isa-model 0.3.4__py3-none-any.whl → 0.3.6__py3-none-any.whl

isa_model/serving/api/schemas/ui_analysis.py

@@ -0,0 +1,78 @@
+"""
+UI Analysis API Schemas
+
+Pydantic models for UI analysis endpoints
+"""
+
+from pydantic import BaseModel, Field
+from typing import List, Dict, Any, Optional
+import time
+
+class UIElement(BaseModel):
+    """UI element detection result"""
+    id: str = Field(..., description="Unique element identifier")
+    type: str = Field(..., description="Element type (textbox, button, etc.)")
+    content: str = Field(..., description="Element text content or description")
+    center: List[int] = Field(..., description="Center coordinates [x, y]")
+    bbox: List[int] = Field(..., description="Bounding box [x1, y1, x2, y2]")
+    confidence: float = Field(..., description="Detection confidence score")
+    interactable: bool = Field(True, description="Whether element is interactable")
+
+class ActionStep(BaseModel):
+    """Single action step in automation plan"""
+    step: int = Field(..., description="Step number")
+    action: str = Field(..., description="Action type (click, type, scroll)")
+    target_coordinates: List[int] = Field(..., description="Target coordinates [x, y]")
+    actual_coordinates: List[int] = Field(..., description="Actual coordinates [x, y]")
+    description: str = Field(..., description="Human-readable action description")
+    confidence: float = Field(0.9, description="Action confidence score")
+    text: Optional[str] = Field(None, description="Text to type (for type actions)")
+
+class ActionPlan(BaseModel):
+    """Complete action plan for UI automation"""
+    steps: List[ActionStep] = Field(..., description="List of action steps")
+    success_probability: float = Field(0.9, description="Overall success probability")
+    estimated_duration: float = Field(5.0, description="Estimated execution time in seconds")
+
+class AutomationReadiness(BaseModel):
+    """Automation readiness assessment"""
+    ready: bool = Field(..., description="Whether automation is ready")
+    confidence: float = Field(..., description="Automation confidence score")
+    page_type: str = Field(..., description="Detected page type")
+    steps_count: int = Field(..., description="Number of automation steps")
+    estimated_success_rate: float = Field(0.9, description="Estimated success rate")
+
+class UIAnalysisRequest(BaseModel):
+    """UI analysis request"""
+    image_b64: str = Field(..., description="Base64 encoded image")
+    task_type: str = Field("search", description="Analysis task type")
+    
+    model_config = {
+        "json_schema_extra": {
+            "example": {
+                "image_b64": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mP8/5+hHgAHggJ/PchI7wAAAABJRU5ErkJggg==",
+                "task_type": "search"
+            }
+        }
+    }
+
+class UIAnalysisResponse(BaseModel):
+    """UI analysis response"""
+    success: bool = Field(..., description="Analysis success status")
+    service: str = Field("ui_analysis", description="Service identifier")
+    total_execution_time: float = Field(..., description="Total processing time in seconds")
+    ui_elements: List[UIElement] = Field(..., description="Detected UI elements")
+    action_plan: ActionPlan = Field(..., description="Generated action plan")
+    automation_ready: AutomationReadiness = Field(..., description="Automation readiness")
+    metadata: Dict[str, Any] = Field(default_factory=dict, description="Additional metadata")
+    timestamp: float = Field(default_factory=time.time, description="Response timestamp")
+
+class UIDetectionResponse(BaseModel):
+    """UI elements detection only response"""
+    success: bool = Field(..., description="Detection success status")
+    processing_time: float = Field(..., description="Processing time in seconds")
+    ui_elements: List[UIElement] = Field(..., description="Detected UI elements")
+    element_count: int = Field(..., description="Number of detected elements")
+    task_type: str = Field(..., description="Analysis task type")
+    detection_method: str = Field("omniparser", description="Detection method used")
+    timestamp: float = Field(default_factory=time.time, description="Response timestamp")

{isa_model-0.3.4.dist-info → isa_model-0.3.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: isa_model
-Version: 0.3.4
+Version: 0.3.6
 Summary: Unified AI model serving framework
 Author: isA_Model Contributors
 Classifier: Development Status :: 3 - Alpha
@@ -34,6 +34,9 @@ Requires-Dist: accelerate>=0.20.0
 Requires-Dist: bitsandbytes>=0.39.0
 Requires-Dist: peft>=0.4.0
 Requires-Dist: trl>=0.4.0
+Requires-Dist: supabase>=2.0.0
+Requires-Dist: pgvector>=0.2.0
+Requires-Dist: psycopg2-binary>=2.9.0
 
 # isa_model_sdk - Unified AI Model Serving Framework
 

isa_model-0.3.6.dist-info/RECORD

@@ -0,0 +1,147 @@
+isa_model/__init__.py,sha256=bAbHdrDVQ-mySC_GJtgfLNI8KPcs2LfReBkIOOtpaQQ,867
+isa_model/client.py,sha256=5u_hqGB1hcFX8MQdVYlCLqzs4ylQFY3rq91h3iTI24c,27500
+isa_model/core/config.py,sha256=h9GVTEEMlaJYSCDd0W9q1KtaWTV5V5TawMsKtGuphds,15686
+isa_model/core/pricing_manager.py,sha256=b7HcZsBQ8ZSCzMepOhqN-J9kU43vhTxX5NabQS0aM70,17125
+isa_model/core/types.py,sha256=XLUs442WGNc8E0gF2M-nb6dutD_s-XCfpr2BfGBCA2M,8445
+isa_model/core/config/__init__.py,sha256=SLeHQtYGDHl64NDVyb3ECQXOKepGM8YNHEoM8CVEWus,350
+isa_model/core/config/config_manager.py,sha256=hx0qcdvYEE_cCp-qb8tnVkXnpsTXEuRM1108DoAiUnE,19905
+isa_model/core/models/model_billing_tracker.py,sha256=hxqG5DvQ8kqROC3WVb5Y0tespp73TPPWYq-AwatMZwc,18782
+isa_model/core/models/model_manager.py,sha256=9_JHok4i2q79dhFD3nckrlG-k3z8UGb6bM82iUR-T84,14917
+isa_model/core/models/model_repo.py,sha256=OqvtUrvWmn_k4tkAgdOQ61NneUHsJGbUjkobJf3LNSw,14036
+isa_model/core/models/model_storage.py,sha256=yMLapW87EY1EPXw6S7H8UQAZh3hJ1KxsEohjgjw-HrA,4507
+isa_model/core/services/__init__.py,sha256=M1ob5N-PDPUW0o03ioHORRl5ye5ZEEzT7265-u-NrP4,481
+isa_model/core/services/intelligent_model_selector.py,sha256=vf8BhITetIh5VJcccsESrHyeh9p-V6AHD9NRAEt6a5w,21501
+isa_model/core/storage/hf_storage.py,sha256=HTj1-YGJM3Q-9_Adw7u4NjEmSdr0njsFEL45KXzfcFw,14701
+isa_model/core/storage/local_storage.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+isa_model/core/storage/minio_storage.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+isa_model/deployment/__init__.py,sha256=tzBOOvDXl6Hh8IiS2ehW6RKeUcBia_MY1uegQFFfFRg,1400
+isa_model/deployment/cloud/__init__.py,sha256=ztahTvIZYNoEU_bqmVAvb3xL_ttWHAGO_UAiwQP4dHY,135
+isa_model/deployment/cloud/modal/__init__.py,sha256=iD65eaqvI7L_W31p-tDO4fMIG5EWfkir1l3SKRSp72Y,265
+isa_model/deployment/cloud/modal/isa_vision_doc_service.py,sha256=GnIOwMNibXFqeA4ToUOovPxuj0NQTLXgkSbR1r6nUcU,30386
+isa_model/deployment/cloud/modal/isa_vision_table_service.py,sha256=ewuRLIM1sqeet_7Vb9y1xcB1vXg2OAHVZNDfeFA_KHM,19814
+isa_model/deployment/cloud/modal/isa_vision_ui_service.py,sha256=75iTaucfLYvWBqAvNdSXJT80R7hInYWOeLamxCyfteQ,14027
+isa_model/deployment/cloud/modal/register_models.py,sha256=gqvKDE8hdwOlSyg5nWrAYNlQ0AjHa4aP9OhFBw7UXLw,12162
+isa_model/deployment/core/__init__.py,sha256=QJkJrs0FYgYcjvnHMSvAtUBiT6uq_ciqLKWLwx0mkDg,803
+isa_model/deployment/core/deployment_config.py,sha256=__bHohsvbdZK_rS_86S1rSHPPP1bTkOnx_G0cj1HMcA,11305
+isa_model/deployment/core/deployment_manager.py,sha256=kICHX1V8wIlmldkrfdqakz2OAjitUfGY6ZG_QjGzZbM,20068
+isa_model/deployment/core/isa_deployment_service.py,sha256=sXU7REZ4xhUUGrpqxlJh-twx18rd97Da4sPEk62QaME,12600
+isa_model/deployment/gpu_int8_ds8/app/server.py,sha256=lwWxdnR2DNEd0vIGQyfabKtDSUzSHVQsy3Z_AJejpVg,2102
+isa_model/deployment/gpu_int8_ds8/scripts/test_client.py,sha256=aCULgRYzEQj_ELUK1bmPgN99yvFgNR5C0O3gc8S32pg,1421
+isa_model/deployment/gpu_int8_ds8/scripts/test_client_os.py,sha256=XXrneTCHUeh1LNRcu-YtZQ5B4pNawlrxC-cTWmJU2A8,936
+isa_model/deployment/runtime/deployed_service.py,sha256=0Z_Hg42oXasEVvuKjwBylJPazcmJYXhS-L9uPainaIg,13400
+isa_model/deployment/services/__init__.py,sha256=JrLlmBlLb6RfiqGMzVVxKZfF5tAKliQqpon_rPoNoeA,216
+isa_model/deployment/services/auto_deploy_vision_service.py,sha256=Luo8FaXsEBoKjGw5HQ7veOnv9Eh0e7U0claXaGa3-1o,19624
+isa_model/deployment/services/model_service.py,sha256=_ncC--8hr5BUwzCWh59yRXPKIPVLapx_31TorB2DIr8,13492
+isa_model/deployment/services/service_monitor.py,sha256=P1zGoeqkNEJwt9AXZF2qTjfSLRm5PKUa80GJVNDSIdA,15223
+isa_model/deployment/services/service_registry.py,sha256=LQgWQOvoP0lb7mC6WTS6shEt6WuX6xc8rRmcixrKwTc,22765
+isa_model/eval/__init__.py,sha256=CRbxC5SN7ow4ymdALSNTHawqw4f82DEdAb7twNT_Pw0,2447
+isa_model/eval/benchmarks.py,sha256=_L4Vwj2hwf2yhqoleIASO9z5e3LRCClCVEVCQbGt0I8,16885
+isa_model/eval/factory.py,sha256=bm5OVY7HIxdBgjlH1n7e5K1YO4ytv8e4KB7z_JS9HVQ,20737
+isa_model/eval/metrics.py,sha256=VMQqcB13OScJsEmfuMZeBk5RLCs01zWknuMqQRVFCjo,30315
+isa_model/eval/config/__init__.py,sha256=SDwprIRp1GSG7PAXJuyNldUZ6dPeuIcwdxCkHZXIeVQ,181
+isa_model/eval/config/evaluation_config.py,sha256=y4tQAqafx5snoQ0QD239C9QXHmqcQvjH34uGSEJUhvI,3051
+isa_model/eval/evaluators/__init__.py,sha256=bDMBhD8bTW740dQEt8Ru-nWPGiJHkyQQcfGEejgzkh4,461
+isa_model/eval/evaluators/base_evaluator.py,sha256=1RivgnnuA-k9EtsZ-KMEtts_5gcfnaTGAoF-uBVSesE,19292
+isa_model/eval/evaluators/llm_evaluator.py,sha256=yfFJFdxwGV2F3mzEWjZ-0fr9u8SR3A20UJ7zS7OgKsw,18054
+isa_model/eval/infrastructure/__init__.py,sha256=fxTdtwAFtjCDOV9MJ3GbhY0A-DqKeTwr_u9WTBnGI_U,648
+isa_model/eval/infrastructure/experiment_tracker.py,sha256=yfMWIAk6oA8Lfer3AtmKg0OEZiGhczmsCD5gmp--uew,15283
+isa_model/inference/__init__.py,sha256=usfuQJ4zYY2RRtHkE-V6LuJ5aN7WJogtPUj9Qmy4Wvw,318
+isa_model/inference/ai_factory.py,sha256=IN-q3jNmcraZ-PWNTHyhdABoxxhIweZYcXO2fr_uXoM,16478
+isa_model/inference/base.py,sha256=qwOddnSGI0GUdD6qIdGBPQpkW7UjU3Y-zaZvu70B4WA,1278
+isa_model/inference/adapter/unified_api.py,sha256=67_Ok8W20m6Otf6r9WyOEVpnxondP4UAxOASk9ozDk4,8668
+isa_model/inference/providers/__init__.py,sha256=a83q-LMFv8u47wf0XtxvqOw_mlVgA_90wtuwy02qdDE,581
+isa_model/inference/providers/base_provider.py,sha256=PT-YnGwBu-Jn_4T3iAphkAJw_mYmKVLjUID62vf2_Ow,2711
+isa_model/inference/providers/ml_provider.py,sha256=4oGGF7lVWQ91Qh3h7olyPFoACLxCROaMxUZlDiZrRL4,1661
+isa_model/inference/providers/modal_provider.py,sha256=klRYXECD5TJicodHIElsGNGMAsAWRFhvn4yfCRcqdVs,3654
+isa_model/inference/providers/model_cache_manager.py,sha256=dLRpx7OJweQ5LcSAkU7D0DQRfLtIhG6nGvg4W_gau80,15315
+isa_model/inference/providers/ollama_provider.py,sha256=IfM9XhdzfE1faguzS2-4GfhK30v5kDPecD3l4z2eB1w,3620
+isa_model/inference/providers/openai_provider.py,sha256=tB8FMsMivlRx0cfPJ0Yrxh1DCvuXyyjNFXrO4lMkkhA,5366
+isa_model/inference/providers/replicate_provider.py,sha256=0oi_BglIE6-HYgzLau9ifP8OdpAMO-QkwYk0OXRUzPk,4490
+isa_model/inference/providers/triton_provider.py,sha256=GKlth7cTOx6ERbsXXJ0gDNby3kVGQNULBDt098BXBSU,15258
+isa_model/inference/providers/yyds_provider.py,sha256=KbDsopShs11_G9oX3b2i2NgHIqkZV7HYWe9K9uZLccc,4284
+isa_model/inference/services/__init__.py,sha256=yfLz0YGl8ixk6LfTRL6cRTvZMb9F_Pv1QRgGyNc9xYM,386
+isa_model/inference/services/base_service.py,sha256=fVaSx0CogHK71UEsNJeSyM8mhqmq5_9ePbbSZVi3Al8,5085
+isa_model/inference/services/audio/base_stt_service.py,sha256=sfzAfreFdvEOBHtphoTrQSjb-gCoCOW4WCj6iIe51oU,5804
+isa_model/inference/services/audio/base_tts_service.py,sha256=PgctcV98Pe9I2kSjScsm8epRwdaEU-vAGCIfdd2P8us,6924
+isa_model/inference/services/audio/openai_realtime_service.py,sha256=UENsx1bEb7aJoXNuBtFGIbTmETpNTZcCHlv0RydEp_U,13340
+isa_model/inference/services/audio/openai_stt_service.py,sha256=chqVuSU8JtwkqY6Y7INm0AdSoDqh-bsg9POzJkxN3h0,10989
+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/base_embed_service.py,sha256=_9HLzwDfKXbhFWT_3VbLQpDF3N1Rr3JS-QXqAZM9Wyc,6045
+isa_model/inference/services/embedding/ollama_embed_service.py,sha256=Pbc3jePaEsudHOn07BSf_A525weoesH3d3r5vs8ODvc,6702
+isa_model/inference/services/embedding/openai_embed_service.py,sha256=Egzq0sxFWf5lndf12xijLuvJSw1wnLeU9wdNR9pnzkQ,8342
+isa_model/inference/services/embedding/helpers/text_splitter.py,sha256=6AbvcQ7H6MS54B9d9T1XBGg4GhvmKfZqp00lKp9pF-U,1635
+isa_model/inference/services/helpers/stacked_config.py,sha256=xPGvWBu364qSF5RXAefAdsqC9SUHC6frTtJamQRQZX8,5473
+isa_model/inference/services/img/__init__.py,sha256=Mip969-_UGRAADfDlcXEBPrsYY7sZleztolcjjmKfyA,518
+isa_model/inference/services/img/base_image_gen_service.py,sha256=PECzUood4E25Bh2hAbe-d62nB6CwRbg1pORdDkLlEjg,7194
+isa_model/inference/services/img/flux_professional_service.py,sha256=c-3F9ANUuYiZPG4SgsOgb6jTDFIXWD52Kz-RC9g_a-Q,26407
+isa_model/inference/services/img/replicate_image_gen_service.py,sha256=QLjgrXNmtdXmKQPCLkmrTjNPL7_icy6enWmeArRCicU,17240
+isa_model/inference/services/img/helpers/base_stacked_service.py,sha256=Y2g2Hz3n2Uwo4RoCbsC33IXxTeQ2TeT6T-2HnXd-2B0,10546
+isa_model/inference/services/llm/__init__.py,sha256=hSdfeqE0463CtQ6ZzREqPBvtzXNuzi3W5PFKS0nwhvo,336
+isa_model/inference/services/llm/base_llm_service.py,sha256=fg79J5mKy27qahvtLscMcquOe4O2L-EoNjE33yPRI9E,22196
+isa_model/inference/services/llm/ollama_llm_service.py,sha256=c0i9TLce6YcPlsLpj11kvwd-H2Uvw23G0ACuNShGyAM,16009
+isa_model/inference/services/llm/openai_llm_service.py,sha256=yhqsExCWvVs6G7EhwZnoXMtKncpwY1VPeZqgLibMSX0,11922
+isa_model/inference/services/llm/yyds_llm_service.py,sha256=WA5vwK9j7PrEEffdvP4thNwBlZ5Z13vFXX_F3Kd5V-Y,10475
+isa_model/inference/services/llm/helpers/llm_adapter.py,sha256=gkKND55EoizRxsaGOCEazUmL-2yTIBI-_njpEOXt-4k,21779
+isa_model/inference/services/llm/helpers/llm_prompts.py,sha256=4ZOovr_Jx5bwPiMkgO1lZF7GMyEFbITP3ZrhhI48QMs,10964
+isa_model/inference/services/llm/helpers/llm_utils.py,sha256=LNfB3qzREyD2TyleOyVa20FU8HbhdxA8G6QV-N-wfZs,10016
+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/others/table_transformer_service.py,sha256=r74h6QUSwSj6jTt-gRProz9SgwBwKWDe50NR0uqW0ZI,2367
+isa_model/inference/services/vision/__init__.py,sha256=9JkNzwZa6WQPUXtq4i7x78mPxkzBNRB-6CkU2WyoCYE,1191
+isa_model/inference/services/vision/base_vision_service.py,sha256=FInmrdhKaeu0vBUbxScH3_B9a_fk3pj2foLx0P81a6o,12645
+isa_model/inference/services/vision/doc_analysis_service.py,sha256=_klnuI99tSkA1gcs5hPQmj6Ld8GElg0S823LXa9id2Y,24797
+isa_model/inference/services/vision/openai_vision_service.py,sha256=IcDX0nBPqt9TJSwMEUD89Fojz1X8jF3ZD1voJGOzu4A,9609
+isa_model/inference/services/vision/replicate_vision_service.py,sha256=smRkSCTwk5mvyKVnvyplqPNuVYjRZngVBWxTCbFmrxA,20679
+isa_model/inference/services/vision/ui_analysis_service.py,sha256=LTFY5rMIQwgWh_kh9KWA44ZI01Mb3We5NsG2scSgBeA,32153
+isa_model/inference/services/vision/disabled/isA_vision_service.py,sha256=VYa8VJtxDB9KdnfNW0GPEP_TPker4pHp33gLD_TnpaM,18336
+isa_model/inference/services/vision/helpers/base_stacked_service.py,sha256=Y2g2Hz3n2Uwo4RoCbsC33IXxTeQ2TeT6T-2HnXd-2B0,10546
+isa_model/inference/services/vision/helpers/image_utils.py,sha256=7RZ368o2UXcRCqyzldUOGhzB5vWbCCJOVR24UdiVdhs,11061
+isa_model/inference/services/vision/helpers/vision_prompts.py,sha256=WbzOYu-Z2-8Xn9dcvuPRTA7VTy23_uoMRRGO4t0wZ8Q,12098
+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/scripts/inference_tracker.py,sha256=T6qQJMHJcAIQ8eYlgqpM9RWxfiV4z5xIolaoglKBBsg,8831
+isa_model/scripts/mlflow_manager.py,sha256=7xMN0_wELr1jcALuTW9WeWirRkPZPlE2LlFfZKflXBY,12142
+isa_model/scripts/model_registry.py,sha256=7rycPkVk8WHUO3LJaHfdyy5Yq8qmd_4WkGk4wKan-2w,14279
+isa_model/scripts/register_models.py,sha256=ukqhUFiXkZh2IGzJTjEKpqRpf6VW4oSYm4PP_JjYcM8,14658
+isa_model/scripts/register_models_with_embeddings.py,sha256=A4utiT5_uqvgMQJ9qioIZM2XMreHLgJoqZOysNbzmM8,20990
+isa_model/scripts/start_mlflow.py,sha256=3AGKBzByjzbZ56I8w0IOfYnp3V6EU2Lv9NtX9maSqL8,2571
+isa_model/scripts/training_tracker.py,sha256=cnXPi8ip2OK76-aWAOgC-dKx90PqZLEnP6UbHso7Fwc,8080
+isa_model/serving/__init__.py,sha256=LTO0Adbvm7A-bgQqtuOQSoHvdu9OH3OrEjYgQanuHgI,429
+isa_model/serving/api/__init__.py,sha256=wgWD69eqV37fFTLxhz8b0rOn_34P7SZHoWw2sufWjk4,162
+isa_model/serving/api/fastapi_server.py,sha256=UP3CZim8E2tNcyUGaoU9cYM80_yzzpWQFd3ADfo6ANk,2628
+isa_model/serving/api/middleware/__init__.py,sha256=iCKUYECf0bjNGXgV91K03hb8Dnp0Jc_wnUL897Rd0sg,163
+isa_model/serving/api/middleware/request_logger.py,sha256=d48n6tp1pqZ7HFWFl8jg6er24ugWkWkMOc1y80aqPU8,2938
+isa_model/serving/api/routes/__init__.py,sha256=RIaG9OPg0AjAIVbtMzwnqGyNU-tuQXbdvFcYOt4b_Do,84
+isa_model/serving/api/routes/health.py,sha256=NwQcC_bpcaI4YZHTIKbGtg82yQ6QLdp0TwcqbEiqbWs,2208
+isa_model/serving/api/routes/llm.py,sha256=5ZVxWugff0i6VBKz_Nv5CqacMZJsPZEKyoSB6XDrW34,385
+isa_model/serving/api/routes/ui_analysis.py,sha256=-WxLaRKQNHnRh4okB85cWA4blTegpEPZtzHTsF3yeeU,6848
+isa_model/serving/api/routes/unified.py,sha256=rSoHPtMWkGlzFwzzoZeFlCmFGWj2r3q-5QH9VeNQQxA,7074
+isa_model/serving/api/routes/vision.py,sha256=U9jxssQYe6igtayUW0C2fcYwqmLRIE15__X-5Ru9J4c,396
+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/training/__init__.py,sha256=lfgaSGmOdfizXYV0NKZ6UDXdx_KIlit62eVhGK_6zXA,1533
+isa_model/training/factory.py,sha256=c-77203-2jL3ppcAhhtms6eb8RwI1xz7k324V_NqCFM,13733
+isa_model/training/annotation/annotation_schema.py,sha256=BDEgUlRxMoXGTn12VZ_UUU8rWUHQW_JL39d1AvWU-04,1271
+isa_model/training/annotation/processors/annotation_processor.py,sha256=hz5VhaPLLPuwq2IoBMbxrZfOS_xBVCrqWk1GEKW2zd0,4839
+isa_model/training/annotation/storage/dataset_manager.py,sha256=nKxhmkw-K5vO7Wd5I0Rp5j9fqwV06h_9i_1lVQiU7uU,4592
+isa_model/training/annotation/storage/dataset_schema.py,sha256=JPhrT-pbT0jGd_rmDlhyTesXKv9OYxy85U-RAJFe05o,1086
+isa_model/training/annotation/tests/test_annotation_flow.py,sha256=DXYHP8rLKaLII6bo5Rtltqk4sQxr8k8G-wQegfuXHiE,3605
+isa_model/training/annotation/tests/test_minio copy.py,sha256=EI-PlH5xttAZF14Z_xn6LjgIJBkvP2qjLcvbX2hc0RM,3946
+isa_model/training/annotation/tests/test_minio_upload.py,sha256=fL1eMubwR6L9lYc3zEwlWU9yjJuTsIYi93i0l9QUjm0,1109
+isa_model/training/annotation/views/annotation_controller.py,sha256=3VzJ52yI-YIpcaAAXy2qac7sr4hTnFdtn-ZEKTt4IkM,5792
+isa_model/training/cloud/__init__.py,sha256=ZVsNsnZUgueqtd-e1__xD19njf7KrLTwz28htaU174g,678
+isa_model/training/cloud/job_orchestrator.py,sha256=WDv_7HwibjN7iogCKPnO0UTvvl7ADCQc6rRDHOBj_OQ,15501
+isa_model/training/cloud/runpod_trainer.py,sha256=x9NMFNMnz6HEolADf9wYY5OnkklOspwcE6u_pf_7SVQ,15208
+isa_model/training/cloud/storage_manager.py,sha256=qitWGuPHKNmYCSkMdOO0ccz2xPxFa9EfhcDZwQ-fZXA,18556
+isa_model/training/core/__init__.py,sha256=HyIsPibT0MAy9v55BK95K30aXKkBU6tgVbeTL17HFTY,526
+isa_model/training/core/config.py,sha256=oqgKpBvtzrN6jwLIQYQ2707lH6nmjrktRiSxp9iocVc,5084
+isa_model/training/core/dataset.py,sha256=XCFsnf0NUMU1dJpdvo_CAMyvXB-9_RCUEiy8TU50e20,7802
+isa_model/training/core/trainer.py,sha256=h5TjqjdFr0Fsv5y4-0siy1KmOlqLfliVaUXybvuoeXU,26932
+isa_model/training/core/utils.py,sha256=Nik0M2ssfNbWqP6fKO0Kfyhzr_H6Q19ioxB-qCYbn5E,8387
+isa_model-0.3.6.dist-info/METADATA,sha256=TMGcK76gGTCDWcXfCp17JuAoWxVN4TfVv5Nu-8mN8JE,12326
+isa_model-0.3.6.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+isa_model-0.3.6.dist-info/top_level.txt,sha256=eHSy_Xb3kNkh2kK11mi1mZh0Wz91AQ5b8k2KFYO-rE8,10
+isa_model-0.3.6.dist-info/RECORD,,

isa_model/core/model_manager.py

@@ -1,208 +0,0 @@
-from typing import Dict, Optional, List, Any
-import logging
-from pathlib import Path
-from huggingface_hub import hf_hub_download, snapshot_download
-from huggingface_hub.errors import HfHubHTTPError
-from .model_storage import ModelStorage, LocalModelStorage
-from .model_registry import ModelRegistry, ModelType, ModelCapability
-
-logger = logging.getLogger(__name__)
-
-class ModelManager:
-    """Model management service for handling model downloads, versions, and caching"""
-    
-    # 统一的模型计费信息 (per 1M tokens)
-    MODEL_PRICING = {
-        # OpenAI Models
-        "openai": {
-            "gpt-4o-mini": {"input": 0.15, "output": 0.6},
-            "gpt-4.1-mini": {"input": 0.4, "output": 1.6},
-            "gpt-4.1-nano": {"input": 0.1, "output": 0.4},
-            "gpt-4o": {"input": 5.0, "output": 15.0},
-            "gpt-4-turbo": {"input": 10.0, "output": 30.0},
-            "gpt-4": {"input": 30.0, "output": 60.0},
-            "gpt-3.5-turbo": {"input": 0.5, "output": 1.5},
-            "text-embedding-3-small": {"input": 0.02, "output": 0.0},
-            "text-embedding-3-large": {"input": 0.13, "output": 0.0},
-            "whisper-1": {"input": 6.0, "output": 0.0},
-            "tts-1": {"input": 15.0, "output": 0.0},
-            "tts-1-hd": {"input": 30.0, "output": 0.0},
-        },
-        # Ollama Models (免费本地模型)
-        "ollama": {
-            "llama3.2:3b-instruct-fp16": {"input": 0.0, "output": 0.0},
-            "llama3.2-vision:latest": {"input": 0.0, "output": 0.0},
-            "bge-m3": {"input": 0.0, "output": 0.0},
-        },
-        # Replicate Models
-        "replicate": {
-            "black-forest-labs/flux-schnell": {"input": 3.0, "output": 0.0},  # $3 per 1000 images
-            "black-forest-labs/flux-kontext-pro": {"input": 40.0, "output": 0.0},  # $0.04 per image = $40 per 1000 images
-            "meta/meta-llama-3-8b-instruct": {"input": 0.05, "output": 0.25},
-            "kokoro-82m": {"input": 0.0, "output": 0.4},  # ~$0.0004 per second
-            "jaaari/kokoro-82m:f559560eb822dc509045f3921a1921234918b91739db4bf3daab2169b71c7a13": {"input": 0.0, "output": 0.4},
-        }
-    }
-    
-    def __init__(self, 
-                 storage: Optional[ModelStorage] = None,
-                 registry: Optional[ModelRegistry] = None):
-        self.storage = storage or LocalModelStorage()
-        self.registry = registry or ModelRegistry()
-    
-    def get_model_pricing(self, provider: str, model_name: str) -> Dict[str, float]:
-        """获取模型定价信息"""
-        return self.MODEL_PRICING.get(provider, {}).get(model_name, {"input": 0.0, "output": 0.0})
-    
-    def calculate_cost(self, provider: str, model_name: str, input_tokens: int, output_tokens: int) -> float:
-        """计算请求成本"""
-        pricing = self.get_model_pricing(provider, model_name)
-        input_cost = (input_tokens / 1_000_000) * pricing["input"]
-        output_cost = (output_tokens / 1_000_000) * pricing["output"]
-        return input_cost + output_cost
-    
-    def get_cheapest_model(self, provider: str, model_type: str = "llm") -> Optional[str]:
-        """获取最便宜的模型"""
-        provider_models = self.MODEL_PRICING.get(provider, {})
-        if not provider_models:
-            return None
-        
-        # 计算每个模型的平均成本 (假设输入输出比例 1:1)
-        cheapest_model = None
-        lowest_cost = float('inf')
-        
-        for model_name, pricing in provider_models.items():
-            avg_cost = (pricing["input"] + pricing["output"]) / 2
-            if avg_cost < lowest_cost:
-                lowest_cost = avg_cost
-                cheapest_model = model_name
-        
-        return cheapest_model
-
-    async def get_model(self, 
-                       model_id: str, 
-                       repo_id: str,
-                       model_type: ModelType,
-                       capabilities: List[ModelCapability],
-                       revision: Optional[str] = None,
-                       force_download: bool = False) -> Optional[Path]:
-        """
-        Get model files, downloading if necessary
-        
-        Args:
-            model_id: Unique identifier for the model
-            repo_id: Hugging Face repository ID
-            model_type: Type of model (LLM, embedding, etc.)
-            capabilities: List of model capabilities
-            revision: Specific model version/tag
-            force_download: Force re-download even if cached
-            
-        Returns:
-            Path to the model files or None if failed
-        """
-        # Check if model is already downloaded
-        if not force_download:
-            model_path = await self.storage.load_model(model_id)
-            if model_path:
-                logger.info(f"Using cached model {model_id}")
-                return model_path
-        
-        try:
-            # Download model files
-            logger.info(f"Downloading model {model_id} from {repo_id}")
-            model_dir = Path(f"./models/temp/{model_id}")
-            model_dir.mkdir(parents=True, exist_ok=True)
-            
-            snapshot_download(
-                repo_id=repo_id,
-                revision=revision,
-                local_dir=model_dir,
-                local_dir_use_symlinks=False
-            )
-            
-            # Save model and metadata
-            metadata = {
-                "repo_id": repo_id,
-                "revision": revision,
-                "downloaded_at": str(Path(model_dir).stat().st_mtime)
-            }
-            
-            # Register model
-            self.registry.register_model(
-                model_id=model_id,
-                model_type=model_type,
-                capabilities=capabilities,
-                metadata=metadata
-            )
-            
-            # Save model files
-            await self.storage.save_model(model_id, str(model_dir), metadata)
-            
-            return await self.storage.load_model(model_id)
-            
-        except HfHubHTTPError as e:
-            logger.error(f"Failed to download model {model_id}: {e}")
-            return None
-        except Exception as e:
-            logger.error(f"Unexpected error downloading model {model_id}: {e}")
-            return None
-    
-    async def list_models(self) -> List[Dict[str, Any]]:
-        """List all downloaded models with their metadata"""
-        models = await self.storage.list_models()
-        return [
-            {
-                "model_id": model_id,
-                **metadata,
-                **(self.registry.get_model_info(model_id) or {})
-            }
-            for model_id, metadata in models.items()
-        ]
-    
-    async def remove_model(self, model_id: str) -> bool:
-        """Remove a model and its metadata"""
-        try:
-            # Remove from storage
-            storage_success = await self.storage.delete_model(model_id)
-            
-            # Unregister from registry
-            registry_success = self.registry.unregister_model(model_id)
-            
-            return storage_success and registry_success
-            
-        except Exception as e:
-            logger.error(f"Failed to remove model {model_id}: {e}")
-            return False
-    
-    async def get_model_info(self, model_id: str) -> Optional[Dict[str, Any]]:
-        """Get information about a specific model"""
-        storage_info = await self.storage.get_metadata(model_id)
-        registry_info = self.registry.get_model_info(model_id)
-        
-        if not storage_info and not registry_info:
-            return None
-            
-        return {
-            **(storage_info or {}),
-            **(registry_info or {})
-        }
-    
-    async def update_model(self, 
-                          model_id: str, 
-                          repo_id: str,
-                          model_type: ModelType,
-                          capabilities: List[ModelCapability],
-                          revision: Optional[str] = None) -> bool:
-        """Update a model to a new version"""
-        try:
-            return bool(await self.get_model(
-                model_id=model_id,
-                repo_id=repo_id,
-                model_type=model_type,
-                capabilities=capabilities,
-                revision=revision,
-                force_download=True
-            ))
-        except Exception as e:
-            logger.error(f"Failed to update model {model_id}: {e}")
-            return False