Questions related to the open big data serving engine Vespa.
Use Stackoverflow for questions related to the open big data serving engine Vespa.
Info: http://vespa.ai
Documentation: http://docs.vespa.ai/
Github: https://github.com/vespa-engine
Questions tagged [vespa]
230 questions
2
votes
1 answer
Is there a Kibana equivalent for Vespa Search?
I want to be able to quickly make index, modify schema, feed test data, delete data, copy/clone index, run queries on the index from the web interface - just like I can do with Elasticsearch. Is there such tooling available? If not is it in plans?
I…
rrh
- 45
- 3
2
votes
1 answer
How to delete all documents in a Vespa index?
What is a clean way to delete all documents in a Vespa index and leave everything else as it is?
Please share API or Vespa CLI option, if it exists.
I want to empty the index, all docs at once.
I found this command: $ vespa document -v remove…
rrh
- 45
- 3
2
votes
1 answer
Preserving word order in Vespa in non-English
I am creating a schema for Vespa mainly for English, but with two fields in Wylie transliteration of Tibetan, which looks like this
'jam dpal smra ba'i seng ge la bstod pa ut+pal dmar po'i do shal
Typically users want to match every token and…
Roope K
- 101
- 5
2
votes
1 answer
Vespa semantic search with own dataset
I am learning the basics of vector search in Vespa and went through https://github.com/vespa-engine/sample-apps/blob/master/msmarco-ranking/passage-ranking-README.md . I studied the four-part blog too. Now it would be super interesting to replace…
Roope K
- 101
- 5
2
votes
1 answer
Ranking in fuzzy match in vespa
Looks like while doing fuzzy matching in vespa, ranking is not getting applied to the documents. All the documents have a similar relevance score, which is the score achieved from any one document which is matched completely.
I am getting documents…
QCoder
- 89
- 4
2
votes
1 answer
How to perform exact nearest neighbors search in Vespa?
I have such schema
schema embeddings {
document embeddings {
field id type int {}
field text_embedding type tensor(d0[960]) {
indexing: attribute | index
attribute {
distance-metric: euclidean
}
}
…
eawer
- 1,398
- 3
- 13
- 25
2
votes
1 answer
Vespa content node search threads not reflecting in vespa-get-config
After configuring application package with:
88
4
…
S.Glick
- 63
- 3
2
votes
1 answer
How filtered document list look up work in nearest neighbour search prefiltering
In pre-filter based ANN, once we have list of documents after applying pre-filter, vespa starts hsnw algorithm to find nearest neighbours. In hsnw algorithm, vespa starts with a node and look for the neighbours which are present in pre-filter list,…
tourism
- 155
- 12
2
votes
1 answer
Rank score in summary-features
Looking for a way to always have the executed rank profile score as part of the summary (rather than configure it explicitly for each new rank profile (by adding the function used under summary-features))
Is that possible ?
S.Glick
- 63
- 3
2
votes
1 answer
Using imported fields as summary not working
While testing out parent/child feature, created 2 schemas.
Child schema:
schema item {
document item {
field id type long {
indexing : attribute
}
field campaign_ref type reference {
…
S.Glick
- 63
- 3
2
votes
1 answer
Query tensor in vespa.ai
Imitating: https://blog.vespa.ai/billion-scale-knn/
Command line:
curl -s -d '{"yql":"select * from user where {\"targetHits\":10}nearestNeighbor(approximate,…
doublemax
- 443
- 1
- 4
- 11
2
votes
1 answer
Parent-Child Mode cannot be searched by parent column
I follow this article
https://blog.vespa.ai/parent-child-in-vespa/
this is OK
vespa query -v 'yql=select * from ad where ad_campaign_budget < 500'
but this cannot find any result
vespa query -v 'yql=select * from ad where ad_campaign_budget < 500…
user2666618
- 61
- 6
2
votes
1 answer
Versioning document changes in Vespa
I would like to allow for versioning of text in Vespa. If a user changes certain fields over time the changes would be tracked and versions could be restored.
I imagine a solution running in parallel to Vespa would be the way to go, with version…
SirGanya
- 142
- 1
- 9
2
votes
1 answer
Cannot index a document in a self-hosted Vespa instance
We're trying to build our own Vespa cluster starting with a Kubernetes quick start, and indexing a document returns a "no space" error.
The problem is that we can't really understand where do we add that space. Any pointers on what to…
Alexander Solovyov
- 1,526
- 1
- 13
- 21
2
votes
1 answer
`vespa` tutorial : ./src/python/user_search.py U33527 10 KeyError: 'children'
I'm following step by step the Vespa tutorials: https://docs.vespa.ai/en/tutorials/news-5-recommendation.html
(vespa) raphy@pc:~/vespa/sample-apps/news$ python3 src/python/train_cold_start.py mind 10
Total loss after epoch 9: 534.6995239257812…
Raphael10
- 2,508
- 7
- 22
- 50