Skip to content

Build AI methods with your coding agent, then run them anywhere: as an MCP for chatbots, as a webapp for people, or via API for your software.

Fix choice of ocr for generated and tested specs

Louis Choquelf8186d21b8a4
diff --git a/pipelex/libraries/pipelines/builder/pipe/pipe_ocr_spec.py b/pipelex/libraries/pipelines/builder/pipe/pipe_ocr_spec.py
index 5beac7584..8f2ce3723 100644
--- a/pipelex/libraries/pipelines/builder/pipe/pipe_ocr_spec.py
+++ b/pipelex/libraries/pipelines/builder/pipe/pipe_ocr_spec.py
@@ -8,7 +8,7 @@ from pipelex.pipe_operators.ocr.pipe_ocr_blueprint import PipeOcrBlueprint
from pipelex.types import StrEnum
-class RecommendedOcrPresets(StrEnum):
+class RecommendedOcrPreset(StrEnum):
BASE_OCR_MISTRAL = "base_ocr_mistral"
BASE_OCR_PYPDFIUM2 = "base_ocr_pypdfium2"
@@ -40,7 +40,7 @@ class PipeOcrSpec(PipeSpec):
type: Literal["PipeOcr"] = "PipeOcr"
category: Literal["PipeOperator"] = "PipeOperator"
the_pipe_code: str = Field(description="Pipe code. Must be snake_case.")
- ocr: RecommendedOcrPresets = Field(strict=False, description="Use one of the recommended OCR presets")
+ ocr: RecommendedOcrPreset | str = Field(description="Use one of the recommended OCR presets")
page_images: bool | None = None
page_image_captions: bool | None = None
page_views: bool | None = None
diff --git a/tests/unit/pipelex/libraries/pipelines/builder/pipe/pipe_operators/pipe_ocr/test_data.py b/tests/unit/pipelex/libraries/pipelines/builder/pipe/pipe_operators/pipe_ocr/test_data.py
index 87339d30a..653c80549 100644
--- a/tests/unit/pipelex/libraries/pipelines/builder/pipe/pipe_operators/pipe_ocr/test_data.py
+++ b/tests/unit/pipelex/libraries/pipelines/builder/pipe/pipe_operators/pipe_ocr/test_data.py
@@ -14,7 +14,7 @@ class PipeOcrTestCases:
definition="Extract text from image",
inputs={"image": InputRequirementSpec(concept="Image")},
output="ExtractedText",
- ocr="mistral-pixtral",
+ ocr="base_ocr_mistral",
),
PipeOcrBlueprint(
definition="Extract text from image",
@@ -22,7 +22,7 @@ class PipeOcrTestCases:
output="ExtractedText",
type="PipeOcr",
category="PipeOperator",
- ocr="mistral-pixtral",
+ ocr="base_ocr_mistral",
),
)
@@ -33,7 +33,7 @@ class PipeOcrTestCases:
definition="OCR with page options",
inputs={"document": InputRequirementSpec(concept="PDF")},
output="PageContent",
- ocr="tesseract",
+ ocr="base_ocr_mistral",
page_images=True,
page_image_captions=True,
page_views=True,
@@ -45,7 +45,7 @@ class PipeOcrTestCases:
output="PageContent",
type="PipeOcr",
category="PipeOperator",
- ocr="tesseract",
+ ocr="base_ocr_mistral",
),
)
diff --git a/tests/unit/pipelex/libraries/pipelines/builder/pipe/pipe_operators/pipe_ocr/test_pipe_ocr.py b/tests/unit/pipelex/libraries/pipelines/builder/pipe/pipe_operators/pipe_ocr/test_pipe_ocr.py
index f4cdfdafb..d3d63b25b 100644
--- a/tests/unit/pipelex/libraries/pipelines/builder/pipe/pipe_operators/pipe_ocr/test_pipe_ocr.py
+++ b/tests/unit/pipelex/libraries/pipelines/builder/pipe/pipe_operators/pipe_ocr/test_pipe_ocr.py
@@ -3,6 +3,7 @@ import pytest
from pipelex.libraries.pipelines.builder.pipe.pipe_ocr_spec import PipeOcrSpec
from pipelex.pipe_operators.ocr.pipe_ocr_blueprint import PipeOcrBlueprint
+from pipelex import log
from .test_data import PipeOcrTestCases
@@ -17,5 +18,6 @@ class TestPipeOcrBlueprintConversion:
pipe_spec: PipeOcrSpec,
expected_blueprint: PipeOcrBlueprint,
):
+ log.verbose(f"Testing {test_name}")
result = pipe_spec.to_blueprint()
assert result == expected_blueprint