Thiago G. Martins
Thiago G. Martins
@NThakur20 could you take a look at this PR? The idea is to make it easier to benchmark Vespa applications using the BEIR datasets and framework. We started with Lexical...
I noticed that the NDCG@10 for Touche-2020 on the BEIR leaderboard is around 0.60 for elastic bm25. Is it correct to assume that Touche-2020 is represented by the dataset named...
Hi, Thanks for the great work. BEIR is extremely valuable! I just tried to run [BEIR.ipynb](https://colab.research.google.com/drive/1HfutiEhHMJLXiWGT8pcipxT5L2TpYEdt?usp=sharing) on Goggle Colab and I was unable to complete "Lexical Retrieval using BM25 (Elasticsearch)"...
Is it possible to export models so that we can use it outside of your ranking pipeline? For example BERT models fine tuned on MSMARCO.
Hi, Thanks for writing this jupyter extension. I tried to publish [this notebook](https://github.com/vespa-engine/pyvespa/blob/master/docs/sphinx/source/use_cases/cord19/cord19_download_parse_trec_covid.ipynb) but got `Got 413 Request Entity Too Large` as a result. My guess is that the plotly...
Using `output-file` on the notebook frontmatter works great to specify a fixed URL. However, I lost the automatic refresh of the output of `nbdev_preview`. Without `output-file`, any notebook changes saved...
When running the following cell of the [08_collab.ipynb](https://github.com/fastai/fastbook/blob/master/08_collab.ipynb)  in a virtual environment (tried with python 3.7, 3.8, and 3.9), I get the following error...
pyvespa currently generates a data plane certificate and key and stores it in a file every time a deployment is made. This behavior conflicts with the workflow of using the...
To reproduce clean all local vespa images and try to deploy. It will run for a long time and `docker image ls -a` will show many vespa images.
It seems that previously defined volumes are not preserved. To reproduce try to deploy the same application with two different instances of VespaDocker. The first deployment will create the container....