-
Using the [POST query api](https://docs.vespa.ai/en/query-api.html#using-post) Vespa will accept the [] short indexed form, but not the short mapped form, which is silently ignored.
```json
{
…
-
### Question Validation
- [X] I have searched both the documentation and discord for an answer.
### Question
Dear all,
I have a problem concerning the ordering of the retrieved chunks. This …
Cotum updated
10 months ago
-
# 1. The schema:
```
schema Vespa1 {
document Vespa1 {
field wpsolr_title type string {
indexing: summary | index
summary: dynamic
}
field wpsolr_content type s…
-
Dear FracMinHash team,
My understanding of FracMinHash is that a much smaller number of hash functions can be used for estimating containment Jaccard and then Jaccard index (after obtaining the car…
-
I'm interested in using ColBERTv2 for re-ranking already-ranked approximate nearest neighbor results. I couldn't find any docs or examples that exactly match this use case. My thinking is that I woul…
-
Currently the biggest bottleneck at query time is the `countHits` method in `MatchHashesAndScoreQuery`. This counts the number of times each doc in the segment matches one of the query vector's hashes…
-
微博内容精选
-
Using a component id that does not exist does not prevent queries to return results !
YQL query:
`{"offset":0,"hits":20,"input.query(q_384)":"embed(???, query: parot)","ranking":"wpsolr_rank…
-
# TODO
* [ ] Close this issue when the **great fork merge** happens.
# Original comment
Like the thread in the [other repo](https://github.com/ioccc-src/mkiocccentry/issues/171) this is to he…
xexyl updated
8 hours ago
-
### What happened?
I have persisted a library, the distance found when n_results is 5 is different from the distance found when n_results is 12.
### Versions
Chroma 0.4.6
Python 3.9.13
macOS Vent…