lumen-resources 0.2.2__py3-none-any.whl → 0.3.1__py3-none-any.whl

lumen_resources/__init__.py

@@ -38,25 +38,20 @@ The package follows a layered architecture:
 - CLI layer: User-friendly command-line interface
 """
 
-from .lumen_config import LumenConfig, Runtime, Region
 from .downloader import Downloader, DownloadResult
 from .exceptions import (
-    ResourceError,
     ConfigError,
     DownloadError,
+    ModelInfoError,
     PlatformUnavailableError,
+    ResourceError,
     ValidationError,
-    ModelInfoError,
 )
+from .lumen_config import LumenConfig, Region, Runtime
 from .lumen_config_validator import load_and_validate_config
-
-from .model_info import ModelInfo, Source, Runtimes, Metadata
+from .model_info import Metadata, ModelInfo, Runtimes, Source
 from .model_info_validator import load_and_validate_model_info
-from .result_schemas import (
-    EmbeddingV1,
-    FaceV1,
-    LabelsV1
-)
+from .result_schemas import OCRV1, EmbeddingV1, FaceV1, LabelsV1
 
 __version__ = "0.1.0"
 
@@ -76,6 +71,7 @@ __all__ = [
     "FaceV1",
     "EmbeddingV1",
     "LabelsV1",
+    "OCRV1",
     # Downloader
     "Downloader",
     "DownloadResult",

lumen_resources/downloader.py

@@ -183,6 +183,7 @@ class Downloader:
         patterns = [
             "model_info.json",
             "*config*",
+            "*.txt",
         ]  # Always include model_info.json and config files.
 
         if runtime == Runtime.torch:

lumen_resources/model_info.py

@@ -1,115 +1,42 @@
 # generated by datamodel-codegen:
 #   filename:  model_info-schema.json
-#   timestamp: 2025-10-19T06:58:43+00:00
+#   timestamp: 2025-12-11T07:52:17+00:00
 
 from __future__ import annotations
 
 from datetime import date
 from enum import Enum
+from typing import Any
 
 from pydantic import AwareDatetime, BaseModel, ConfigDict, Field
 
 
 class Format(Enum):
-    """Model source format type.
-
-    Defines the format and source platform for a model. Different formats
-    have different loading mechanisms and repository structures.
-
-    Attributes:
-        huggingface: Hugging Face Hub model format.
-        openclip: OpenCLIP model format.
-        modelscope: ModelScope model format.
-        custom: Custom model format.
-
-    Example:
-        >>> source = Source(format=Format.huggingface, repo_id="openai/clip-vit-base-patch32")
-        >>> print(source.format.value)
-        'huggingface'
-    """
-
-    huggingface = "huggingface"
-    openclip = "openclip"
-    modelscope = "modelscope"
-    custom = "custom"
+    huggingface = 'huggingface'
+    openclip = 'openclip'
+    modelscope = 'modelscope'
+    custom = 'custom'
 
 
 class Source(BaseModel):
-    """Model source information.
-
-    Contains information about where and how to obtain the model, including
-    the format type and repository identifier.
-
-    Attributes:
-        format: Model format type (huggingface, openclip, modelscope, custom).
-        repo_id: Repository identifier for the model source.
-
-    Example:
-        >>> source = Source(
-        ...     format=Format.huggingface,
-        ...     repo_id="openai/clip-vit-base-patch32"
-        ... )
-        >>> print(source.repo_id)
-        'openai/clip-vit-base-patch32'
-    """
-
     model_config = ConfigDict(
-        extra="forbid",
+        extra='forbid',
     )
     format: Format
-    repo_id: str = Field(
-        ..., description="Repository identifier for model source", min_length=1
-    )
+    repo_id: str = Field(..., min_length=1)
+    """
+    Repository identifier for model source
+    """
 
 
 class Requirements(BaseModel):
-    """Python environment requirements for model runtime.
-
-    Specifies the Python version and package dependencies required to run
-    the model in a specific runtime configuration.
-
-    Attributes:
-        python: Minimum Python version requirement.
-        dependencies: List of required Python package dependencies.
-
-    Example:
-        >>> req = Requirements(
-        ...     python=">=3.8",
-        ...     dependencies=["torch", "transformers", "pillow"]
-        ... )
-        >>> print(req.python)
-        '>=3.8'
-    """
-
     python: str | None = None
     dependencies: list[str] | None = None
 
 
 class Runtimes(BaseModel):
-    """Runtime configuration for a specific model execution environment.
-
-    Defines the availability, file requirements, device compatibility, and
-    dependencies for a model runtime (e.g., torch, onnx, rknn).
-
-    Attributes:
-        available: Whether this runtime is available for the model.
-        files: List of required files or dict mapping runtime to file lists.
-        devices: List of compatible devices for this runtime.
-        requirements: Python environment requirements for this runtime.
-
-    Example:
-        >>> runtime = Runtimes(
-        ...     available=True,
-        ...     files=["model.pt", "config.json"],
-        ...     devices=["cuda", "cpu"],
-        ...     requirements=Requirements(python=">=3.8", dependencies=["torch"])
-        ... )
-        >>> print(runtime.available)
-        True
-    """
-
     model_config = ConfigDict(
-        extra="forbid",
+        extra='forbid',
     )
     available: bool
     files: list[str] | dict[str, list[str]] | None = None
@@ -118,56 +45,16 @@ class Runtimes(BaseModel):
 
 
 class Datasets(BaseModel):
-    """Dataset configuration for model evaluation and inference.
-
-    Defines the label and embedding datasets used for zero-shot classification
-    or other dataset-specific model operations.
-
-    Attributes:
-        labels: Dataset identifier for class labels.
-        embeddings: Dataset identifier for embeddings.
-
-    Example:
-        >>> dataset = Datasets(
-        ...     labels="imagenet1k_labels",
-        ...     embeddings="imagenet1k_embeddings"
-        ... )
-        >>> print(dataset.labels)
-        'imagenet1k_labels'
-    """
-
     model_config = ConfigDict(
-        extra="forbid",
+        extra='forbid',
     )
     labels: str
     embeddings: str
 
 
 class Metadata(BaseModel):
-    """Model metadata information.
-
-    Contains descriptive metadata about the model including licensing,
-    authorship, creation dates, and categorization tags.
-
-    Attributes:
-        license: License identifier for the model.
-        author: Model author or organization.
-        created_at: Model creation date.
-        updated_at: Last model update timestamp.
-        tags: List of descriptive tags for categorization.
-
-    Example:
-        >>> metadata = Metadata(
-        ...     license="MIT",
-        ...     author="OpenAI",
-        ...     tags=["computer-vision", "multimodal", "clip"]
-        ... )
-        >>> print(metadata.license)
-        'MIT'
-    """
-
     model_config = ConfigDict(
-        extra="forbid",
+        extra='forbid',
     )
     license: str | None = None
     author: str | None = None
@@ -177,57 +64,38 @@ class Metadata(BaseModel):
 
 
 class ModelInfo(BaseModel):
-    """Schema for Lumen AI model configuration files.
-
-    Complete model definition including source information, runtime configurations,
-    dataset compatibility, and metadata. This is the top-level schema for
-    model_info.json files.
-
-    Attributes:
-        name: Model name identifier, also OpenCLIP model identifier if applicable.
-        version: Model version following semantic versioning (X.Y.Z).
-        description: Model description and purpose.
-        model_type: Type/category of the model.
-        embedding_dim: Dimension of the model's embedding space.
-        source: Model source information including format and repository.
-        runtimes: Dictionary mapping runtime names to runtime configurations.
-        datasets: Optional dataset configurations for model evaluation.
-        metadata: Optional model metadata including license and author.
-
-    Example:
-        >>> model_info = ModelInfo(
-        ...     name="ViT-B-32",
-        ...     version="1.0.0",
-        ...     description="Vision Transformer for CLIP",
-        ...     model_type="vision-transformer",
-        ...     embedding_dim=512,
-        ...     source=Source(format=Format.huggingface, repo_id="openai/clip-vit-base-patch32"),
-        ...     runtimes={"torch": Runtimes(available=True)}
-        ... )
-        >>> print(model_info.name)
-        'ViT-B-32'
+    """
+    Schema for Lumen AI model configuration files
     """
 
     model_config = ConfigDict(
-        extra="forbid",
-    )
-    name: str = Field(
-        ...,
-        description="Model name identifier, this is also openclip model identifier if openclip is set as source format",
-        max_length=100,
-        min_length=1,
-    )
-    version: str = Field(
-        ..., description="Model version", pattern="^[0-9]+\\.[0-9]+\\.[0-9]+$"
-    )
-    description: str = Field(
-        ..., description="Model description and purpose", max_length=500, min_length=1
-    )
-    model_type: str = Field(..., description="Type of the model")
-    embedding_dim: int = Field(
-        ..., description="Dimension of the embedding space", ge=1, le=100000
+        extra='forbid',
     )
+    name: str = Field(..., max_length=100, min_length=1)
+    """
+    Model name identifier, this is also openclip model identifier if openclip is set as source format
+    """
+    version: str = Field(..., pattern='^[0-9]+\\.[0-9]+\\.[0-9]+$')
+    """
+    Model version
+    """
+    description: str = Field(..., max_length=500, min_length=1)
+    """
+    Model description and purpose
+    """
+    model_type: str
+    """
+    Type of the model
+    """
+    embedding_dim: int | None = Field(None, ge=1, le=100000)
+    """
+    Dimension of the embedding space
+    """
     source: Source
     runtimes: dict[str, Runtimes]
     datasets: dict[str, Datasets] | None = None
+    extra_metadata: dict[str, Any] | None = None
+    """
+    Additional model-specific configuration and metadata
+    """
     metadata: Metadata | None = None

lumen_resources/result_schemas/__init__.py

@@ -1,14 +1,11 @@
 # generated by datamodel-codegen:
 #   filename:  result_schemas
-#   timestamp: 2025-11-28T17:04:43+00:00
+#   timestamp: 2025-12-10T15:13:26+00:00
 
 
 from .embedding_v1 import EmbeddingV1
 from .face_v1 import FaceV1
 from .labels_v1 import LabelsV1
+from .ocr_v1 import OCRV1
 
-__all__ = [
-    "FaceV1",
-    "EmbeddingV1",
-    "LabelsV1",
-]
+__all__ = ["FaceV1", "EmbeddingV1", "LabelsV1", "OCRV1"]

lumen_resources/result_schemas/embedding_v1.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  embedding_v1.json
-#   timestamp: 2025-11-28T17:04:43+00:00
+#   timestamp: 2025-12-10T15:13:26+00:00
 
 from __future__ import annotations
 

lumen_resources/result_schemas/face_v1.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  face_v1.json
-#   timestamp: 2025-11-28T17:04:43+00:00
+#   timestamp: 2025-12-10T15:13:26+00:00
 
 from __future__ import annotations
 

lumen_resources/result_schemas/labels_v1.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  labels_v1.json
-#   timestamp: 2025-11-28T17:04:43+00:00
+#   timestamp: 2025-12-10T15:13:26+00:00
 
 from __future__ import annotations
 

lumen_resources/result_schemas/ocr_v1.py

@@ -0,0 +1,54 @@
+# generated by datamodel-codegen:
+#   filename:  ocr_v1.json
+#   timestamp: 2025-12-10T15:13:26+00:00
+
+from __future__ import annotations
+
+from pydantic import BaseModel, ConfigDict, Field, RootModel
+
+
+class BoxItem(RootModel[list[int]]):
+    root: list[int] = Field(..., max_length=2, min_length=2)
+    """
+    Point coordinates [x, y]
+    """
+
+
+class Item(BaseModel):
+    model_config = ConfigDict(
+        extra='forbid',
+    )
+    box: list[BoxItem] = Field(..., min_length=3)
+    """
+    Polygon coordinates defining the text region (usually 4 points for rotated rectangle: TL, TR, BR, BL)
+    """
+    text: str
+    """
+    Recognized text content
+    """
+    confidence: float = Field(..., ge=0.0, le=1.0)
+    """
+    Recognition confidence score
+    """
+
+
+class OCRV1(BaseModel):
+    """
+    Universal schema for OCR text detection and recognition responses across Lumen services
+    """
+
+    model_config = ConfigDict(
+        extra='forbid',
+    )
+    items: list[Item]
+    """
+    Detected text regions with content and metadata
+    """
+    count: int = Field(..., ge=0)
+    """
+    Number of detected text regions
+    """
+    model_id: str = Field(..., min_length=1)
+    """
+    Model identifier (combined detection and recognition models)
+    """

lumen_resources/schemas/model_info-schema.json

@@ -9,7 +9,6 @@
         "version",
         "description",
         "model_type",
-        "embedding_dim",
         "source",
         "runtimes"
     ],
@@ -135,6 +134,11 @@
             },
             "additionalProperties": false
         },
+        "extra_metadata": {
+            "type": "object",
+            "description": "Additional model-specific configuration and metadata",
+            "additionalProperties": true
+        },
         "metadata": {
             "type": "object",
             "properties": {

lumen_resources/schemas/result_schemas/ocr_v1.json

@@ -0,0 +1,55 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "title": "OCRV1",
+  "description": "Universal schema for OCR text detection and recognition responses across Lumen services",
+  "type": "object",
+  "properties": {
+    "items": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "box": {
+            "type": "array",
+            "items": {
+              "type": "array",
+              "items": {
+                "type": "integer"
+              },
+              "minItems": 2,
+              "maxItems": 2,
+              "description": "Point coordinates [x, y]"
+            },
+            "minItems": 3,
+            "description": "Polygon coordinates defining the text region (usually 4 points for rotated rectangle: TL, TR, BR, BL)"
+          },
+          "text": {
+            "type": "string",
+            "description": "Recognized text content"
+          },
+          "confidence": {
+            "type": "number",
+            "minimum": 0.0,
+            "maximum": 1.0,
+            "description": "Recognition confidence score"
+          }
+        },
+        "required": ["box", "text", "confidence"],
+        "additionalProperties": false
+      },
+      "description": "Detected text regions with content and metadata"
+    },
+    "count": {
+      "type": "integer",
+      "minimum": 0,
+      "description": "Number of detected text regions"
+    },
+    "model_id": {
+      "type": "string",
+      "minLength": 1,
+      "description": "Model identifier (combined detection and recognition models)"
+    }
+  },
+  "required": ["items", "count", "model_id"],
+  "additionalProperties": false
+}

{lumen_resources-0.2.2.dist-info → lumen_resources-0.3.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: lumen-resources
-Version: 0.2.2
+Version: 0.3.1
 Summary: Unified model resource management for Lumen ML services
 Author-email: EdwinZhanCN <support@lumilio.org>
 License: MIT

lumen_resources-0.3.1.dist-info/RECORD

@@ -0,0 +1,26 @@
+lumen_resources/__init__.py,sha256=yS4AldwTQlRYfu35DlqBlnoSNXyGw0G0P41AUlZyFac,2687
+lumen_resources/cli.py,sha256=gGGfe0BmqjZX-2fIEEQ-MgElMn21OrabPs7Fcu6aY6A,14204
+lumen_resources/downloader.py,sha256=nQtYcCfSHdWpCqB9zy6-Ri0Ot7j8Hdz--F4oNNPa04Q,17655
+lumen_resources/exceptions.py,sha256=cUS76Revda0Vt6rPeUNLI2QhluNyLon1GiF5ZM4Kx30,3148
+lumen_resources/lumen_config.py,sha256=EtWdlWiN6sP8QZxJfw3mZZKkN_9Kh6aRl-EeC4iSpKg,14814
+lumen_resources/lumen_config_validator.py,sha256=6ZaCVZViEPSDTfbke37P0bDSNI7hE5K8H17bv1V8KSE,9734
+lumen_resources/model_info.py,sha256=O7LRJnC2OJ5uAuic074hzWThruHhVyMg5Kt7eNAdZQ4,2355
+lumen_resources/model_info_validator.py,sha256=91QsUCRuxZT3wCt7xI3wsLVBmEiVXxJUk8d2MOHwNb0,9294
+lumen_resources/platform.py,sha256=EwqjQMoQY2jK0VP1jstgIW_Lu82Cxn9HDxwdCj1EN8w,9824
+lumen_resources/result_schemas/README.md,sha256=nPbihM4RCJxFbBHyUsRYLljyaRjULuMQgW6K1nWYGy0,384
+lumen_resources/result_schemas/__init__.py,sha256=7nsrPKQE9WN39-DwTSrir4sZD7IiDlxfuY12TPKbJ8s,289
+lumen_resources/result_schemas/embedding_v1.py,sha256=VtU4Uy_tTKDIKy4cKZxH_rp_L6VGDlz-ptUbWBwkebw,671
+lumen_resources/result_schemas/face_v1.py,sha256=d-cHhkwvrKw4x7CT_UsihIpDrnxuqnkrnQ38_I3ZfvI,1314
+lumen_resources/result_schemas/labels_v1.py,sha256=S8hgrcJs1XlxOibfgeqiXcNv2epdShuN83kuunQEVbw,829
+lumen_resources/result_schemas/ocr_v1.py,sha256=XddG9tKp2Nw77NEGmRTYGJFoFbXfLFjoPJFzYuiLtAI,1259
+lumen_resources/schemas/config-schema.yaml,sha256=FC4Iz4O-nzAvFXkGMhLkAxy2-efq47wPgcID962Vjx4,8167
+lumen_resources/schemas/model_info-schema.json,sha256=VkARnNvzdFKee_AROQG9AUU5Q9s2P_dt7Nvm9Mj39aU,5837
+lumen_resources/schemas/result_schemas/embedding_v1.json,sha256=6iZaXbmkP0J5fXGD4Gkrt6AZPvpK6FZaQ754sOXxFrc,841
+lumen_resources/schemas/result_schemas/face_v1.json,sha256=XcnHxwP_KR8lAv6s6npjWQxwyYAQTuBLEKrvlOqH84g,1771
+lumen_resources/schemas/result_schemas/labels_v1.json,sha256=AnOiM0VCuIKrLdrbA73pmu4QD4QaHIDNsANeU3BIOeg,1222
+lumen_resources/schemas/result_schemas/ocr_v1.json,sha256=btVUZjR_RW4CLJjIyEGCITPJFJxMqGSM7QX8OyfVguo,1653
+lumen_resources-0.3.1.dist-info/METADATA,sha256=Al6kVXuTCVTb0TxP6_BbcxaeHIEjAVLumZMpsSs0Bi0,4002
+lumen_resources-0.3.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+lumen_resources-0.3.1.dist-info/entry_points.txt,sha256=fLCrIB9BxyIDAbJVqDGW4QyvLPlvL53WI-6lkTZ3h2M,61
+lumen_resources-0.3.1.dist-info/top_level.txt,sha256=XgLNoNrF2RIpI2sYIpjLuUREYRVHW13ElHoCnFYHjAQ,16
+lumen_resources-0.3.1.dist-info/RECORD,,

lumen_resources-0.2.2.dist-info/RECORD

@@ -1,24 +0,0 @@
-lumen_resources/__init__.py,sha256=vwiadtQgIE2Dopk1bQBahH-9JBdLrMjxPQTzRn0BJ-k,2684
-lumen_resources/cli.py,sha256=gGGfe0BmqjZX-2fIEEQ-MgElMn21OrabPs7Fcu6aY6A,14204
-lumen_resources/downloader.py,sha256=h9ch7O2BdMnqxnOd8tDstAVcPLBErVVnnTSJN9veABQ,17634
-lumen_resources/exceptions.py,sha256=cUS76Revda0Vt6rPeUNLI2QhluNyLon1GiF5ZM4Kx30,3148
-lumen_resources/lumen_config.py,sha256=EtWdlWiN6sP8QZxJfw3mZZKkN_9Kh6aRl-EeC4iSpKg,14814
-lumen_resources/lumen_config_validator.py,sha256=6ZaCVZViEPSDTfbke37P0bDSNI7hE5K8H17bv1V8KSE,9734
-lumen_resources/model_info.py,sha256=qHvwJbU2h-Fdr5iCJLfjZMIc5FKlXTg6hrN0CVEZFVo,7259
-lumen_resources/model_info_validator.py,sha256=91QsUCRuxZT3wCt7xI3wsLVBmEiVXxJUk8d2MOHwNb0,9294
-lumen_resources/platform.py,sha256=EwqjQMoQY2jK0VP1jstgIW_Lu82Cxn9HDxwdCj1EN8w,9824
-lumen_resources/result_schemas/README.md,sha256=nPbihM4RCJxFbBHyUsRYLljyaRjULuMQgW6K1nWYGy0,384
-lumen_resources/result_schemas/__init__.py,sha256=CnpSCH01YXBIW9BQH1xmcqIDNTf5-IDJ1G7k-ZTF6D4,269
-lumen_resources/result_schemas/embedding_v1.py,sha256=RJXVNWt8Qv-6ZvKqqddacGoIszy6n9Z3PQ1rsIPbcYs,671
-lumen_resources/result_schemas/face_v1.py,sha256=fkT2cD59NDpIVvMhdPMz22zH7d42FGgzlc957NPBPPI,1314
-lumen_resources/result_schemas/labels_v1.py,sha256=8GsqQlWH1G--pptrPwo8124D1xUc5gXtn95OolLwE0k,829
-lumen_resources/schemas/config-schema.yaml,sha256=FC4Iz4O-nzAvFXkGMhLkAxy2-efq47wPgcID962Vjx4,8167
-lumen_resources/schemas/model_info-schema.json,sha256=Qee-Pd6XdVSaij6Cqxn1GaSMRIrPRp0rvTPfWTp_8ms,5669
-lumen_resources/schemas/result_schemas/embedding_v1.json,sha256=6iZaXbmkP0J5fXGD4Gkrt6AZPvpK6FZaQ754sOXxFrc,841
-lumen_resources/schemas/result_schemas/face_v1.json,sha256=XcnHxwP_KR8lAv6s6npjWQxwyYAQTuBLEKrvlOqH84g,1771
-lumen_resources/schemas/result_schemas/labels_v1.json,sha256=AnOiM0VCuIKrLdrbA73pmu4QD4QaHIDNsANeU3BIOeg,1222
-lumen_resources-0.2.2.dist-info/METADATA,sha256=eHfm1uBIZVpkv39QvceEoOiXupgt5uzYE4c8LSaG8z0,4002
-lumen_resources-0.2.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-lumen_resources-0.2.2.dist-info/entry_points.txt,sha256=fLCrIB9BxyIDAbJVqDGW4QyvLPlvL53WI-6lkTZ3h2M,61
-lumen_resources-0.2.2.dist-info/top_level.txt,sha256=XgLNoNrF2RIpI2sYIpjLuUREYRVHW13ElHoCnFYHjAQ,16
-lumen_resources-0.2.2.dist-info/RECORD,,