isa-model 0.4.3__tar.gz → 0.4.5__tar.gz

{isa_model-0.4.3 → isa_model-0.4.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: isa_model
-Version: 0.4.3
+Version: 0.4.5
 Summary: Unified AI model serving framework
 Author: isA_Model Contributors
 Classifier: Development Status :: 3 - Alpha
@@ -89,6 +89,11 @@ Requires-Dist: isa-model[cloud,k8s,monitoring,storage]; extra == "production"
 Provides-Extra: staging
 Requires-Dist: isa-model[cloud,langchain,monitoring,storage]; extra == "staging"
 Requires-Dist: python-consul>=1.1.0; extra == "staging"
+Provides-Extra: staging-minimal
+Requires-Dist: isa-model[cloud,langchain,storage]; extra == "staging-minimal"
+Requires-Dist: influxdb-client>=1.36.0; extra == "staging-minimal"
+Requires-Dist: python-logging-loki>=0.3.1; extra == "staging-minimal"
+Requires-Dist: python-consul>=1.1.0; extra == "staging-minimal"
 Provides-Extra: all
 Requires-Dist: isa-model[audio,cloud,gpu-cloud,k8s,langchain,local,monitoring,storage,training,vision]; extra == "all"
 

{isa_model-0.4.3 → isa_model-0.4.5}/isa_model/core/config.py

@@ -54,7 +54,7 @@ class LocalGPUGlobalConfig:
     enable_local_gpu: bool = True
     auto_detect_gpu: bool = True
     workspace_dir: str = "./local_deployments"
-    preferred_backend: str = "transformers"  # vllm, tensorrt_llm, transformers
+    preferred_backend: str = "api"  # cloud api only
     
     # Default resource settings
     default_gpu_memory_fraction: float = 0.9
@@ -114,7 +114,7 @@ class GlobalConfig:
     local_gpu_memory_fraction: float = 0.9
     local_workspace_dir: str = "./local_deployments"
     auto_detect_gpu: bool = True
-    preferred_local_backend: str = "transformers"  # vllm, tensorrt_llm, transformers
+    preferred_local_backend: str = "api"  # cloud api only
     
     # Local service defaults
     local_health_check_interval: int = 30  # seconds
@@ -263,7 +263,7 @@ class ConfigManager:
             "enable_local_gpu": os.getenv("ISA_ENABLE_LOCAL_GPU", "true").lower() == "true",
             "auto_detect_gpu": os.getenv("ISA_AUTO_DETECT_GPU", "true").lower() == "true",
             "workspace_dir": os.getenv("ISA_LOCAL_WORKSPACE_DIR", "./local_deployments"),
-            "preferred_backend": os.getenv("ISA_PREFERRED_LOCAL_BACKEND", "transformers"),
+            "preferred_backend": os.getenv("ISA_PREFERRED_LOCAL_BACKEND", "api"),
             "default_gpu_memory_fraction": float(os.getenv("ISA_GPU_MEMORY_FRACTION", "0.9")),
             "health_check_interval": int(os.getenv("ISA_LOCAL_HEALTH_CHECK_INTERVAL", "30")),
             "max_concurrent_services": int(os.getenv("ISA_MAX_CONCURRENT_SERVICES", "3")),

{isa_model-0.4.3 → isa_model-0.4.5}/isa_model/core/logging/__init__.py

@@ -3,21 +3,24 @@ Logging module for ISA Model
 
 Provides comprehensive logging capabilities including:
 - Loki-based centralized application logging (via loki_logger)
-- InfluxDB-based inference metrics logging (via influx_logger)
-- Real-time monitoring and alerting
+- Basic inference logging with request tracking
 
 Architecture:
 - Loki: General application logs (INFO, WARNING, ERROR, DEBUG)
-- InfluxDB: Inference metrics (tokens, costs, performance data)
+- Basic logging: Simple request tracking and basic metrics
 """
 
-# InfluxDB inference metrics logging
-from .influx_logger import (
-    InfluxInferenceLogger,
-    InferenceLogEntry,
-    get_inference_logger,
-    generate_request_id
-)
+# Basic inference logging (no external dependencies)
+import uuid
+import logging
+
+def generate_request_id():
+    """Generate unique request ID for tracking"""
+    return str(uuid.uuid4())
+
+def get_inference_logger():
+    """Get basic inference logger"""
+    return logging.getLogger("isa_model.inference")
 
 # Loki centralized application logging
 from .loki_logger import (
@@ -34,9 +37,7 @@ from .loki_logger import (
 )
 
 __all__ = [
-    # InfluxDB inference logging
-    'InfluxInferenceLogger',
-    'InferenceLogEntry',
+    # Basic inference logging
     'get_inference_logger',
     'generate_request_id',
 

{isa_model-0.4.3 → isa_model-0.4.5}/isa_model/core/models/model_manager.py

@@ -2,8 +2,6 @@ from typing import Dict, Optional, List, Any
 import logging
 from pathlib import Path
 from datetime import datetime
-from huggingface_hub import hf_hub_download, snapshot_download
-from huggingface_hub.errors import HfHubHTTPError
 from .model_storage import ModelStorage, LocalModelStorage
 from .model_repo import ModelRegistry, ModelType, ModelCapability
 from .model_billing_tracker import ModelBillingTracker, ModelOperationType
@@ -102,73 +100,7 @@ class ModelManager:
             logger.warning(f"Failed to find cheapest model for {provider}: {e}")
             return None
 
-    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
+    # Local model download functionality removed - use cloud API services only
     
     async def list_models(self) -> List[Dict[str, Any]]:
         """List all downloaded models with their metadata"""

{isa_model-0.4.3 → isa_model-0.4.5}/isa_model/core/models/model_storage.py

@@ -39,11 +39,13 @@ class ModelStorage(ABC):
 class LocalModelStorage(ModelStorage):
     """Local file system based model storage"""
     
-    def __init__(self, base_dir: str = "./models"):
+    def __init__(self, base_dir: str = "./models", auto_create: bool = False):
         self.base_dir = Path(base_dir)
         self.models_dir = self.base_dir / "models"
         self.metadata_file = self.base_dir / "model_metadata.json"
-        self._ensure_directories()
+        self.auto_create = auto_create
+        if auto_create:
+            self._ensure_directories()
         self._load_metadata()
     
     def _ensure_directories(self):

{isa_model-0.4.3 → isa_model-0.4.5}/isa_model.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: isa_model
-Version: 0.4.3
+Version: 0.4.5
 Summary: Unified AI model serving framework
 Author: isA_Model Contributors
 Classifier: Development Status :: 3 - Alpha
@@ -89,6 +89,11 @@ Requires-Dist: isa-model[cloud,k8s,monitoring,storage]; extra == "production"
 Provides-Extra: staging
 Requires-Dist: isa-model[cloud,langchain,monitoring,storage]; extra == "staging"
 Requires-Dist: python-consul>=1.1.0; extra == "staging"
+Provides-Extra: staging-minimal
+Requires-Dist: isa-model[cloud,langchain,storage]; extra == "staging-minimal"
+Requires-Dist: influxdb-client>=1.36.0; extra == "staging-minimal"
+Requires-Dist: python-logging-loki>=0.3.1; extra == "staging-minimal"
+Requires-Dist: python-consul>=1.1.0; extra == "staging-minimal"
 Provides-Extra: all
 Requires-Dist: isa-model[audio,cloud,gpu-cloud,k8s,langchain,local,monitoring,storage,training,vision]; extra == "all"
 

{isa_model-0.4.3 → isa_model-0.4.5}/isa_model.egg-info/SOURCES.txt

@@ -24,7 +24,6 @@ isa_model/core/database/supabase_client.py
 isa_model/core/discovery/__init__.py
 isa_model/core/discovery/consul_discovery.py
 isa_model/core/logging/__init__.py
-isa_model/core/logging/influx_logger.py
 isa_model/core/logging/loki_logger.py
 isa_model/core/models/__init__.py
 isa_model/core/models/config_models.py
@@ -40,22 +39,12 @@ isa_model/core/models/system_models.py
 isa_model/core/repositories/__init__.py
 isa_model/core/repositories/config_repository.py
 isa_model/core/resilience/circuit_breaker.py
-isa_model/core/security/secrets.py
 isa_model/core/services/__init__.py
 isa_model/core/services/intelligent_model_selector.py
-isa_model/core/storage/hf_storage.py
 isa_model/core/storage/local_storage.py
 isa_model/deployment/__init__.py
 isa_model/deployment/core/__init__.py
 isa_model/deployment/core/deployment_manager.py
-isa_model/deployment/local/__init__.py
-isa_model/deployment/local/config.py
-isa_model/deployment/local/gpu_gateway.py
-isa_model/deployment/local/health_checker.py
-isa_model/deployment/local/provider.py
-isa_model/deployment/local/tensorrt_service.py
-isa_model/deployment/local/transformers_service.py
-isa_model/deployment/local/vllm_service.py
 isa_model/deployment/modal/__init__.py
 isa_model/deployment/modal/config.py
 isa_model/deployment/modal/deployer.py
@@ -107,7 +96,6 @@ isa_model/inference/repositories/__init__.py
 isa_model/inference/repositories/inference_repository.py
 isa_model/inference/services/__init__.py
 isa_model/inference/services/base_service.py
-isa_model/inference/services/custom_model_manager.py
 isa_model/inference/services/audio/__init__.py
 isa_model/inference/services/audio/base_realtime_service.py
 isa_model/inference/services/audio/base_stt_service.py
@@ -137,7 +125,6 @@ isa_model/inference/services/llm/__init__.py
 isa_model/inference/services/llm/base_llm_service.py
 isa_model/inference/services/llm/cerebras_llm_service.py
 isa_model/inference/services/llm/huggingface_llm_service.py
-isa_model/inference/services/llm/local_llm_service.py
 isa_model/inference/services/llm/ollama_llm_service.py
 isa_model/inference/services/llm/openai_llm_service.py
 isa_model/inference/services/llm/yyds_llm_service.py
@@ -148,7 +135,6 @@ isa_model/inference/services/ml/base_ml_service.py
 isa_model/inference/services/ml/sklearn_ml_service.py
 isa_model/inference/services/vision/__init__.py
 isa_model/inference/services/vision/base_vision_service.py
-isa_model/inference/services/vision/blip_vision_service.py
 isa_model/inference/services/vision/isa_vision_service.py
 isa_model/inference/services/vision/openai_vision_service.py
 isa_model/inference/services/vision/replicate_vision_service.py

{isa_model-0.4.3 → isa_model-0.4.5}/isa_model.egg-info/requires.txt

@@ -83,6 +83,12 @@ isa-model[cloud,k8s,monitoring,storage]
 isa-model[cloud,langchain,monitoring,storage]
 python-consul>=1.1.0
 
+[staging-minimal]
+isa-model[cloud,langchain,storage]
+influxdb-client>=1.36.0
+python-logging-loki>=0.3.1
+python-consul>=1.1.0
+
 [storage]
 boto3>=1.26.0
 google-cloud-storage>=2.7.0

{isa_model-0.4.3 → isa_model-0.4.5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "isa_model"
-version = "0.4.3"
+version = "0.4.5"
 description = "Unified AI model serving framework"
 authors = [{name = "isA_Model Contributors"}]
 readme = "README.md"
@@ -152,6 +152,14 @@ staging = [
     "python-consul>=1.1.0",  # Service discovery
 ]
 
+# Ultra-lightweight staging (no MLflow monitoring)
+staging-minimal = [
+    "isa-model[cloud,storage,langchain]",
+    "influxdb-client>=1.36.0",  # Basic logging only
+    "python-logging-loki>=0.3.1",  # Centralized logging
+    "python-consul>=1.1.0",  # Service discovery
+]
+
 all = [
     "isa-model[cloud,local,training,audio,vision,langchain,storage,monitoring,k8s,gpu-cloud]",
 ]