mirror of
https://github.com/docling-project/docling-serve.git
synced 2025-11-29 00:23:36 +00:00
a91ee83c61030656b5134199155f8728271544c7
* Publish docling-serve images to ghcr and quay container repositories This commit: - Creates container file to build the image for cpu only and default "with gpu" images - Adds workflow jobs to publish the images to ghcr.io and quay.io - Makefile to build these images locally for linux/amd64 platform. Signed-off-by: Anil Vishnoi <vishnoianil@gmail.com> * make cpu-only version with poetry Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * Rename cpu/gpu image names and also update the supported platforms Signed-off-by: Anil Vishnoi <vishnoianil@gmail.com> --------- Signed-off-by: Anil Vishnoi <vishnoianil@gmail.com> Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
Docling Serve
Running Docling as an API service.
Note
This is an unstable draft implementation which will quickly evolve.
Development
Install the dependencies
# Install dependencies
poetry install
# Run the server
poetry run uvicorn docling_serve.app:app --reload
Example payload (http source):
curl -X 'POST' \
'http://127.0.0.1:8000/convert' \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"http_source": {
"url": "https://arxiv.org/pdf/2206.01062"
}
}'
Languages
Python
93.2%
Makefile
5.1%
Dockerfile
1.7%