openparser-sdk 1.0.24__tar.gz → 1.0.26__tar.gz

{openparser_sdk-1.0.24 → openparser_sdk-1.0.26}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: openparser-sdk
-Version: 1.0.24
+Version: 1.0.26
 Summary: Parse documents and extract structured data with Python
 Project-URL: Homepage, https://openparser.dev
 Project-URL: Documentation, https://docs.openparser.dev
@@ -131,7 +131,7 @@ derivation DAG:
 ```python
 extracted = client.extract.sync(
     {
-        "ocr_model": "mistral-ocr-4",
+        "ocr_model": "mistral-ocr-4-1",
         "llm_model": "openai/gpt-6-luna",
         "grounding": "field",
         "schema": {

{openparser_sdk-1.0.24 → openparser_sdk-1.0.26}/README.md

@@ -94,7 +94,7 @@ derivation DAG:
 ```python
 extracted = client.extract.sync(
     {
-        "ocr_model": "mistral-ocr-4",
+        "ocr_model": "mistral-ocr-4-1",
         "llm_model": "openai/gpt-6-luna",
         "grounding": "field",
         "schema": {

{openparser_sdk-1.0.24 → openparser_sdk-1.0.26}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "openparser-sdk"
-version = "1.0.24"
+version = "1.0.26"
 description = "Parse documents and extract structured data with Python"
 readme = "README.md"
 requires-python = ">=3.10"

{openparser_sdk-1.0.24 → openparser_sdk-1.0.26}/src/openparser/_telemetry.py

@@ -6,7 +6,7 @@ import platform
 import sys
 
 SDK_LANGUAGE = "python"
-SDK_VERSION = "1.0.24"
+SDK_VERSION = "1.0.26"
 
 
 def _detect_runtime() -> str:

{openparser_sdk-1.0.24 → openparser_sdk-1.0.26}/src/openparser/hosted_models.py

@@ -14,6 +14,7 @@ from typing_extensions import NotRequired
 
 HostedOcrModelId = Literal[
     "paddleocr-vl-1.6",
+    "glm-ocr",
     "mistral-ocr-4-1",
     "mistral-ocr-4",
     "mistral-ocr-3",
@@ -27,6 +28,7 @@ HostedOcrModelId = Literal[
 
 HOSTED_OCR_MODEL_IDS: tuple[HostedOcrModelId, ...] = (
     "paddleocr-vl-1.6",
+    "glm-ocr",
     "mistral-ocr-4-1",
     "mistral-ocr-4",
     "mistral-ocr-3",
@@ -52,6 +54,13 @@ class PaddleocrVl16Options(TypedDict):
     # Merge layout blocks: Merge nearby boxes for reading order.
     merge_layout_blocks: NotRequired[bool]
 
+class GlmOcrOptions(TypedDict):
+    """Hosted ocr_options for glm-ocr (GLM-OCR).
+
+    Output: Markdown + boxes.
+    """
+    pass
+
 class MistralOcr41Options(TypedDict):
     """Hosted ocr_options for mistral-ocr-4-1 (Mistral OCR 4.1).
 
@@ -199,6 +208,7 @@ class AwsTextractTablesLayoutOptions(TypedDict):
 # Mapping used by type checkers / docs; values are TypedDict types, not instances.
 HOSTED_OCR_OPTIONS_BY_MODEL: Mapping[HostedOcrModelId, type] = {
     "paddleocr-vl-1.6": PaddleocrVl16Options,
+    "glm-ocr": GlmOcrOptions,
     "mistral-ocr-4-1": MistralOcr41Options,
     "mistral-ocr-4": MistralOcr4Options,
     "mistral-ocr-3": MistralOcr3Options,
@@ -234,6 +244,27 @@ HOSTED_OCR_MODEL_CATALOG_SUMMARY: dict[str, dict[str, Any]] = {
             "text_annotations": "none",
         },
     },
+    "glm-ocr": {
+        "id": "glm-ocr",
+        "label": "GLM-OCR",
+        "is_default": False,
+        "output_summary": "Markdown + boxes",
+        "capabilities": {
+            "parse": True,
+            "extract_source": True,
+            "markdown": True,
+            "regions": True,
+            "options": {
+
+            },
+        },
+        "converter": {
+            "element_kinds": ("text", "table", "figure", "formula", "stamp"),
+            "geometry": "optional",
+            "assets": "optional",
+            "text_annotations": "none",
+        },
+    },
     "mistral-ocr-4-1": {
         "id": "mistral-ocr-4-1",
         "label": "Mistral OCR 4.1",
@@ -471,6 +502,16 @@ def hosted_parse_request(
     output_format: Literal["openparser@1", "raw"] | None = None,
 ) -> dict[str, Any]: ...
 
+@overload
+def hosted_parse_request(
+    ocr_model: Literal["glm-ocr"],
+    /,
+    *,
+    ocr_options: GlmOcrOptions | None = None,
+    file_id: str | None = None,
+    output_format: Literal["openparser@1", "raw"] | None = None,
+) -> dict[str, Any]: ...
+
 @overload
 def hosted_parse_request(
     ocr_model: Literal["mistral-ocr-4-1"],
@@ -601,6 +642,7 @@ __all__ = [
     "HOSTED_OCR_MODEL_IDS",
     "DEFAULT_HOSTED_OCR_MODEL_ID",
     "PaddleocrVl16Options",
+    "GlmOcrOptions",
     "MistralOcr41Options",
     "MistralOcr4Options",
     "MistralOcr3Options",