dromeuf
dromeuf
I also get errors when integrating with intfloat/multilingual-e5-large-instruct with General & max token of 512. This embedding model seems to be well rated in MMTEB https://arxiv.org/abs/2502.13595 HF TEI text-embeddings-inference logs...
Hi, I've noticed the same thing with : - version 0.17.2 - with vLLM embedding intfloat/multilingual-e5-large-instruct limit to 512 max tokens model providers configuration. - KB General chunking to 250...
> Hello, this problem occurs reliably on a default install of Ubuntu 22.04 + docling from PyPI. Basically it's the usual C++ being incompatible with C++ and CUDA being incompatible...
> [@dromeuf](https://github.com/dromeuf) what was your Ubuntu and CUDA versions? I tried this on a fresh container with latest cuda (from Nvidia's image: [Ubuntu 24.04 + CUDA 12.8.0](https://hub.docker.com/layers/nvidia/cuda/12.8.0-cudnn-devel-ubuntu24.04/images/sha256-ea73ae92d1ab9453de0910d342b005aaec8fa2388d3f8913694a6de69392c6ab)) with no luck....
And Docling error dependencys : ``` Installing collected packages: python-bidi, pyclipper, XlsxWriter, tifffile, Shapely, rtree, pypdfium2, opencv-python-headless, ninja, marko, lazy-loader, jsonref, jsonlines, imageio, docling-parse, scikit-image, python-pptx, typer, pydantic-settings, torchvision, docling-core,...
[Bug]: v0.15.0-17 / Chunk Book + RAPTOR / Page(265~277): [ERROR]Internal server error while chunking
Hi Kevin, You can DL here : https://filesender.renater.fr/?s=download&token=207ddd57-7bf6-420b-9d63-0188017aead9 Kind regards, David.
> `castorini/monot5-large-msmarco` is not a re-rank model. Unless I'm mistaken, Kevin, in https://huggingface.co/castorini/monot5-large-msmarco : This model is a T5-large reranker fine-tuned on the MS MARCO passage dataset for 100k steps...
> From these, it's not a rerank model at all. ok so don't use it. Thanks.
> From these, it's not a rerank model at all. Kevin, can you recommend the best LOCAL (not cloud) reranker to run with RAGFlow ? Kind regards,
> ``` > (HF_TGI) dromeuf@MAIA:~$ sudo docker run --gpus all -p 33437:80 ghcr.io/huggingface/text-generation-inference:latest --model-id castorini/monot5-large-msmarco > > dromeuf@MAIA:~$ curl -X POST http://localhost:33437/v1/completions -H "Content-Type: application/json" -d '{"prompt": "texte à reranker",...