Elias Bassani

I truly appreciate your help and feedback, but I am building a separate searcher with metadata and doc ids filtering as I prefer to keep it separate from the SparseRetriever...

Hi, I released an experimental retriever with filtering functionalities. You can read more about it [here](https://github.com/AmenRa/retriv/blob/main/docs/advanced_retriever.md). It only supports single query search at the moment. Feedbacks are welcome.

@alex2awesome can you add comments to your code, please? I do not understand what you are doing / trying to achieve.

It's not possibile atm. I will consider adding this feature in the future. Elias

Hi, you can find a very condensed example [here](https://github.com/AmenRa/retriv/blob/main/docs/sparse_retriever.md#autotune). `queries` is a list of dictionaries where each dictionary has two keys: `q_id` and `text`. Both `q_id` and `text` must be...

Hi, I have no time to work on this at the moment. You can implement it by yourself and make a PR if you want.

Hi and sorry for the delay. Unfortunately, I cannot help with this. If you find a solution, please post it here for others. Thanks.

I get similar errors for `Aggretriever-DistilBERT` and `Aggretriever-coCondenser` following the scripts reported [here](https://castorini.github.io/pyserini/2cr/msmarco-v1-passage.html). ``` Attempting to initialize pre-built index msmarco-passage.aggretriever-distilbert. Unrecognized index name msmarco-passage.aggretriever-distilbert ``` ``` Attempting to initialize pre-built...

PyPI. Should I use the other one?

Ok, thank you very much for the clarification. Do you have an approximate ETA for the next release?