semantic-search

Describe the feature
Right now sort is done on all the Document collection, I would like to sort only up to a top_k.

Many users in our community have been asking to have easier ways to return the output of intermediate nodes. I can see that this could be very useful for debugging and also qualitative evaluation.

I think this feature would be very useful, though the exact design is not yet fully clear.

The SimpleIndexer is used in a lot of examples.

However, it is using the old API.

The task is to check all the examples that use SimpleIndexer still work and fix the version to a specific version, like /v0.3.

SimpleIndexer hub image: https://hub.jina.ai/executor/zb38xlt4

Describe the bug

Elastiknn exceptions do not extend ElasticsearchException, so they seem to always be turned into a 500, when a 4xx would often be more appropriate.

Expected behavior

• When a query is incompatible with a mapping, use an exception that will get converted to a 400 response code. [See code where exception is initialized.](https://github.com/alexklibisz/elastiknn/blob

Is your feature request related to a problem? Please describe.
Support for multiple languages is required keeping with the essence of FOSS.

Describe the solution you'd like
Contributors who can understand English well enough and also native language to translate contents of the repository.
Add a separate FOLDER containing translations of the entire README.md with name README_Spanish/

The doc2query model to increase the ranking performance based on ideas from the https://arxiv.org/abs/2004.14503.

KoBART is used instead of T5 due to Korean performance issues.

Opened training data

• https://huggingface.co/datasets/squad_kor_v2