-
### Problem Statement:
When using search request processors, users need to send an initial search request with properly constructed query builders. However, if the initial request fails to meet th…
-
https://arxiv.org/pdf/1712.00559.pdf
-
**Is your feature request related to a problem? Please describe.**
I am using Qdrant Search API to retrieve the data from the vectorDB, Currently I am providing vectors in the payload of search API, …
-
Initial bug reported in https://github.com/opensearch-project/ml-commons/issues/2303
**What is the bug?**
I am creating a text embedding processor that creates vectors on a nested field. However, …
-
### 論文へのリンク
[[arXiv:2006.04647] Neural Architecture Search without Training](https://arxiv.org/abs/2006.04647)
### 著者・所属機関
Joseph Mellor, Jack Turner, Amos Storkey, Elliot J. Crowley
- Ush…
-
### What is the bug?
The instructions to start working on the neural-search plugin in the [DEVELOPER_GUIDE.md](https://github.com/opensearch-project/neural-search/blob/main/DEVELOPER_GUIDE.md) seem t…
-
### What is the bug?
When configured with deep nested map type configuration in text_embedding processor, the embedding result will override the original value of document key:
pipeline configurati…
-
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…
-
https://arxiv.org/abs/1808.05377
-
### Is there an existing issue for this?
- [X] I have searched the existing issues
### Package/Plugin version
0.3.0
### Platforms
- [ ] Android
- [X] iOS
- [ ] Linux
- [ ] MacOS
- [ ] Web
- [ ] W…