mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 20:58:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat!: Docling v2 (#117)

Browse Source 
---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Maxim Lysak <mly@zurich.ibm.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
Co-authored-by: Maxim Lysak <mly@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
This commit is contained in:
Christoph Auer
2024-10-16 21:02:03 +02:00
committed by GitHub
parent d504432c1e
commit 7d3be0edeb
144 changed files with 15180 additions and 3828 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
pyproject.toml
View File

@@ -37,9 +37,9 @@ torchvision = [
######################
python = "^3.10"
pydantic = "^2.0.0"
docling-core = "^1.7.1"
docling-ibm-models = "^2.0.0"
deepsearch-glm = "^0.22.0"
docling-core = "^2.0.0"
docling-ibm-models = "^2.0.1"
deepsearch-glm = "^0.25.0"
filetype = "^1.2.0"
pypdfium2 = "^4.30.0"
pydantic-settings = "^2.3.0"
@@ -53,6 +53,9 @@ rtree = "^1.3.0"
scipy = "^1.14.1"
pyarrow = "^16.1.0"
typer = "^0.12.5"
python-docx = "^1.1.2"
python-pptx = "^1.0.2"
beautifulsoup4 = "^4.12.3"
pandas = "^2.1.4"
[tool.poetry.group.dev.dependencies]
@@ -78,12 +81,12 @@ mkdocs-jupyter = "^0.25.0"
[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"
# llama-index-readers-docling = { version = "^0.1.0", markers = 'python_version < "3.13"' }
# llama-index-node-parser-docling = { version = "^0.1.0", markers = 'python_version < "3.13"' }
# llama-index-readers-file = { version = "^0.2.2", markers = 'python_version < "3.13"' }
# llama-index-embeddings-huggingface = { version = "^0.3.1", markers = 'python_version < "3.13"' }
# llama-index-llms-huggingface-api = { version = "^0.2.0", markers = 'python_version < "3.13"' }
# llama-index-vector-stores-milvus ={ version = "^0.2.1", markers = 'python_version < "3.13"' }
langchain-huggingface = "^0.0.3"
langchain-milvus = "^0.1.4"
langchain-text-splitters = "^0.2.4"
@@ -112,6 +115,7 @@ py_version=311
pretty = true
# strict = true
no_implicit_optional = true
plugins = "pydantic.mypy"
python_version = "3.10"
[[tool.mypy.overrides]]
@@ -119,6 +123,15 @@ module = [
"docling_parse.*",
"pypdfium2.*",
"networkx.*",
"scipy.*",
"filetype.*",
"tesserocr.*",
"docling_ibm_models.*",
"easyocr.*",
"deepsearch_glm.*",
"lxml.*",
"bs4.*",
"huggingface_hub.*"
]
ignore_missing_imports = true