docling 1.19.0__tar.gz → 1.19.1__tar.gz

{docling-1.19.0 → docling-1.19.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 1.19.0
+Version: 1.19.1
 Summary: Docling PDF conversion package
 Home-page: https://github.com/DS4SD/docling
 License: MIT
@@ -22,12 +22,13 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Provides-Extra: tesserocr
 Requires-Dist: certifi (>=2024.7.4)
 Requires-Dist: deepsearch-glm (>=0.22.0,<0.23.0)
-Requires-Dist: docling-core (>=1.6.2,<2.0.0)
+Requires-Dist: docling-core (>=1.7.1,<2.0.0)
 Requires-Dist: docling-ibm-models (>=2.0.0,<3.0.0)
 Requires-Dist: docling-parse (>=1.4.1,<2.0.0)
 Requires-Dist: easyocr (>=1.7,<2.0)
 Requires-Dist: filetype (>=1.2.0,<2.0.0)
 Requires-Dist: huggingface_hub (>=0.23,<1)
+Requires-Dist: pandas (>=2.1.4,<3.0.0)
 Requires-Dist: pyarrow (>=16.1.0,<17.0.0)
 Requires-Dist: pydantic (>=2.0.0,<3.0.0)
 Requires-Dist: pydantic-settings (>=2.3.0,<3.0.0)
@@ -335,15 +336,14 @@ from docling_core.transforms.chunker import HierarchicalChunker
 
 doc = DocumentConverter().convert_single("https://arxiv.org/pdf/2206.01062").output
 chunks = list(HierarchicalChunker().chunk(doc))
-# > [
-# >     ChunkWithMetadata(
-# >         path='$.main-text[0]',
-# >         text='DocLayNet: A Large Human-Annotated Dataset [...]',
-# >         page=1,
-# >         bbox=[107.30, 672.38, 505.19, 709.08]
-# >     ),
-# >     [...]
-# > ]
+print(chunks[0])
+# ChunkWithMetadata(
+#     path='#/main-text/1',
+#     text='DocLayNet: A Large Human-Annotated Dataset [...]',
+#     page=1,
+#     bbox=[107.30, 672.38, 505.19, 709.08],
+#     [...]
+# )
 ```
 
 

{docling-1.19.0 → docling-1.19.1}/README.md

@@ -289,15 +289,14 @@ from docling_core.transforms.chunker import HierarchicalChunker
 
 doc = DocumentConverter().convert_single("https://arxiv.org/pdf/2206.01062").output
 chunks = list(HierarchicalChunker().chunk(doc))
-# > [
-# >     ChunkWithMetadata(
-# >         path='$.main-text[0]',
-# >         text='DocLayNet: A Large Human-Annotated Dataset [...]',
-# >         page=1,
-# >         bbox=[107.30, 672.38, 505.19, 709.08]
-# >     ),
-# >     [...]
-# > ]
+print(chunks[0])
+# ChunkWithMetadata(
+#     path='#/main-text/1',
+#     text='DocLayNet: A Large Human-Annotated Dataset [...]',
+#     page=1,
+#     bbox=[107.30, 672.38, 505.19, 709.08],
+#     [...]
+# )
 ```
 
 

{docling-1.19.0 → docling-1.19.1}/docling/models/tesseract_ocr_cli_model.py

@@ -1,7 +1,7 @@
 import io
 import logging
 import tempfile
-from subprocess import PIPE, Popen
+from subprocess import DEVNULL, PIPE, Popen
 from typing import Iterable, Tuple
 
 import pandas as pd
@@ -81,7 +81,7 @@ class TesseractOcrCliModel(BaseOcrModel):
         cmd += [ifilename, "stdout", "tsv"]
         _log.info("command: {}".format(" ".join(cmd)))
 
-        proc = Popen(cmd, stdout=PIPE)
+        proc = Popen(cmd, stdout=PIPE, stderr=DEVNULL)
         output, _ = proc.communicate()
 
         # _log.info(output)

{docling-1.19.0 → docling-1.19.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling"
-version = "1.19.0"  # DO NOT EDIT, updated automatically
+version = "1.19.1"  # DO NOT EDIT, updated automatically
 description = "Docling PDF conversion package"
 authors = ["Christoph Auer <cau@zurich.ibm.com>", "Michele Dolfi <dol@zurich.ibm.com>", "Maxim Lysak <mly@zurich.ibm.com>", "Nikos Livathinos <nli@zurich.ibm.com>", "Ahmed Nassar <ahn@zurich.ibm.com>", "Peter Staar <taa@zurich.ibm.com>"]
 license = "MIT"
@@ -37,7 +37,7 @@ torchvision = [
 ######################
 python = "^3.10"
 pydantic = "^2.0.0"
-docling-core = "^1.6.2"
+docling-core = "^1.7.1"
 docling-ibm-models = "^2.0.0"
 deepsearch-glm = "^0.22.0"
 filetype = "^1.2.0"
@@ -53,6 +53,7 @@ rtree = "^1.3.0"
 scipy = "^1.14.1"
 pyarrow = "^16.1.0"
 typer = "^0.12.5"
+pandas = "^2.1.4"
 
 [tool.poetry.group.dev.dependencies]
 black = {extras = ["jupyter"], version = "^24.4.2"}
@@ -67,7 +68,7 @@ pytest-xdist = "^3.3.1"
 types-requests = "^2.31.0.2"
 flake8-pyproject = "^1.2.3"
 pylint = "^2.17.5"
-pandas-stubs = "^2.2.2.240909"
+pandas-stubs = "^2.1.4.231227"
 ipykernel = "^6.29.5"
 ipywidgets = "^8.1.5"
 nbqa = "^1.9.0"
@@ -75,6 +76,9 @@ nbqa = "^1.9.0"
 [tool.poetry.group.examples.dependencies]
 datasets = "^2.21.0"
 python-dotenv = "^1.0.1"
+llama-index-readers-docling = "^0.1.0"
+llama-index-node-parser-docling = "^0.1.0"
+llama-index-readers-file = "^0.2.2"
 llama-index-embeddings-huggingface = "^0.3.1"
 llama-index-llms-huggingface-api = "^0.2.0"
 llama-index-vector-stores-milvus = "^0.2.1"