docs: add styling for faq (#502)

* docs: add styling to faq

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* remove torchaudio

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Michele Dolfi 2024-12-03 11:20:49 +01:00 committed by GitHub
parent 051789d017
commit 5ba3807f31
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -3,7 +3,9 @@
This is a collection of FAQ collected from the user questions on <https://github.com/DS4SD/docling/discussions>.
### Python 3.13 support
??? question "Is Python 3.13 supported?"
### Is Python 3.13 supported?
Full support for Python 3.13 is currently waiting for [pytorch](https://github.com/pytorch/pytorch).
@ -15,7 +17,7 @@ python3.13 -m venv venv
source ./venv/bin/activate
# Install torch nightly builds, see https://pytorch.org/
pip3 install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cpu
pip3 install --pre torch torchvision --index-url https://download.pytorch.org/whl/nightly/cpu
# Install docling
pip3 install docling
@ -29,8 +31,14 @@ _Note: we are disabling OCR since easyocr and the nightly torch builds have some
Source: Issue [#136](https://github.com/DS4SD/docling/issues/136)
??? question "Install conflicts with numpy (python 3.13)"
### Install conflicts with numpy (python 3.13)
When using `docling-ibm-models>=2.0.7` and `deepsearch-glm>=0.26.2` these issues should not show up anymore.
Docling supports numpy versions `>=1.24.4,<3.0.0` which should match all usages.
**For older versions**
This has been observed installing docling and langchain via poetry.
@ -54,19 +62,20 @@ numpy = [
]
```
Source: Issue [#283](https://github.com/DS4SD/docling/issues/283#issuecomment-2465035868)
### GPU support
??? question "Are text styles (bold, underline, etc) supported?"
TBA
### Are text styles (bold, underline, etc) supported?
Currently text styles are not supported in the `DoclingDocument` format.
If you are interest in contributing this feature, please open a discussion topic to brainstorm on the design.
_Note: this is not a simple topic_
### Text styles (bold, underline, etc)
TBA
??? question "How do I run completely offline?"
### How do I run completely offline?
@ -89,6 +98,7 @@ converter = DocumentConverter(
Source: Issue [#326](https://github.com/DS4SD/docling/issues/326)
??? question " Which model weights are needed to run Docling?"
### Which model weights are needed to run Docling?
Model weights are needed for the AI models used in the PDF pipeline. Other document types (docx, pptx, etc) do not have any such requirement.
@ -98,6 +108,7 @@ For processing PDF documents, Docling requires the model weights from <https://h
When OCR is enabled, some engines also require model artifacts. For example EasyOCR, for which Docling has [special pipeline options](https://github.com/DS4SD/docling/blob/main/docling/datamodel/pipeline_options.py#L68) to control the runtime behavior.
??? question "SSL error downloading model weights"
### SSL error downloading model weights
@ -114,6 +125,8 @@ Possible solutions were
- Use [pip-system-certs](https://pypi.org/project/pip-system-certs/) to use the latest trusted certificates on your system.
??? question "Which OCR languages are supported?"
### Which OCR languages are supported?
Docling supports multiple OCR engine, each one has its own list of supported languages.