_service.py,sha256=CUw24rMytVXAUcberTzogKRLwYZiYifyg-kcNfHiHkg,36402
+isa_model/inference/services/llm/cerebras_llm_service.py,sha256=8BU9I7HHO481nn7ddsiP4nl2ItYTCQJzJyaIArKA0ZA,25126
+isa_model/inference/services/llm/huggingface_llm_service.py,sha256=mWnOGh3OsRyaL002Ax71Mb7oXp254VDDdP0QiQ-p9Yk,22733
+isa_model/inference/services/llm/local_llm_service.py,sha256=_ILRD-oKcolf972aXe3zPS_tBu8SD-xH_Iw29alpkHM,27606
+isa_model/inference/services/llm/ollama_llm_service.py,sha256=78VNSspzlQrXDqAxUR52jLGIKnBw4e_4LT2unAFMiTk,17967
+isa_model/inference/services/llm/openai_llm_service.py,sha256=BpYugS2Vsrc-SS69cnW2VqFv4JXMbgglXvvbNgUZNZY,43874
+isa_model/inference/services/llm/yyds_llm_service.py,sha256=ZHl2ukcDVkwYahF4OV5etTvJKa9Ni6O1TkJp75pQWaA,12495
+isa_model/inference/services/llm/helpers/llm_adapter.py,sha256=7PrpiKvZaMfI9U6wabfTegwDMKcGDsv6I_lqnzcsE-o,24392
+isa_model/inference/services/llm/helpers/llm_prompts.py,sha256=qGcG5hiBcnuq3IrcpNvshpWR1TqUrkdtf2Il__xeBoo,21661
+isa_model/inference/services/llm/helpers/llm_utils.py,sha256=x2-wbij95bWgrZpJyXah9uMhEHKYAznChYRldT0VVno,22776
+isa_model/inference/services/ml/base_ml_service.py,sha256=mLBA6ENowa3KVzNqHyhWxf_Pr-cJJj84lDE4TniPzYI,2894
+isa_model/inference/services/ml/sklearn_ml_service.py,sha256=Lf9JrwvI25lca7JBbjB_e66eAUtXFbwxZ3Hs13dVGkA,5512
+isa_model/inference/services/vision/__init__.py,sha256=1GO2NoC7p8IJ92mI6fGcPaN4MeFzLhdNdNlAnFYpzpE,1839
+isa_model/inference/services/vision/base_vision_service.py,sha256=mjrfcUT01HBi0k1qeIL3CkpkvQIuL_jar-N03W8sMV8,10531
+isa_model/inference/services/vision/blip_vision_service.py,sha256=tmGCznQ9qBsidLV_mnKEtvpSUPvBUbwJdwviKYXrrkA,12020
+isa_model/inference/services/vision/isa_vision_service.py,sha256=OPuIZmG_lYOgajGfrQj4uLzVk5Y4H0PkeSNViIiL1O0,22960
+isa_model/inference/services/vision/openai_vision_service.py,sha256=LeD910WWyJd6QiJncSM3x_Whj-a32Vr1_2FG4gfjtc4,10179
+isa_model/inference/services/vision/replicate_vision_service.py,sha256=smRkSCTwk5mvyKVnvyplqPNuVYjRZngVBWxTCbFmrxA,20679
+isa_model/inference/services/vision/vgg16_vision_service.py,sha256=5w9r3vXQz5EAdXFPawtsuWzaNlhFA2N0xcJxSJcudQI,9382
+isa_model/inference/services/vision/disabled/isA_vision_service.py,sha256=VYa8VJtxDB9KdnfNW0GPEP_TPker4pHp33gLD_TnpaM,18336
+isa_model/inference/services/vision/helpers/image_utils.py,sha256=BYEFnOu2MBRJrJmKdALfFy5CTKpI4Co9PTVCxJvdFqc,11388
+isa_model/inference/services/vision/helpers/vision_prompts.py,sha256=WbzOYu-Z2-8Xn9dcvuPRTA7VTy23_uoMRRGO4t0wZ8Q,12098
+isa_model/inference/services/vision/tests/test_ocr_client.py,sha256=IY2KbHuIf1FmKFrUO9HrmKtgyT9achylwKykOIFLR8E,11250
+isa_model/inference/utils/conversion/bge_rerank_convert.py,sha256=1dvtxe5-PPCe2Au6SO8F2XaD-xdIoeA4zDTcid2L9FU,2691
+isa_model/inference/utils/conversion/onnx_converter.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+isa_model/inference/utils/conversion/torch_converter.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+isa_model/serving/__init__.py,sha256=LTO0Adbvm7A-bgQqtuOQSoHvdu9OH3OrEjYgQanuHgI,429
+isa_model/serving/modal_proxy_server.py,sha256=U8AJMF4ewtTGHjmbLb6ezR3NCT6d0APBtFuKVxVkRu4,7481
+isa_model/serving/api/__init__.py,sha256=wgWD69eqV37fFTLxhz8b0rOn_34P7SZHoWw2sufWjk4,162
+isa_model/serving/api/cache_manager.py,sha256=pBA9-4OUrHlyqYGtNbJSfZrDYPfEs2DV1Cx1qI0pM6U,8120
+isa_model/serving/api/error_handlers.py,sha256=UigiYCu7O59Mp-GkB3grzMgAz5rl9ClgK81DyEzX6ZU,10869
+isa_model/serving/api/fastapi_server.py,sha256=huSO9ZMuFirr5LhQO__mfM0tq1qKik11Wid9Qzk6T-Y,12367
+isa_model/serving/api/startup.py,sha256=iZqRnkgBFvuMYkueeVxKheZZ13Hy5xoaeenX2udrPW8,12944
+isa_model/serving/api/dependencies/__init__.py,sha256=e9ho7V27vnK73k2R7uRqVFzJ9hOHOsEydSz5mOAQbQU,21
+isa_model/serving/api/dependencies/auth.py,sha256=6G46JMx35O_9PWhc66ptA67BTH3fb9ASgdOW-dKfK0g,6149
+isa_model/serving/api/dependencies/database.py,sha256=fh8nrLNuD2ATVHnaMOxGD8ueR2g1f54rgflM1ISqcWg,4145
+isa_model/serving/api/middleware/__init__.py,sha256=iCKUYECf0bjNGXgV91K03hb8Dnp0Jc_wnUL897Rd0sg,163
+isa_model/serving/api/middleware/auth.py,sha256=WRoRrsDTlf4FDa7E8PnNhY5qfhUn76Be3ZMOPdi3FMk,11313
+isa_model/serving/api/middleware/request_logger.py,sha256=d48n6tp1pqZ7HFWFl8jg6er24ugWkWkMOc1y80aqPU8,2938
+isa_model/serving/api/middleware/security.py,sha256=YBzP3BZtEM1-PLSvVEuyTIxwGJqtw0IioRFWPUSu8FA,10233
+isa_model/serving/api/middleware/tenant_context.py,sha256=uf2Lla2aov-vIOXCIukBURn90GJ3G484tbqj993NktI,16008
+isa_model/serving/api/routes/__init__.py,sha256=RIaG9OPg0AjAIVbtMzwnqGyNU-tuQXbdvFcYOt4b_Do,84
+isa_model/serving/api/routes/analytics.py,sha256=qUVo1SV-wNJZPyvVx_w80gL6JYuiL3DbyEahEZGJIVU,17655
+isa_model/serving/api/routes/config.py,sha256=ER2PiKExoctMLkxs9ZxihGB0rEiczgU2Zt-FxpzMPsY,22453
+isa_model/serving/api/routes/deployment_billing.py,sha256=-9Ut6FIexwXbL_wT6oG-6yRxJLvCTXMBThiJn3av1B0,12350
+isa_model/serving/api/routes/deployments.py,sha256=DQHCePARLy1xht7nmeGlfomdUhWDqBzeAwReSI0arCc,17536
+isa_model/serving/api/routes/gpu_gateway.py,sha256=cTZmOApxinMqSQe1W9nglx3UduUnC-wRJ311bEajSV0,15512
+isa_model/serving/api/routes/health.py,sha256=dqmTLF_x0AvEdXHPYd9mf4mqUN-Z5oziNW_7yMI735s,2974
+isa_model/serving/api/routes/inference_monitoring.py,sha256=yXLQApZv5kDeTQjQAduKyv30k36AGl7tQ9ifG-wn21I,18799
+isa_model/serving/api/routes/llm.py,sha256=5ZVxWugff0i6VBKz_Nv5CqacMZJsPZEKyoSB6XDrW34,385
+isa_model/serving/api/routes/local_deployments.py,sha256=LbAiRcozooyhckg4joQXCWjpX2Au8Wt-MMq-GLZHul0,16289
+isa_model/serving/api/routes/logs.py,sha256=9t8cft3fprpQHHCj8UNxvcHmvOiELxbu7WXoWe8JLPw,14238
+isa_model/serving/api/routes/settings.py,sha256=Xj_uXnRxmHpgSxUfztvrwE2yjWtlWQElE2CizmeeVds,20905
+isa_model/serving/api/routes/tenants.py,sha256=7gU7xpEjYuDeCunWWeY6BIwuEw-t3_ctqYDU5Sv3GBI,21000
+isa_model/serving/api/routes/ui_analysis.py,sha256=-WxLaRKQNHnRh4okB85cWA4blTegpEPZtzHTsF3yeeU,6848
+isa_model/serving/api/routes/unified.py,sha256=rKCHKU4accmnE2jdZw-ZVSN8hDh8vB0a1Q-8U35faQM,44294
+isa_model/serving/api/routes/vision.py,sha256=U9jxssQYe6igtayUW0C2fcYwqmLRIE15__X-5Ru9J4c,396
+isa_model/serving/api/routes/webhooks.py,sha256=kspHgX8PIZ5L6S0klnV0XtGoE9BiTfYTMMx7Qsuf6CY,16219
+isa_model/serving/api/schemas/__init__.py,sha256=Tu_hzxoKW1ZHpww3-5ER4A2hNuDByZ0rAfrgaJ7Bs-M,275
+isa_model/serving/api/schemas/common.py,sha256=HVaAS7wlvqrwC1gMZ2Cvo0vzHB053x2uOTAwUoY2vsE,696
+isa_model/serving/api/schemas/ui_analysis.py,sha256=IpOcIvmUeXN1UtZsbGozMfV1vvz7AVF2PVXjjxYl_0k,4089
+isa_model/utils/gpu_utils.py,sha256=HbMvJzSsOCcjOJluUrszAJ58dC8LPnyA_nQn9s_1I6c,11730
+isa_model-0.4.3.dist-info/METADATA,sha256=2xHn4pAvo10QKBDQK34v0-acBWGBUZRR6ZUZa-xq7BU,15090
+isa_model-0.4.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+isa_model-0.4.3.dist-info/top_level.txt,sha256=eHSy_Xb3kNkh2kK11mi1mZh0Wz91AQ5b8k2KFYO-rE8,10
+isa_model-0.4.3.dist-info/RECORD,,

isa_model/deployment/cloud/__init__.py

@@ -1,9 +0,0 @@
-"""
-Cloud Deployment Module
-
-Support for various cloud platforms
-"""
-
-from .modal import ModalDeployment
-
-__all__ = ["ModalDeployment"]

isa_model/deployment/cloud/modal/__init__.py

@@ -1,10 +0,0 @@
-"""
-Modal Deployment Module
-
-Modal.com cloud deployment for ISA Model services
-"""
-
-from .ui_analysis_service import UIAnalysisService as UIAnalysisModalService
-from .deployment_manager import ModalDeployment
-
-__all__ = ["UIAnalysisModalService", "ModalDeployment"]

isa_model/deployment/core/deployment_config.py

@@ -1,356 +0,0 @@
-"""
-Deployment Configuration Classes
-
-Defines configuration classes for different deployment scenarios including
-RunPod serverless, Triton inference server, and TensorRT-LLM backend.
-"""
-
-from dataclasses import dataclass, field
-from typing import Optional, Dict, Any, List
-from enum import Enum
-from pathlib import Path
-
-
-class DeploymentProvider(str, Enum):
-    """Deployment providers"""
-    RUNPOD_SERVERLESS = "runpod_serverless"
-    RUNPOD_PODS = "runpod_pods"
-    AWS_LAMBDA = "aws_lambda"
-    GOOGLE_CLOUD_RUN = "google_cloud_run"
-    AZURE_CONTAINER_INSTANCES = "azure_container_instances"
-    LOCAL = "local"
-
-
-class InferenceEngine(str, Enum):
-    """Inference engines"""
-    TRITON = "triton"
-    VLLM = "vllm"
-    TENSORRT_LLM = "tensorrt_llm"
-    HUGGINGFACE = "huggingface"
-    ONNX = "onnx"
-    TORCHSCRIPT = "torchscript"
-
-
-class ModelFormat(str, Enum):
-    """Model formats for deployment"""
-    HUGGINGFACE = "huggingface"
-    TENSORRT = "tensorrt"
-    ONNX = "onnx"
-    TORCHSCRIPT = "torchscript"
-    SAFETENSORS = "safetensors"
-
-
-@dataclass
-class TritonConfig:
-    """Configuration for Triton Inference Server"""
-    
-    # Model repository configuration
-    model_repository: str = "/models"
-    model_name: str = "model"
-    model_version: str = "1"
-    
-    # Backend configuration
-    backend: str = "tensorrtllm"  # tensorrtllm, python, onnxruntime
-    max_batch_size: int = 8
-    max_sequence_length: int = 2048
-    
-    # TensorRT-LLM specific
-    tensorrt_llm_model_dir: str = "/models/tensorrt_llm"
-    engine_dir: str = "/models/engines"
-    tokenizer_dir: str = "/models/tokenizer"
-    
-    # Performance settings
-    instance_group_count: int = 1
-    instance_group_kind: str = "KIND_GPU"  # KIND_GPU, KIND_CPU
-    
-    # Memory settings
-    optimization_level: str = "OPTIMIZATION_LEVEL_ENABLED"
-    enable_pinned_input: bool = True
-    enable_pinned_output: bool = True
-    
-    def to_dict(self) -> Dict[str, Any]:
-        """Convert to dictionary"""
-        return self.__dict__.copy()
-
-
-@dataclass
-class RunPodServerlessConfig:
-    """Configuration for RunPod Serverless deployment"""
-    
-    # RunPod settings
-    api_key: str
-    endpoint_id: Optional[str] = None
-    template_id: Optional[str] = None
-    
-    # Container configuration
-    container_image: str = "runpod/pytorch:2.1.0-py3.10-cuda11.8.0-devel-ubuntu22.04"
-    container_disk_in_gb: int = 20
-    
-    # GPU configuration
-    gpu_type: str = "NVIDIA RTX A6000"
-    gpu_count: int = 1
-    
-    # Scaling configuration
-    min_workers: int = 0
-    max_workers: int = 3
-    idle_timeout: int = 5  # seconds
-    
-    # Network configuration
-    network_volume_id: Optional[str] = None
-    
-    # Environment variables
-    env_vars: Dict[str, str] = field(default_factory=dict)
-    
-    def to_dict(self) -> Dict[str, Any]:
-        """Convert to dictionary"""
-        return self.__dict__.copy()
-
-
-@dataclass
-class ModelConfig:
-    """Configuration for model deployment"""
-    
-    # Model identification
-    model_id: str
-    model_name: str
-    model_version: str = "1.0.0"
-    
-    # Model source
-    source_type: str = "huggingface"  # huggingface, local, s3, gcs
-    source_path: str = ""
-    
-    # Model format and engine
-    model_format: ModelFormat = ModelFormat.HUGGINGFACE
-    inference_engine: InferenceEngine = InferenceEngine.TRITON
-    
-    # Model metadata
-    model_type: str = "llm"  # llm, embedding, vision, audio
-    capabilities: List[str] = field(default_factory=lambda: ["text_generation"])
-    
-    # Performance configuration
-    max_batch_size: int = 8
-    max_sequence_length: int = 2048
-    dtype: str = "float16"  # float32, float16, int8, int4
-    
-    # Optimization settings
-    use_tensorrt: bool = True
-    use_quantization: bool = False
-    quantization_method: str = "int8"  # int8, int4, awq, gptq
-    
-    def to_dict(self) -> Dict[str, Any]:
-        """Convert to dictionary"""
-        return self.__dict__.copy()
-
-
-@dataclass
-class DeploymentConfig:
-    """Main deployment configuration"""
-    
-    # Deployment identification
-    deployment_id: str
-    deployment_name: str
-    description: Optional[str] = None
-    
-    # Provider and engine configuration
-    provider: DeploymentProvider = DeploymentProvider.RUNPOD_SERVERLESS
-    inference_engine: InferenceEngine = InferenceEngine.TRITON
-    
-    # Model configuration
-    model_config: ModelConfig = None
-    
-    # Provider-specific configurations
-    runpod_config: Optional[RunPodServerlessConfig] = None
-    triton_config: Optional[TritonConfig] = None
-    
-    # Health check configuration
-    health_check_path: str = "/health"
-    health_check_timeout: int = 30
-    
-    # Monitoring configuration
-    enable_logging: bool = True
-    log_level: str = "INFO"
-    enable_metrics: bool = True
-    
-    # Networking
-    custom_domain: Optional[str] = None
-    allowed_origins: List[str] = field(default_factory=lambda: ["*"])
-    
-    # Additional settings
-    extra_config: Dict[str, Any] = field(default_factory=dict)
-    
-    def __post_init__(self):
-        """Validate configuration after initialization"""
-        if not self.deployment_id:
-            raise ValueError("deployment_id is required")
-        
-        if not self.deployment_name:
-            raise ValueError("deployment_name is required")
-        
-        if not self.model_config:
-            raise ValueError("model_config is required")
-        
-        # Set default provider configs if not provided
-        if self.provider == DeploymentProvider.RUNPOD_SERVERLESS and not self.runpod_config:
-            self.runpod_config = RunPodServerlessConfig(api_key="")
-        
-        if self.inference_engine == InferenceEngine.TRITON and not self.triton_config:
-            self.triton_config = TritonConfig()
-    
-    def to_dict(self) -> Dict[str, Any]:
-        """Convert config to dictionary"""
-        config_dict = {}
-        
-        for key, value in self.__dict__.items():
-            if key in ['model_config', 'runpod_config', 'triton_config']:
-                if value is not None:
-                    config_dict[key] = value.to_dict()
-                else:
-                    config_dict[key] = None
-            elif isinstance(value, Enum):
-                config_dict[key] = value.value
-            else:
-                config_dict[key] = value
-        
-        return config_dict
-    
-    @classmethod
-    def from_dict(cls, config_dict: Dict[str, Any]) -> 'DeploymentConfig':
-        """Create config from dictionary"""
-        # Handle nested configs
-        if 'model_config' in config_dict and config_dict['model_config'] is not None:
-            config_dict['model_config'] = ModelConfig(**config_dict['model_config'])
-        
-        if 'runpod_config' in config_dict and config_dict['runpod_config'] is not None:
-            config_dict['runpod_config'] = RunPodServerlessConfig(**config_dict['runpod_config'])
-        
-        if 'triton_config' in config_dict and config_dict['triton_config'] is not None:
-            config_dict['triton_config'] = TritonConfig(**config_dict['triton_config'])
-        
-        # Handle enums
-        if 'provider' in config_dict:
-            config_dict['provider'] = DeploymentProvider(config_dict['provider'])
-        
-        if 'inference_engine' in config_dict:
-            config_dict['inference_engine'] = InferenceEngine(config_dict['inference_engine'])
-        
-        return cls(**config_dict)
-
-
-# Predefined configurations for common deployment scenarios
-
-def create_gemma_runpod_triton_config(
-    model_id: str,
-    runpod_api_key: str,
-    model_source_path: str = "xenobordom/gemma-4b-alpaca-v1"
-) -> DeploymentConfig:
-    """
-    Create a deployment configuration for Gemma model on RunPod with Triton + TensorRT-LLM.
-    
-    Args:
-        model_id: Unique identifier for the deployment
-        runpod_api_key: RunPod API key
-        model_source_path: HuggingFace model path or local path
-        
-    Returns:
-        DeploymentConfig for Gemma deployment
-    """
-    model_config = ModelConfig(
-        model_id=model_id,
-        model_name="gemma-4b-alpaca",
-        source_type="huggingface",
-        source_path=model_source_path,
-        model_format=ModelFormat.HUGGINGFACE,
-        inference_engine=InferenceEngine.TRITON,
-        model_type="llm",
-        capabilities=["text_generation", "chat"],
-        max_batch_size=8,
-        max_sequence_length=2048,
-        dtype="float16",
-        use_tensorrt=True
-    )
-    
-    runpod_config = RunPodServerlessConfig(
-        api_key=runpod_api_key,
-        container_image="nvcr.io/nvidia/tritonserver:23.10-trtllm-python-py3",
-        container_disk_in_gb=30,
-        gpu_type="NVIDIA RTX A6000",
-        gpu_count=1,
-        min_workers=0,
-        max_workers=3,
-        idle_timeout=5,
-        env_vars={
-            "TRITON_MODEL_REPOSITORY": "/models",
-            "CUDA_VISIBLE_DEVICES": "0"
-        }
-    )
-    
-    triton_config = TritonConfig(
-        model_repository="/models",
-        model_name="gemma-4b-alpaca",
-        backend="tensorrtllm",
-        max_batch_size=8,
-        max_sequence_length=2048,
-        tensorrt_llm_model_dir="/models/tensorrt_llm",
-        engine_dir="/models/engines",
-        tokenizer_dir="/models/tokenizer"
-    )
-    
-    return DeploymentConfig(
-        deployment_id=f"gemma-deployment-{model_id}",
-        deployment_name=f"Gemma 4B Alpaca - {model_id}",
-        description="Gemma 4B model fine-tuned on Alpaca dataset, deployed with Triton + TensorRT-LLM",
-        provider=DeploymentProvider.RUNPOD_SERVERLESS,
-        inference_engine=InferenceEngine.TRITON,
-        model_config=model_config,
-        runpod_config=runpod_config,
-        triton_config=triton_config
-    )
-
-
-def create_local_triton_config(
-    model_id: str,
-    model_source_path: str,
-    triton_model_repository: str = "./models/triton"
-) -> DeploymentConfig:
-    """
-    Create a deployment configuration for local Triton deployment.
-    
-    Args:
-        model_id: Unique identifier for the deployment
-        model_source_path: Path to the model
-        triton_model_repository: Path to Triton model repository
-        
-    Returns:
-        DeploymentConfig for local deployment
-    """
-    model_config = ModelConfig(
-        model_id=model_id,
-        model_name=f"local-model-{model_id}",
-        source_type="local",
-        source_path=model_source_path,
-        model_format=ModelFormat.HUGGINGFACE,
-        inference_engine=InferenceEngine.TRITON,
-        model_type="llm",
-        capabilities=["text_generation"],
-        max_batch_size=4,
-        max_sequence_length=1024,
-        dtype="float16"
-    )
-    
-    triton_config = TritonConfig(
-        model_repository=triton_model_repository,
-        model_name=f"local-model-{model_id}",
-        backend="python",  # Use Python backend for local development
-        max_batch_size=4,
-        max_sequence_length=1024
-    )
-    
-    return DeploymentConfig(
-        deployment_id=f"local-deployment-{model_id}",
-        deployment_name=f"Local Model - {model_id}",
-        description="Local model deployment for development and testing",
-        provider=DeploymentProvider.LOCAL,
-        inference_engine=InferenceEngine.TRITON,
-        model_config=model_config,
-        triton_config=triton_config
-    )