-
I specified an elasticsearch retrieval that requires authentication. I specified the username and password in the options section of the retrieval. When I try to run a query, the app fails with:
> …
-
**Describe the bug**
I follow the DPR training example with all the default settings. (Training DPR from Scratch)
However, when Preprocessing Dataset data/dpr_training/train/biencoder-nq-train.json,…
-
Hello:
Thanks for this nice work! I have two questions:
1. In the test reader, it would output the prediction_results_file in a json file as below. There is a score and a relevant score. From my…
-
### [REQUIRED] Step 2: Describe your environment
* Android Studio version: 4.0.1
* Firebase Component: Crashlytics
* Component version: 17.2.1
### [REQUIRED] Step 3:
I have seen t…
-
- I'm using an Elasticsearch instance hosted on Azure.
- My index has around 20K passages (with an average of 90 words for each passage) and, for each passage, I have pre-computed and stored embeddin…
-
If we look at the Python replications: https://github.com/castorini/pyserini/blob/master/docs/pypi-replication.md
Compared against Anserini replications: e.g., https://github.com/castorini/anserini/b…
-
Currently, we use pre-encoded queries. We'll need to add the query encoder into the codebase.
-
Hi
I finetuned the cross encoders model using one of the huggingface model ([link](https://huggingface.co/lordtt13/COVID-SciBERT#)) on the sts dataset using your training script. I loaded the model…
-
Hi!
While evaluating vespa for a our product we ran into a limitation regarding the size of the HSNW index. Currently, with a rather small (for us) dataset and 512 dimensional vectors to search fo…
-
Hi @AdeDZY ,
Thanks for the repository. I wanted to evaluate DeepCT baselines with datasets apart from MSMARCO, such as NQ and SQuAD as passage retrieval tasks. Is this possible currently?
Kind…