paddleocr-haystack 0.1.0__tar.gz → 1.0.0__tar.gz

paddleocr_haystack-1.0.0/CHANGELOG.md

@@ -0,0 +1,9 @@
+# Changelog
+
+## [integrations/paddleocr-v0.1.0] - 2025-12-10
+
+### 🚀 Features
+
+- Add PaddleOCR-VL document converter (#2567)
+
+<!-- generated by git-cliff -->

{paddleocr_haystack-0.1.0 → paddleocr_haystack-1.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: paddleocr-haystack
-Version: 0.1.0
+Version: 1.0.0
 Summary: An integration of PaddleOCR with Haystack
 Project-URL: Documentation, https://github.com/haystack-core-integrations/tree/main/integrations/paddleocr#readme
 Project-URL: Issues, https://github.com/haystack-core-integrations/issues
@@ -10,14 +10,13 @@ License-Expression: Apache-2.0
 License-File: LICENSE.txt
 Classifier: Development Status :: 4 - Beta
 Classifier: Programming Language :: Python
-Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Programming Language :: Python :: Implementation :: PyPy
-Requires-Python: >=3.9
-Requires-Dist: haystack-ai>=2.19.0
+Requires-Python: >=3.10
+Requires-Dist: haystack-ai>=2.22.0
 Requires-Dist: paddleocr>=3.3.2
 Requires-Dist: paddlex[serving]>=3.3.10
 Requires-Dist: requests>=2.25.0

{paddleocr_haystack-0.1.0 → paddleocr_haystack-1.0.0}/pyproject.toml

@@ -7,7 +7,7 @@ name = "paddleocr-haystack"
 dynamic = ["version"]
 description = 'An integration of PaddleOCR with Haystack'
 readme = "README.md"
-requires-python = ">=3.9"
+requires-python = ">=3.10"
 license = "Apache-2.0"
 keywords = []
 authors = [
@@ -16,7 +16,6 @@ authors = [
 classifiers = [
   "Development Status :: 4 - Beta",
   "Programming Language :: Python",
-  "Programming Language :: Python :: 3.9",
   "Programming Language :: Python :: 3.10",
   "Programming Language :: Python :: 3.11",
   "Programming Language :: Python :: 3.12",
@@ -24,7 +23,7 @@ classifiers = [
   "Programming Language :: Python :: Implementation :: PyPy",
 ]
 dependencies = [
-  "haystack-ai>=2.19.0",
+  "haystack-ai>=2.22.0",
   "paddleocr>=3.3.2",
   "paddlex[serving]>=3.3.10",
   "requests>=2.25.0",
@@ -52,7 +51,7 @@ dependencies = ["haystack-pydoc-tools", "ruff"]
 
 [tool.hatch.envs.default.scripts]
 docs = ["pydoc-markdown pydoc/config_docusaurus.yml"]
-fmt = "ruff check --fix {args} && ruff format {args}"
+fmt = "ruff check --fix {args}; ruff format {args}"
 fmt-check = "ruff check {args} && ruff format --check {args}"
 
 [tool.hatch.envs.test]
@@ -80,7 +79,6 @@ check_untyped_defs = true
 disallow_incomplete_defs = true
 
 [tool.ruff]
-target-version = "py39"
 line-length = 120
 
 [tool.ruff.lint]
@@ -127,10 +125,6 @@ ignore = [
   "B008",
   "S101",
 ]
-unfixable = [
-  # Don't touch unused imports
-  "F401",
-]
 
 [tool.ruff.lint.isort]
 known-first-party = ["haystack_integrations"]

{paddleocr_haystack-0.1.0 → paddleocr_haystack-1.0.0}/src/haystack_integrations/components/converters/paddleocr/paddleocr_vl_document_converter.py

@@ -3,7 +3,7 @@
 # SPDX-License-Identifier: Apache-2.0
 import base64
 from pathlib import Path
-from typing import Any, Literal, Optional, Union
+from typing import Any, Literal
 
 import requests
 from haystack import Document, component, default_from_dict, default_to_dict, logging
@@ -24,7 +24,7 @@ from paddlex.inference.serving.schemas.shared.ocr import FileType  # type: ignor
 logger = logging.getLogger(__name__)
 
 
-FileTypeInput = Union[Literal["pdf", "image"], None]
+FileTypeInput = Literal["pdf", "image"] | None
 
 # Supported image file extensions
 _IMAGE_EXTENSIONS = {
@@ -41,9 +41,9 @@ _PDF_EXTENSIONS = {".pdf"}
 
 
 def _infer_file_type_from_source(
-    source: Union[str, Path, ByteStream],
-    mime_type: Optional[str] = None,
-) -> Optional[FileType]:
+    source: str | Path | ByteStream,
+    mime_type: str | None = None,
+) -> FileType | None:
     """
     Infer file type from file extension or MIME type.
 
@@ -56,7 +56,7 @@ def _infer_file_type_from_source(
         determined.
     """
     # Try to get extension from file path
-    file_path: Optional[str] = None
+    file_path: str | None = None
 
     # Check if source is a file path
     if isinstance(source, (str, Path)):
@@ -86,7 +86,7 @@ def _infer_file_type_from_source(
     return None
 
 
-def _normalize_file_type(file_type: Optional[FileTypeInput]) -> Optional[FileType]:
+def _normalize_file_type(file_type: FileTypeInput) -> FileType | None:
     """
     Normalize file type input to the numeric format expected by the API.
 
@@ -145,26 +145,26 @@ class PaddleOCRVLDocumentConverter:
         *,
         api_url: str,
         access_token: Secret = Secret.from_env_var("AISTUDIO_ACCESS_TOKEN"),
-        file_type: Optional[FileTypeInput] = None,
-        use_doc_orientation_classify: Optional[bool] = None,
-        use_doc_unwarping: Optional[bool] = None,
-        use_layout_detection: Optional[bool] = None,
-        use_chart_recognition: Optional[bool] = None,
-        layout_threshold: Optional[Union[float, dict]] = None,
-        layout_nms: Optional[bool] = None,
-        layout_unclip_ratio: Optional[Union[float, tuple[float, float], dict]] = None,
-        layout_merge_bboxes_mode: Optional[Union[str, dict]] = None,
-        prompt_label: Optional[str] = None,
-        format_block_content: Optional[bool] = None,
-        repetition_penalty: Optional[float] = None,
-        temperature: Optional[float] = None,
-        top_p: Optional[float] = None,
-        min_pixels: Optional[int] = None,
-        max_pixels: Optional[int] = None,
-        prettify_markdown: Optional[bool] = None,
-        show_formula_number: Optional[bool] = None,
-        visualize: Optional[bool] = None,
-        additional_params: Optional[dict[str, Any]] = None,
+        file_type: FileTypeInput = None,
+        use_doc_orientation_classify: bool | None = None,
+        use_doc_unwarping: bool | None = None,
+        use_layout_detection: bool | None = None,
+        use_chart_recognition: bool | None = None,
+        layout_threshold: float | dict | None = None,
+        layout_nms: bool | None = None,
+        layout_unclip_ratio: float | tuple[float, float] | dict | None = None,
+        layout_merge_bboxes_mode: str | dict | None = None,
+        prompt_label: str | None = None,
+        format_block_content: bool | None = None,
+        repetition_penalty: float | None = None,
+        temperature: float | None = None,
+        top_p: float | None = None,
+        min_pixels: int | None = None,
+        max_pixels: int | None = None,
+        prettify_markdown: bool | None = None,
+        show_formula_number: bool | None = None,
+        visualize: bool | None = None,
+        additional_params: dict[str, Any] | None = None,
     ):
         """
         Create a `PaddleOCRVLDocumentConverter` component.
@@ -372,7 +372,7 @@ class PaddleOCRVLDocumentConverter:
 
         # Prepare headers with authentication
         access_token_value = self.access_token.resolve_value() if self.access_token else None
-        headers = {"Content-Type": "application/json"}
+        headers = {"Content-Type": "application/json", "Client-Platform": "haystack"}
         if access_token_value:
             headers["Authorization"] = f"token {access_token_value}"
 
@@ -421,8 +421,8 @@ class PaddleOCRVLDocumentConverter:
     @component.output_types(documents=list[Document], raw_paddleocr_responses=list[dict[str, Any]])
     def run(
         self,
-        sources: list[Union[str, Path, ByteStream]],
-        meta: Optional[Union[dict[str, Any], list[dict[str, Any]]]] = None,
+        sources: list[str | Path | ByteStream],
+        meta: dict[str, Any] | list[dict[str, Any]] | None = None,
     ) -> dict[str, Any]:
         """
         Convert image or PDF files to Documents.
@@ -448,7 +448,7 @@ class PaddleOCRVLDocumentConverter:
 
         meta_list = normalize_metadata(meta, sources_count=len(sources))
 
-        for source, metadata in zip(sources, meta_list):
+        for source, metadata in zip(sources, meta_list, strict=True):
             try:
                 bytestream = get_bytestream_from_source(source)
             except Exception as e: