Francisco Perez-Sorrosal

Same problem here when trying to run inference using: ```bash sudo docker run --gpus '"device=0"' --rm -p8000:8000 --shm-size=1g --ulimit memlock=-1 --ulimit stack=67108864 --net inference_network --network-alias=trt_server -v/home/fperez/dev/models/tensorrt:/models nvcr.io/nvidia/tensorrt:20.03-py3 giexec --onnx=/models/bert-onnx/test/model.onnx --device=0...

Added an initial implementation. Added some tests to check the main paths and functionality. Also basic documentation in the mdBook guide. All the test were passing in my local machine....

This can be done now through [this plugin/preprocessor](https://github.com/francisco-perez-sorrosal/mdbook-bib). Crates: https://crates.io/crates/mdbook-bib Src/Binaries: https://github.com/francisco-perez-sorrosal/mdbook-bib/releases/tag/v0.0.3

After these changes, I can exercise finally the toolkit successfully in my mac: ``` ╰─❯ $ curl --location 'http://localhost:8000/chat-stream' --header 'User-Id: test-user' --header 'Content-Type: application/json' --data '{"message": "hey"}' data: {"event":...

Hey, sorry for the delay in doing this. Updated the main branch, rebased my commits, squashed them into a single one and signed it. Hope is what you need! Thanks!

Done! Just, updated poetry.lock

Hey @ShadowMitia, is this more or less what you want? You can find this feature for now in this [branch](https://github.com/francisco-perez-sorrosal/mdbook-bib/tree/chapter-cites) if you want to try it.

@man-chi Did the parentheses solve your problem with the references?