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.
Feature/small tweaks (#557)
Louis Choquel3ef97715c5c8
diff --git a/.blackboxrules b/.blackboxrulesindex 402bd7140..b34c89a60 100644--- a/.blackboxrules+++ b/.blackboxrules@@ -20,6 +20,14 @@Always fix any issues reported by these tools before proceeding.+### Cleaning Derived Files++ If you need to clean derived files and caches, typically after you erased files or moved tests, the linters can get confused, the pytest collection can be off...++ ```bash+ make cleanderived+ ```+### Running TestsAfter you're finished making code changes, you must always run tests using `make test-xdist`.@@ -139,7 +147,16 @@ This document outlines the core coding standards, best practices, and quality co- Import all necessary libraries at the top of the file- Do not import libraries in functions or classes unless in very specific cases, to be discussed with the user, as they would required a `# noqa: ...` comment to pass linting- - Do not bother with ordering the imports, our Ruff linter will handle it for us. Same goes with removing unused imports.+ - Do not bother with ordering the imports, our Ruff linter will handle it for us.++#### **Removing unused imports**++ - To remove unused imports, run `make fix-unused-imports` or `make fui` (shorthand). This is faster and cheaper than rewriting with LLM.++#### **No re-exports in `__init__.py`**++ - Do NOT fill `__init__.py` files with re-exports.+ - Always use direct full-path imports everywhere. For example:- **Logging and Pretty Printing**:@@ -254,6 +271,7 @@ NEVER USE unittest.mock. YOU MUST USE pytest-mock instead.- `tests/integration/` - for integration tests that test component interactions- `tests/e2e/` - for end-to-end tests that test complete workflows- `tests/test_pipelines/` - for test pipeline definitions (PLX files and their structuring python files)+- Do NOT add `__init__.py` files to test directories. Test directories do not need to be Python packages.- Fixtures are defined in conftest.py modules at different levels of the hierarchy, their scope is handled by pytest- Test data is placed inside test_data.py at different levels of the hierarchy, they must be imported with package paths from the root like `from tests.integration.pipelex.cogt.test_data`. Their content is all constants, regrouped inside classes to keep things tidy.- Always put test inside Test classes: 1 TestClass per module.diff --git a/.cursor/rules/commands.mdc b/.cursor/rules/commands.mdcindex 48817b5fa..2db239c35 100644--- a/.cursor/rules/commands.mdc+++ b/.cursor/rules/commands.mdc@@ -21,6 +21,14 @@ description: Guidelines for running commandsAlways fix any issues reported by these tools before proceeding.+## Cleaning Derived Files++ If you need to clean derived files and caches, typically after you erased files or moved tests, the linters can get confused, the pytest collection can be off...++ ```bash+ make cleanderived+ ```+## Running TestsAfter you're finished making code changes, you must always run tests using `make test-xdist`.diff --git a/.cursor/rules/pytest_standards.mdc b/.cursor/rules/pytest_standards.mdcindex 3c5d361b8..c597b959b 100644--- a/.cursor/rules/pytest_standards.mdc+++ b/.cursor/rules/pytest_standards.mdc@@ -18,6 +18,7 @@ NEVER USE unittest.mock. YOU MUST USE pytest-mock instead.- `tests/integration/` - for integration tests that test component interactions- `tests/e2e/` - for end-to-end tests that test complete workflows- `tests/test_pipelines/` - for test pipeline definitions (PLX files and their structuring python files)+- Do NOT add `__init__.py` files to test directories. Test directories do not need to be Python packages.- Fixtures are defined in conftest.py modules at different levels of the hierarchy, their scope is handled by pytest- Test data is placed inside test_data.py at different levels of the hierarchy, they must be imported with package paths from the root like `from tests.integration.pipelex.cogt.test_data`. Their content is all constants, regrouped inside classes to keep things tidy.- Always put test inside Test classes: 1 TestClass per module.diff --git a/.cursor/rules/python_standards.mdc b/.cursor/rules/python_standards.mdcindex 37bef5c88..03c24d7d9 100644--- a/.cursor/rules/python_standards.mdc+++ b/.cursor/rules/python_standards.mdc@@ -36,7 +36,16 @@ This document outlines the core coding standards, best practices, and quality co- Import all necessary libraries at the top of the file- Do not import libraries in functions or classes unless in very specific cases, to be discussed with the user, as they would required a `# noqa: ...` comment to pass linting- - Do not bother with ordering the imports, our Ruff linter will handle it for us. Same goes with removing unused imports.+ - Do not bother with ordering the imports, our Ruff linter will handle it for us.++### **Removing unused imports**++ - To remove unused imports, run `make fix-unused-imports` or `make fui` (shorthand). This is faster and cheaper than rewriting with LLM.++### **No re-exports in `__init__.py`**++ - Do NOT fill `__init__.py` files with re-exports.+ - Always use direct full-path imports everywhere. For example:- **Logging and Pretty Printing**:diff --git a/.github/copilot-instructions.md b/.github/copilot-instructions.mdindex 402bd7140..b34c89a60 100644--- a/.github/copilot-instructions.md+++ b/.github/copilot-instructions.md@@ -20,6 +20,14 @@Always fix any issues reported by these tools before proceeding.+### Cleaning Derived Files++ If you need to clean derived files and caches, typically after you erased files or moved tests, the linters can get confused, the pytest collection can be off...++ ```bash+ make cleanderived+ ```+### Running TestsAfter you're finished making code changes, you must always run tests using `make test-xdist`.@@ -139,7 +147,16 @@ This document outlines the core coding standards, best practices, and quality co- Import all necessary libraries at the top of the file- Do not import libraries in functions or classes unless in very specific cases, to be discussed with the user, as they would required a `# noqa: ...` comment to pass linting- - Do not bother with ordering the imports, our Ruff linter will handle it for us. Same goes with removing unused imports.+ - Do not bother with ordering the imports, our Ruff linter will handle it for us.++#### **Removing unused imports**++ - To remove unused imports, run `make fix-unused-imports` or `make fui` (shorthand). This is faster and cheaper than rewriting with LLM.++#### **No re-exports in `__init__.py`**++ - Do NOT fill `__init__.py` files with re-exports.+ - Always use direct full-path imports everywhere. For example:- **Logging and Pretty Printing**:@@ -254,6 +271,7 @@ NEVER USE unittest.mock. YOU MUST USE pytest-mock instead.- `tests/integration/` - for integration tests that test component interactions- `tests/e2e/` - for end-to-end tests that test complete workflows- `tests/test_pipelines/` - for test pipeline definitions (PLX files and their structuring python files)+- Do NOT add `__init__.py` files to test directories. Test directories do not need to be Python packages.- Fixtures are defined in conftest.py modules at different levels of the hierarchy, their scope is handled by pytest- Test data is placed inside test_data.py at different levels of the hierarchy, they must be imported with package paths from the root like `from tests.integration.pipelex.cogt.test_data`. Their content is all constants, regrouped inside classes to keep things tidy.- Always put test inside Test classes: 1 TestClass per module.diff --git a/.pipelex/inference/backends/internal.toml b/.pipelex/inference/backends/internal.tomlindex 2d30b7fe0..e44b2227f 100644--- a/.pipelex/inference/backends/internal.toml+++ b/.pipelex/inference/backends/internal.toml@@ -19,7 +19,7 @@################################################################################# --- PyPDFium2 Text Extractor --------------------------------------------------[pypdfium2-extract-text]+[pypdfium2-extract-pdf]model_type = "text_extractor"sdk = "pypdfium2"model_id = "extract-text"diff --git a/.pipelex/inference/deck/base_deck.toml b/.pipelex/inference/deck/base_deck.tomlindex bb28c3a96..c194c36ad 100644--- a/.pipelex/inference/deck/base_deck.toml+++ b/.pipelex/inference/deck/base_deck.toml@@ -111,7 +111,7 @@ cheap_llm_for_creativity = [pdf_text_extractor = ["azure-document-intelligence","mistral-ocr",- "pypdfium2-extract-text",+ "pypdfium2-extract-pdf",]image_text_extractor = ["mistral-ocr"]@@ -173,11 +173,11 @@ for_object = "cheap_llm_for_structured"####################################################################################################[extract]-choice_default = "extract_text_from_visuals"+choice_default = "extract_ocr_from_document"[extract.presets]-extract_text_from_visuals = { model = "azure-document-intelligence", max_nb_images = 100, image_min_size = 50 }-extract_text_from_pdf = { model = "pypdfium2-extract-text", max_nb_images = 100, image_min_size = 50 }+extract_ocr_from_document = { model = "azure-document-intelligence", max_nb_images = 100, image_min_size = 50 }+extract_basic_from_pdf = { model = "pypdfium2-extract-pdf", max_nb_images = 100, image_min_size = 50 }##################################################################################################### Image Generation Presetsdiff --git a/.windsurfrules.md b/.windsurfrules.mdindex 402bd7140..b34c89a60 100644--- a/.windsurfrules.md+++ b/.windsurfrules.md@@ -20,6 +20,14 @@Always fix any issues reported by these tools before proceeding.+### Cleaning Derived Files++ If you need to clean derived files and caches, typically after you erased files or moved tests, the linters can get confused, the pytest collection can be off...++ ```bash+ make cleanderived+ ```+### Running TestsAfter you're finished making code changes, you must always run tests using `make test-xdist`.@@ -139,7 +147,16 @@ This document outlines the core coding standards, best practices, and quality co- Import all necessary libraries at the top of the file- Do not import libraries in functions or classes unless in very specific cases, to be discussed with the user, as they would required a `# noqa: ...` comment to pass linting- - Do not bother with ordering the imports, our Ruff linter will handle it for us. Same goes with removing unused imports.+ - Do not bother with ordering the imports, our Ruff linter will handle it for us.++#### **Removing unused imports**++ - To remove unused imports, run `make fix-unused-imports` or `make fui` (shorthand). This is faster and cheaper than rewriting with LLM.++#### **No re-exports in `__init__.py`**++ - Do NOT fill `__init__.py` files with re-exports.+ - Always use direct full-path imports everywhere. For example:- **Logging and Pretty Printing**:@@ -254,6 +271,7 @@ NEVER USE unittest.mock. YOU MUST USE pytest-mock instead.- `tests/integration/` - for integration tests that test component interactions- `tests/e2e/` - for end-to-end tests that test complete workflows- `tests/test_pipelines/` - for test pipeline definitions (PLX files and their structuring python files)+- Do NOT add `__init__.py` files to test directories. Test directories do not need to be Python packages.- Fixtures are defined in conftest.py modules at different levels of the hierarchy, their scope is handled by pytest- Test data is placed inside test_data.py at different levels of the hierarchy, they must be imported with package paths from the root like `from tests.integration.pipelex.cogt.test_data`. Their content is all constants, regrouped inside classes to keep things tidy.- Always put test inside Test classes: 1 TestClass per module.diff --git a/AGENTS.md b/AGENTS.mdindex 051c86aee..dbdeb9260 100644--- a/AGENTS.md+++ b/AGENTS.md@@ -20,6 +20,14 @@Always fix any issues reported by these tools before proceeding.+### Cleaning Derived Files++ If you need to clean derived files and caches, typically after you erased files or moved tests, the linters can get confused, the pytest collection can be off...++ ```bash+ make cleanderived+ ```+### Running Tests in Codex CloudTo test everything that can be tested from within the Codex Cloud sandbox, run this:@@ -96,7 +104,16 @@ This document outlines the core coding standards, best practices, and quality co- Import all necessary libraries at the top of the file- Do not import libraries in functions or classes unless in very specific cases, to be discussed with the user, as they would required a `# noqa: ...` comment to pass linting- - Do not bother with ordering the imports, our Ruff linter will handle it for us. Same goes with removing unused imports.+ - Do not bother with ordering the imports, our Ruff linter will handle it for us.++#### **Removing unused imports**++ - To remove unused imports, run `make fix-unused-imports` or `make fui` (shorthand). This is faster and cheaper than rewriting with LLM.++#### **No re-exports in `__init__.py`**++ - Do NOT fill `__init__.py` files with re-exports.+ - Always use direct full-path imports everywhere. For example:- **Logging and Pretty Printing**:@@ -211,6 +228,7 @@ NEVER USE unittest.mock. YOU MUST USE pytest-mock instead.- `tests/integration/` - for integration tests that test component interactions- `tests/e2e/` - for end-to-end tests that test complete workflows- `tests/test_pipelines/` - for test pipeline definitions (PLX files and their structuring python files)+- Do NOT add `__init__.py` files to test directories. Test directories do not need to be Python packages.- Fixtures are defined in conftest.py modules at different levels of the hierarchy, their scope is handled by pytest- Test data is placed inside test_data.py at different levels of the hierarchy, they must be imported with package paths from the root like `from tests.integration.pipelex.cogt.test_data`. Their content is all constants, regrouped inside classes to keep things tidy.- Always put test inside Test classes: 1 TestClass per module.diff --git a/CLAUDE.md b/CLAUDE.mdindex 402bd7140..b34c89a60 100644--- a/CLAUDE.md+++ b/CLAUDE.md@@ -20,6 +20,14 @@Always fix any issues reported by these tools before proceeding.+### Cleaning Derived Files++ If you need to clean derived files and caches, typically after you erased files or moved tests, the linters can get confused, the pytest collection can be off...++ ```bash+ make cleanderived+ ```+### Running TestsAfter you're finished making code changes, you must always run tests using `make test-xdist`.@@ -139,7 +147,16 @@ This document outlines the core coding standards, best practices, and quality co- Import all necessary libraries at the top of the file- Do not import libraries in functions or classes unless in very specific cases, to be discussed with the user, as they would required a `# noqa: ...` comment to pass linting- - Do not bother with ordering the imports, our Ruff linter will handle it for us. Same goes with removing unused imports.+ - Do not bother with ordering the imports, our Ruff linter will handle it for us.++#### **Removing unused imports**++ - To remove unused imports, run `make fix-unused-imports` or `make fui` (shorthand). This is faster and cheaper than rewriting with LLM.++#### **No re-exports in `__init__.py`**++ - Do NOT fill `__init__.py` files with re-exports.+ - Always use direct full-path imports everywhere. For example:- **Logging and Pretty Printing**:@@ -254,6 +271,7 @@ NEVER USE unittest.mock. YOU MUST USE pytest-mock instead.- `tests/integration/` - for integration tests that test component interactions- `tests/e2e/` - for end-to-end tests that test complete workflows- `tests/test_pipelines/` - for test pipeline definitions (PLX files and their structuring python files)+- Do NOT add `__init__.py` files to test directories. Test directories do not need to be Python packages.- Fixtures are defined in conftest.py modules at different levels of the hierarchy, their scope is handled by pytest- Test data is placed inside test_data.py at different levels of the hierarchy, they must be imported with package paths from the root like `from tests.integration.pipelex.cogt.test_data`. Their content is all constants, regrouped inside classes to keep things tidy.- Always put test inside Test classes: 1 TestClass per module.diff --git a/README.md b/README.mdindex 1602c65dd..2e71d6e0f 100644--- a/README.md+++ b/README.md@@ -119,7 +119,7 @@ Extracts text content from the candidate's CV PDF document using OCR technology,"""inputs = { cv_pdf = "PDF" }output = "Page[]"-model = "extract_text_from_pdf"+model = "extract_basic_from_pdf"[pipe.extract_job_offer_text]type = "PipeExtract"@@ -128,7 +128,7 @@ Extracts text content from the job offer PDF document using OCR technology, conv"""inputs = { job_offer_pdf = "PDF" }output = "Page[]"-model = "extract_text_from_pdf"+model = "extract_basic_from_pdf"[pipe.analyze_match]type = "PipeLLM"diff --git a/docs/home/3-understand-pipelex/language-spec-v0-1-0.md b/docs/home/3-understand-pipelex/language-spec-v0-1-0.mdindex eb841795d..662aac1a6 100644--- a/docs/home/3-understand-pipelex/language-spec-v0-1-0.md+++ b/docs/home/3-understand-pipelex/language-spec-v0-1-0.md@@ -98,7 +98,7 @@ type = "PipeExtract"description = "Extracts text content from the job offer PDF document into pages."inputs = { job_offer_pdf = "PDF" }output = "Page[]"-model = "extract_text_from_pdf"+model = "extract_basic_from_pdf"[pipe.structure_job_requirements]type = "PipeLLM"@@ -143,7 +143,7 @@ type = "PipeExtract"description = "Extracts text content from a single CV PDF into pages."inputs = { cv_pdf = "PDF" }output = "Page[]"-model = "extract_text_from_pdf"+model = "extract_basic_from_pdf"[pipe.analyze_cv_match]type = "PipeLLM"diff --git a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeExtract.md b/docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeExtract.mdindex 41bec8749..0dc59450f 100644--- a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeExtract.md+++ b/docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeExtract.md@@ -33,7 +33,7 @@ PipeExtract uses the unified inference backend system to manage OCR models. ThisCommon OCR model handles:- `mistral-ocr`: Mistral's OCR model for high-quality text and image extraction-- `pypdfium2-extract-text`: Local PDF text extraction (no API calls required)+- `pypdfium2-extract-pdf`: Local PDF text extraction (no API calls required)OCR presets are defined in your model deck configuration and can include parameters like `max_nb_images` and `image_min_size`.@@ -49,7 +49,7 @@ OCR presets are defined in your model deck configuration and can include paramet| `page_views` | boolean | If `true`, a high-fidelity image of each page will be included in the `page_view` field. Defaults to `false`. | No || `page_views_dpi` | integer | The resolution (in Dots Per Inch) for the generated page views when processing a PDF. Defaults to `150`. | No || `page_image_captions` | boolean | If `true`, the OCR service may attempt to generate captions for the images found. *Note: This feature depends on the OCR provider.* | No |-| `model` | string | The Extract model choice by name, setting, or preset to use (e.g., `"mistral-ocr"`, `"extract_text_from_visuals"`). Defaults to the model specified in the global config. | No |+| `model` | string | The Extract model choice by name, setting, or preset to use (e.g., `"mistral-ocr"`, `"extract_ocr_from_document"`). Defaults to the model specified in the global config. | No |### Example: Processing a PDFdiff --git a/docs/home/7-configuration/config-technical/inference-backend-config.md b/docs/home/7-configuration/config-technical/inference-backend-config.mdindex 3f7c700d0..08fc1dc84 100644--- a/docs/home/7-configuration/config-technical/inference-backend-config.md+++ b/docs/home/7-configuration/config-technical/inference-backend-config.md@@ -452,8 +452,8 @@ OCR presets combine OCR model selection with optimized parameters:```toml[extract.presets]# General purpose OCR-extract_text_from_visuals = { ocr_handle = "mistral-ocr", max_nb_images = 100, image_min_size = 50 }-extract_text_from_pdf = { model = "pypdfium2-extract-text", max_nb_images = 100, image_min_size = 50 }+extract_ocr_from_document = { ocr_handle = "mistral-ocr", max_nb_images = 100, image_min_size = 50 }+extract_basic_from_pdf = { model = "pypdfium2-extract-pdf", max_nb_images = 100, image_min_size = 50 }```### Image Generation Presets@@ -478,7 +478,7 @@ for_text = "cheap_llm_for_text"for_object = "cheap_llm_for_object"[extract]-choice_default = "extract_text_from_visuals"+choice_default = "extract_ocr_from_document"[img_gen]choice_default = "gen_image_basic"@@ -504,7 +504,7 @@ my_custom_img_gen = { model = "flux-dev", quality = "medium" }# Add custom aliases[aliases]my_custom_llm = "claude-3-sonnet"-my_custom_extract = "pypdfium2-extract-text"+my_custom_extract = "pypdfium2-extract-pdf"my_custom_img_gen = "base-img-gen"```diff --git a/pipelex/kit/agent_rules/codex_commands.md b/pipelex/kit/agent_rules/codex_commands.mdindex d0b45a1ea..6557a4ee7 100644--- a/pipelex/kit/agent_rules/codex_commands.md+++ b/pipelex/kit/agent_rules/codex_commands.md@@ -17,6 +17,14 @@Always fix any issues reported by these tools before proceeding.+## Cleaning Derived Files++ If you need to clean derived files and caches, typically after you erased files or moved tests, the linters can get confused, the pytest collection can be off...++ ```bash+ make cleanderived+ ```+## Running Tests in Codex CloudTo test everything that can be tested from within the Codex Cloud sandbox, run this:diff --git a/pipelex/kit/agent_rules/commands.md b/pipelex/kit/agent_rules/commands.mdindex a3da0a706..75b65e0ae 100644--- a/pipelex/kit/agent_rules/commands.md+++ b/pipelex/kit/agent_rules/commands.md@@ -17,6 +17,14 @@Always fix any issues reported by these tools before proceeding.+## Cleaning Derived Files++ If you need to clean derived files and caches, typically after you erased files or moved tests, the linters can get confused, the pytest collection can be off...++ ```bash+ make cleanderived+ ```+## Running TestsAfter you're finished making code changes, you must always run tests using `make test-xdist`.diff --git a/pipelex/kit/agent_rules/pytest_standards.md b/pipelex/kit/agent_rules/pytest_standards.mdindex 6834d125a..7e1ff93c8 100644--- a/pipelex/kit/agent_rules/pytest_standards.md+++ b/pipelex/kit/agent_rules/pytest_standards.md@@ -12,6 +12,7 @@ NEVER USE unittest.mock. YOU MUST USE pytest-mock instead.- `tests/integration/` - for integration tests that test component interactions- `tests/e2e/` - for end-to-end tests that test complete workflows- `tests/test_pipelines/` - for test pipeline definitions (PLX files and their structuring python files)+- Do NOT add `__init__.py` files to test directories. Test directories do not need to be Python packages.- Fixtures are defined in conftest.py modules at different levels of the hierarchy, their scope is handled by pytest- Test data is placed inside test_data.py at different levels of the hierarchy, they must be imported with package paths from the root like `from tests.integration.pipelex.cogt.test_data`. Their content is all constants, regrouped inside classes to keep things tidy.- Always put test inside Test classes: 1 TestClass per module.diff --git a/pipelex/kit/agent_rules/python_standards.md b/pipelex/kit/agent_rules/python_standards.mdindex 32c6fa9c3..855f51972 100644--- a/pipelex/kit/agent_rules/python_standards.md+++ b/pipelex/kit/agent_rules/python_standards.md@@ -30,7 +30,16 @@ This document outlines the core coding standards, best practices, and quality co- Import all necessary libraries at the top of the file- Do not import libraries in functions or classes unless in very specific cases, to be discussed with the user, as they would required a `# noqa: ...` comment to pass linting- - Do not bother with ordering the imports, our Ruff linter will handle it for us. Same goes with removing unused imports.+ - Do not bother with ordering the imports, our Ruff linter will handle it for us.++### **Removing unused imports**++ - To remove unused imports, run `make fix-unused-imports` or `make fui` (shorthand). This is faster and cheaper than rewriting with LLM.++### **No re-exports in `__init__.py`**++ - Do NOT fill `__init__.py` files with re-exports.+ - Always use direct full-path imports everywhere. For example:- **Logging and Pretty Printing**:diff --git a/pipelex/kit/configs/inference/backends/internal.toml b/pipelex/kit/configs/inference/backends/internal.tomlindex 2d30b7fe0..e44b2227f 100644--- a/pipelex/kit/configs/inference/backends/internal.toml+++ b/pipelex/kit/configs/inference/backends/internal.toml@@ -19,7 +19,7 @@################################################################################# --- PyPDFium2 Text Extractor --------------------------------------------------[pypdfium2-extract-text]+[pypdfium2-extract-pdf]model_type = "text_extractor"sdk = "pypdfium2"model_id = "extract-text"diff --git a/pipelex/kit/configs/inference/deck/base_deck.toml b/pipelex/kit/configs/inference/deck/base_deck.tomlindex bb28c3a96..c194c36ad 100644--- a/pipelex/kit/configs/inference/deck/base_deck.toml+++ b/pipelex/kit/configs/inference/deck/base_deck.toml@@ -111,7 +111,7 @@ cheap_llm_for_creativity = [pdf_text_extractor = ["azure-document-intelligence","mistral-ocr",- "pypdfium2-extract-text",+ "pypdfium2-extract-pdf",]image_text_extractor = ["mistral-ocr"]@@ -173,11 +173,11 @@ for_object = "cheap_llm_for_structured"####################################################################################################[extract]-choice_default = "extract_text_from_visuals"+choice_default = "extract_ocr_from_document"[extract.presets]-extract_text_from_visuals = { model = "azure-document-intelligence", max_nb_images = 100, image_min_size = 50 }-extract_text_from_pdf = { model = "pypdfium2-extract-text", max_nb_images = 100, image_min_size = 50 }+extract_ocr_from_document = { model = "azure-document-intelligence", max_nb_images = 100, image_min_size = 50 }+extract_basic_from_pdf = { model = "pypdfium2-extract-pdf", max_nb_images = 100, image_min_size = 50 }##################################################################################################### Image Generation Presetsdiff --git a/tests/e2e/pipelex/pipes/pipe_controller/pipe_sequence/test_pipe_sequence_multiplicity.py b/tests/e2e/pipelex/pipes/pipe_controller/pipe_sequence/test_pipe_sequence_multiplicity.pyindex c01f19603..40be993ea 100644--- a/tests/e2e/pipelex/pipes/pipe_controller/pipe_sequence/test_pipe_sequence_multiplicity.py+++ b/tests/e2e/pipelex/pipes/pipe_controller/pipe_sequence/test_pipe_sequence_multiplicity.py@@ -14,7 +14,6 @@ from pipelex.pipeline.execute import execute_pipeline@pytest.mark.inference@pytest.mark.asyncioclass TestPipeSequenceMultiplicity:- @pytest.mark.usefixtures("request")async def test_creative_ideation_sequence_with_multiplicity(self, pipe_run_mode: PipeRunMode):"""Test creative ideation sequence with nb_output and batching."""# Create test inputdiff --git a/tests/integration/pipelex/cogt/test_content_generator.py b/tests/integration/pipelex/cogt/test_content_generator.pyindex 0b082dd0f..ac9bbf4a7 100644--- a/tests/integration/pipelex/cogt/test_content_generator.py+++ b/tests/integration/pipelex/cogt/test_content_generator.py@@ -114,7 +114,6 @@ class TestContentGenerator:pretty_print(image, title=f"ContentGenerator: Image generated by '{img_gen_handle}' for '{positive_text}'")assert isinstance(image, ImageContent)- @pytest.mark.usefixtures("request")async def test_make_templated_text(self, content_generator: ContentGeneratorProtocol):context = {"the_answer": "elementary, my dear Watson",diff --git a/tests/integration/pipelex/fixtures/extract_fixtures.py b/tests/integration/pipelex/fixtures/extract_fixtures.pyindex dd877334d..57e419d50 100644--- a/tests/integration/pipelex/fixtures/extract_fixtures.py+++ b/tests/integration/pipelex/fixtures/extract_fixtures.py@@ -24,7 +24,7 @@ def is_extract_handle_supported_by_enabled_backends(extract_handle: str) -> bool# ================================================================================================EXTRACT_HANDLE_FROM_PDF = [- "pypdfium2-extract-text",+ "pypdfium2-extract-pdf","docling-extract-text","mistral-ocr","mistral-ocr-2503",@@ -86,8 +86,8 @@ def extract_handle_from_image(request: pytest.FixtureRequest) -> str:@pytest.fixture(params=[- "extract_text_from_visuals",- "extract_text_from_pdf",+ "extract_ocr_from_document",+ "extract_basic_from_pdf",],)def extract_choice_for_pdf(request: pytest.FixtureRequest) -> str:@@ -97,7 +97,7 @@ def extract_choice_for_pdf(request: pytest.FixtureRequest) -> str:@pytest.fixture(params=[- "extract_text_from_visuals",+ "extract_ocr_from_document",],)def extract_choice_for_image(request: pytest.FixtureRequest) -> str:diff --git a/tests/integration/pipelex/pipes/test_image_inputs.py b/tests/integration/pipelex/pipes/test_image_inputs.pyindex 0e9073460..8908b7988 100644--- a/tests/integration/pipelex/pipes/test_image_inputs.py+++ b/tests/integration/pipelex/pipes/test_image_inputs.py@@ -111,7 +111,6 @@ class TestImageInputs:assert pipe_output.working_memory is not Noneassert pipe_output.main_stuff is not None- @pytest.mark.usefixtures("request")async def test_image_input_within_concept_with_text(self, load_test_library: Callable[[list[Path]], None]) -> None:load_test_library([Path("tests/integration/pipelex/pipes/pipelines")])pipe_llm_blueprint = PipeLLMBlueprint(diff --git a/tests/unit/pipelex/cogt/models/test_model_deck.py b/tests/unit/pipelex/cogt/models/test_model_deck.pyindex 8b317663f..be5b69397 100644--- a/tests/unit/pipelex/cogt/models/test_model_deck.py+++ b/tests/unit/pipelex/cogt/models/test_model_deck.py@@ -40,7 +40,7 @@ class TestModelDeckGetOptionalInferenceModel:for_object=LLMSetting(model="default_object", temperature=0.1, max_tokens=1000),),extract_presets={},- extract_choice_default="extract_text_from_visuals",+ extract_choice_default="extract_ocr_from_document",img_gen_presets={},img_gen_choice_default="gen_image_basic",model_deck_config=ModelDeckConfig(is_model_fallback_enabled=is_model_fallback_enabled, missing_presets_reaction=ProblemReaction.NONE),diff --git a/tests/unit/pipelex/core/memory/test_dry_working_memory.py b/tests/unit/pipelex/core/memory/test_dry_working_memory.pyindex c31535ca7..234126eb4 100644--- a/tests/unit/pipelex/core/memory/test_dry_working_memory.py+++ b/tests/unit/pipelex/core/memory/test_dry_working_memory.py@@ -13,10 +13,7 @@ from tests.unit.pipelex.core.memory.tricky_questions import ThoughtfulAnswer@pytest.mark.dry_runnable@pytest.mark.asyncio(loop_scope="class")class TestDryWorkingMemory:- @pytest.mark.usefixtures("request")- async def test_make_for_dry_run_with_page_content(- self,- ):+ async def test_make_for_dry_run_with_page_content(self):log.info("Testing dry run with PageContent")# Test the specific inputs requested by the user@@ -54,10 +51,7 @@ class TestDryWorkingMemory:# Verify page_view field exists (it's Optional so could be None)assert hasattr(page_content, "page_view")- @pytest.mark.usefixtures("request")- async def test_make_for_dry_run_with_structured_content(- self,- ):+ async def test_make_for_dry_run_with_structured_content(self):log.info("Testing dry run with structured content (ThoughtfulAnswer)")# Use ThoughtfulAnswer from tricky questions domain@@ -112,10 +106,7 @@ class TestDryWorkingMemory:log.info("Created mock working memory with structured content:")dry_memory.pretty_print_summary()- @pytest.mark.usefixtures("request")- async def test_make_for_dry_run_with_text_content_fallback(- self,- ):+ async def test_make_for_dry_run_with_text_content_fallback(self):log.info("Testing dry run with TextContent fallback")needed_inputs = [@@ -160,10 +151,7 @@ class TestDryWorkingMemory:log.info("Created mock working memory with TextContent fallback:")dry_memory.pretty_print_summary()- @pytest.mark.usefixtures("request")- async def test_make_for_dry_run_mixed_content_types(- self,- ):+ async def test_make_for_dry_run_mixed_content_types(self):log.info("Testing dry run with mixed content types")needed_inputs = [@@ -218,10 +206,7 @@ class TestDryWorkingMemory:log.info("Created mock working memory with mixed content types:")dry_memory.pretty_print_summary()- @pytest.mark.usefixtures("request")- async def test_make_for_dry_run_empty_inputs(- self,- ):+ async def test_make_for_dry_run_empty_inputs(self):log.info("Testing dry run with empty inputs")needed_inputs: list[TypedNamedStuffSpec] = []@@ -234,7 +219,6 @@ class TestDryWorkingMemory:log.info("Created empty mock working memory")- @pytest.mark.usefixtures("request")async def test_make_for_dry_run_realistic_pipeline_scenario(self):log.info("Testing dry run with realistic tricky questions pipeline scenario")diff --git a/tests/unit/pipelex/core/test_data/pipes/operators/extract/pipe_extract.py b/tests/unit/pipelex/core/test_data/pipes/operators/extract/pipe_extract.pyindex 95309e12e..ab7d74077 100644--- a/tests/unit/pipelex/core/test_data/pipes/operators/extract/pipe_extract.py+++ b/tests/unit/pipelex/core/test_data/pipes/operators/extract/pipe_extract.py@@ -12,7 +12,7 @@ type = "PipeExtract"description = "Extract text from document"inputs = { document = "PDF" }output = "Page[]"-model = "extract_text_from_pdf"+model = "extract_basic_from_pdf"""",PipelexBundleBlueprint(domain="test_pipes",@@ -25,7 +25,7 @@ model = "extract_text_from_pdf""document": NativeConceptCode.PDF,},output=NativeConceptCode.PAGE.as_output_multiple_indeterminate,- model="extract_text_from_pdf",+ model="extract_basic_from_pdf",),},),diff --git a/tests/unit/pipelex/tools/typing/test_structure_printer.py b/tests/unit/pipelex/tools/typing/test_structure_printer.pyindex aeee6bad2..3e1692278 100644--- a/tests/unit/pipelex/tools/typing/test_structure_printer.py+++ b/tests/unit/pipelex/tools/typing/test_structure_printer.py@@ -1,7 +1,6 @@from datetime import datetimefrom typing import Literal-import pytestfrom pydantic import BaseModel, Field, field_validatorfrom pipelex import pretty_print@@ -123,7 +122,6 @@ class GanttChart(StructuredContent):class TestStructurePrinter:- @pytest.mark.usefixtures("request")def test_simple_text_content(self):"""Test structure of simple text content"""result = StructurePrinter().get_type_structure(SimpleTextContent)@@ -134,7 +132,6 @@ class TestStructurePrinter:]assert result == expected, f"Expected:\n{''.join(expected)}\n\nGot:\n{''.join(result)}"- @pytest.mark.usefixtures("request")def test_simple_structured_content(self):"""Test structure of simple structured content"""result = StructurePrinter().get_type_structure(SimpleStructuredContent)@@ -147,7 +144,6 @@ class TestStructurePrinter:]assert result == expected, f"Expected:\n{''.join(expected)}\n\nGot:\n{''.join(result)}"- @pytest.mark.usefixtures("request")def test_enum_content(self):"""Test structure of content with enum"""result = StructurePrinter().get_type_structure(DocumentTypeContent)@@ -162,7 +158,6 @@ class TestStructurePrinter:]assert result == expected, f"Expected:\n{''.join(expected)}\n\nGot:\n{''.join(result)}"- @pytest.mark.usefixtures("request")def test_nested_content(self):"""Test structure of nested content"""result = StructurePrinter().get_type_structure(PersonContent)@@ -198,7 +193,6 @@ class TestStructurePrinter:pretty_print(expected, "expected")assert result == expected, f"Expected:\n{''.join(expected)}\n\nGot:\n{''.join(result)}"- @pytest.mark.usefixtures("request")def test_list_content(self):"""Test structure of list content"""result = StructurePrinter().get_type_structure(ComplexListContent)@@ -235,7 +229,6 @@ class TestStructurePrinter:]assert result == expected, f"Expected:\n{''.join(expected)}\n\nGot:\n{''.join(result)}"- @pytest.mark.usefixtures("request")def test_model_with_field_description(self):"""Test structure of a model with field descriptions"""@@ -257,7 +250,6 @@ class TestStructurePrinter:]assert result == expected, f"Expected:\n{''.join(expected)}\n\nGot:\n{''.join(result)}"- @pytest.mark.usefixtures("request")def test_model_with_docstring_and_field_description(self):"""Test structure of a model with both docstring and field descriptions"""@@ -286,7 +278,6 @@ class TestStructurePrinter:]assert result == expected, f"Expected:\n{''.join(expected)}\n\nGot:\n{''.join(result)}"- @pytest.mark.usefixtures("request")def test_literal_field_content(self) -> None:"""Test structure of content with Literal field"""result = StructurePrinter().get_type_structure(MusicCategoryContent)@@ -311,7 +302,6 @@ class TestStructurePrinter:]assert result == expected, f"Expected:\n{''.join(expected)}\n\nGot:\n{''.join(result)}"- @pytest.mark.usefixtures("request")def test_gantt_chart_content(self):result = StructurePrinter().get_type_structure(GanttChart, base_class=StructuredContent)expected = [