diff --git a/docs/examples/develop_picture_enrichment.py b/docs/examples/develop_picture_enrichment.py index 71286320..d7d2ad4f 100644 --- a/docs/examples/develop_picture_enrichment.py +++ b/docs/examples/develop_picture_enrichment.py @@ -3,7 +3,7 @@ from pathlib import Path from typing import Any, Iterable from docling_core.types.doc import DoclingDocument, NodeItem -from docling_core.types.doc.document import PictureClassificationData, PictureItem +from docling_core.types.doc.document import PictureClassificationData, PictureItem, PictureClassificationClass from docling.datamodel.base_models import InputFormat from docling.datamodel.pipeline_options import PdfPipelineOptions @@ -38,8 +38,7 @@ class ExamplePictureClassifierEnrichmentModel(BaseEnrichmentModel): element.data.classification = PictureClassificationData( provenance="example_classifier-0.0.1", - predicted_class="dummy", - confidence=0.42, + predicted_classes=[PictureClassificationClass(class_name="dummy", confidence=0.42)] ) yield element diff --git a/poetry.lock b/poetry.lock index 63df8397..099f01f0 100644 --- a/poetry.lock +++ b/poetry.lock @@ -987,24 +987,26 @@ resolved_reference = "5fb2f34da63881a7e94418f8bb0d1af38222cc15" [[package]] name = "docling-ibm-models" -version = "2.0.0" +version = "2.0.1" description = "This package contains the AI models used by the Docling PDF conversion package" optional = false -python-versions = "^3.10" -files = [] -develop = false +python-versions = "<4.0,>=3.10" +files = [ + {file = "docling_ibm_models-2.0.1-py3-none-any.whl", hash = "sha256:f81c6002b7e102aa79afb8287fce48872f27d1cffb088ea4d1fbebe490364a1d"}, + {file = "docling_ibm_models-2.0.1.tar.gz", hash = "sha256:4fb0300022cfa0d0ac1fcbcb296c144e71ee9816654407f8a4d3a7b934f3065f"}, +] [package.dependencies] huggingface_hub = ">=0.23,<1" -jsonlines = "^3.1.0" -lxml = "^4.9.1" -mean_average_precision = "^2021.4.26.0" +jsonlines = ">=3.1.0,<4.0.0" +lxml = ">=4.9.1,<5.0.0" +mean_average_precision = ">=2021.4.26.0,<2022.0.0.0" numpy = [ {version = ">=2.1.0,<3.0.0", markers = "python_version >= \"3.13\""}, {version = ">=1.24.4,<2.0.0", markers = "python_version < \"3.13\""}, ] -opencv-python-headless = "^4.6.0.66" -Pillow = "^10.0.0" +opencv-python-headless = ">=4.6.0.66,<5.0.0.0" +Pillow = ">=10.0.0,<11.0.0" torch = [ {version = ">=2.2.2,<3.0.0", markers = "sys_platform != \"darwin\" or platform_machine != \"x86_64\""}, {version = ">=2.2.2,<2.3.0", markers = "sys_platform == \"darwin\" and platform_machine == \"x86_64\""}, @@ -1013,13 +1015,7 @@ torchvision = [ {version = ">=0,<1", markers = "sys_platform != \"darwin\" or platform_machine != \"x86_64\""}, {version = ">=0.17.2,<0.18.0", markers = "sys_platform == \"darwin\" and platform_machine == \"x86_64\""}, ] -tqdm = "^4.64.0" - -[package.source] -type = "git" -url = "https://github.com/DS4SD/docling-ibm-models.git" -reference = "1d2e2a2e6eb152c237f1383cdba20cf85db80b97" -resolved_reference = "1d2e2a2e6eb152c237f1383cdba20cf85db80b97" +tqdm = ">=4.64.0,<5.0.0" [[package]] name = "docling-parse" @@ -7489,4 +7485,4 @@ tesserocr = ["tesserocr"] [metadata] lock-version = "2.0" python-versions = "^3.10" -content-hash = "db457ead3faea75b26fb9d8e9c00375a0e59bad1c118d20af30ea5224a1808b9" +content-hash = "38fa09c8db187d27cdcd0fe632e9843b51d7ee082cf3f6618c7daad82eb40e50" diff --git a/pyproject.toml b/pyproject.toml index 9401049b..00446c52 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -38,7 +38,7 @@ torchvision = [ python = "^3.10" pydantic = "^2.0.0" docling-core = {git = "https://github.com/DS4SD/docling-core.git", rev = "5fb2f34da63881a7e94418f8bb0d1af38222cc15"} -docling-ibm-models = {git = "https://github.com/DS4SD/docling-ibm-models.git", rev = "1d2e2a2e6eb152c237f1383cdba20cf85db80b97"} +docling-ibm-models = "^2.0.1" deepsearch-glm = {git = "https://github.com/DS4SD/deepsearch-glm.git", rev = "ab96c114b71ed99d0736a4fd9d8945b115d7f1b0"} filetype = "^1.2.0" pypdfium2 = "^4.30.0"