-
When I experiment with the HNSW indexing method, kNN search returns less number of results than requested. Is this behavior normal? If normal, how does the algorithm decide how many neighbors to retur…
-
should be faster than calculating the entire matrix
see #32
(creating this issues for documentation purposes)
-
### Description
Currently the only way for users to do a brute-force or exact search with KNN is with a script query. This requires some knowledge of the function names and scoring methodologies.
…
-
## 🚀 Request
Retrieval metrics should be more aligned with typical practices. Recommendation is below.
### Explanation
The current best practice for calculating retrieval metrics follows thi…
-
Thank you very much for providing this code! I’m interested in understanding the samples_per_label parameter for each task. Specifically, I’d like to know how this parameter is set for each dataset. I…
-
### Description
By reading some of the latest bugfixes in `8.13.0` and the documentation it seems it is still not possible to pre-filter a `knn` search on nested mappings, such as:
```
{
"m…
-
{'error': {'root_cause': [{'type': 'illegal_argument_exception', 'reason': 'unknown setting [index.knn] please check that any required plugins are installed, or check the breaking changes documentatio…
ghost updated
2 years ago
-
Incremental knn search save the priority queue in each round generated by knn search if best-first strategy is adopted, and use priority queue saved in the previous round to search knn in the current …
-
### Description
in some scenarios, we want to `reduce the disk usage` and `io throughput` for the source field. so, we would excludes knn fields in mapping which do not store the source like( this wo…
-
## Description
Cosine similarity is one of the more popular space types. faiss does not support it directly. Instead, they prefer to have data be normalized and then use the inner product (which is…