ParvaP
16e88d50fa
Fix link to supported formats in quickstart guide Updated link to supported formats documentation. Signed-off-by: ParvaP <55171512+ParvaP@users.noreply.github.com>
1.5 KiB
Vendored
Basic usage
Python
In Docling, working with documents is as simple as:
- converting your source file to a Docling document
- using that Docling document for your workflow
For example, the snippet below shows conversion with export to Markdown:
from docling.document_converter import DocumentConverter
source = "https://arxiv.org/pdf/2408.09869" # file path or URL
converter = DocumentConverter()
doc = converter.convert(source).document
print(doc.export_to_markdown()) # output: "### Docling Technical Report[...]"
Docling supports a wide array of file formats and, as outlined in the architecture guide, provides a versatile document model along with a full suite of supported operations.
CLI
You can additionally use Docling directly from your terminal, for instance:
docling https://arxiv.org/pdf/2206.01062
The CLI provides various options, such as 🥚GraniteDocling (incl. MLX acceleration) & other VLMs:
docling --pipeline vlm --vlm-model granite_docling https://arxiv.org/pdf/2206.01062
For all available options, run docling --help or check the CLI reference.
What's next
Check out the Usage subpages (navigation menu on the left) as well as our featured examples for additional usage workflows, including conversion customization, RAG, framework integrations, chunking, serialization, enrichments, and much more!