Misleading situation when using the recall keyword

[sephib]

Hi,
I think there is a misleading situation when using the recall keyword with the number of results that are returned from the app.query

When running

query_results = app.query(query=query, 
            query_model=query_model, 
            recall=recall_docs,
            )
query_results.get_hits()

The number of results is 10 (default length of hits)

I think the default hits should be the number of the docs in the recal_docs

query_results = app.query(query=query, 
            query_model=query_model, 
            recall=recall_docs,
            hits=len(_recall_docs)
            )
query_results.get_hits()

If the number of recall docs are less then 10 - I would expect to get less the 10 results, thus when the number of docs in the recall is more then 10, I would expect to get all the hits for the docs in the recall list.

Does this sound reasonable?

[kkraune]

@sephib pls note that Thiago is not working on this right now, it will take some days for a response

[thigm85]

Hi @sephib, when I run an example with recall I get the number of hits equal to the number of documents I want to recall, which I think is the behavior that you expect.

For example, if you run this query notebook you see that in the end, we ask to recall two of the top 3 documents and we get exactly 2 documents back. Right?

[sephib]

The difference between your notebook example and my code is that you provide the body while I provide a query_model.
If the query_model has a hits property then it overrides the len of the recall documents. Unfortunately I can't currently verify this issue.

[thigm85]

Could you paste the code you used for me to try to reproduce the issue?

[thigm85]

Closing for lack of activity.