-
### Introduction:
Right now our model versions are identified by random IDs. Meanwhile, most of our ML-related behaviors at this time require user to refer the model ID directly, which are hard to …
-
I have implemented a hybrid search with according ingest and search pipeline, using text embeddings on document chunks, as the embedding models have input token size limitations of course.
The inge…
-
### Describe the bug
Using collapse feature in an hybrid search did not collapse documents.
### Related component
Search
### To Reproduce
I’m trying to combine hybrid search (semantic + keyword) …
-
**Opensearch Version**: 2.15
**Environment**: AWS OpenSearch
### Issue Description
I am executing hybrid queries with three sub-queries on a large dataset containing tens to hundreds of thous…
-
We found some bug when reindex a non-KNN index to KNN index with neural-search ingest pipeline. We fixed this issue https://github.com/opensearch-project/ml-commons/pull/1418.
It will be best if…
-
### Is your feature request related to a problem?
Currently neural-search text_image_processor allows a single document field to be defined for each image and text mapping. A single field can be defi…
-
## What/Why
### What are you proposing?
With https://github.com/opensearch-project/ml-commons/issues/1799 OpenSearch can now use asymmetric embedding models such as e5. Asymmetric embedding models d…
-
**Context**
Can you provide library requirements for running examples in your docs?
I`m interesting in tutorial number 7
https://deephyper.readthedocs.io/en/latest/tutorials/tutorials/notebooks/07_…
-
## 2.15.0
Number of RC's created: 5
-
## Description
For Normalization and Score Combination feature, we need actual processing unit that will process scores collected on Query phase of Hybrid search. We need approach to define differe…