Skip to content

Allow zero for rescore_vector.oversample to indicate by-passing oversample and rescoring #125599

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 6 commits into from
Mar 26, 2025
Merged

Allow zero for rescore_vector.oversample to indicate by-passing oversample and rescoring #125599

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
b7fb14f
Allow zero for rescore_vector.oversample to indicate by-passing overs…
benwtrent Mar 25, 2025
60846bb
Update docs/changelog/125599.yaml
benwtrent Mar 25, 2025
6f7dfc0
Merge remote-tracking branch 'upstream/main' into feature/rescore-vec…
benwtrent Mar 25, 2025
9a6806f
adding tests, fixing logic
benwtrent Mar 26, 2025
2e15157
Merge remote-tracking branch 'upstream/main' into feature/rescore-vec…
benwtrent Mar 26, 2025
e73ef1e
Adding so many more tests
benwtrent Mar 26, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions docs/changelog/125599.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,6 @@
pr: 125599
summary: Allow zero for `rescore_vector.oversample` to indicate by-passing oversample
and rescoring
area: Vector Search
type: enhancement
issues: []
2 changes: 1 addition & 1 deletion docs/reference/elasticsearch/mapping-reference/dense-vector.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -291,7 +291,7 @@ $$$dense-vector-index-options$$$
: (Optional, object) Functionality in [preview]. An optional section that configures automatic vector rescoring on knn queries for the given field. Only applicable to quantized index types.
:::::{dropdown} Properties of `rescore_vector`
`oversample`
: (required, float) The amount to oversample the search results by. This value should be greater than `1.0` and less than `10.0`. The higher the value, the more vectors will be gathered and rescored with the raw values per shard.
: (required, float) The amount to oversample the search results by. This value should be greater than `1.0` and less than `10.0` or exactly `0` to indicate no oversampling & rescoring should occur. The higher the value, the more vectors will be gathered and rescored with the raw values per shard.
: In case a knn query specifies a `rescore_vector` parameter, the query `rescore_vector` parameter will be used instead.
: See [oversampling and rescoring quantized vectors](docs-content://solutions/search/vector/knn.md#dense-vector-knn-search-rescoring) for details.
:::::
Expand Down
1 change: 1 addition & 0 deletions docs/reference/query-languages/query-dsl/query-dsl-knn-query.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -113,6 +113,7 @@ Rescoring only makes sense for quantized vectors; when [quantization](/reference
* Retrieve `num_candidates` candidates per shard.
* From these candidates, the top `k * oversample` candidates per shard will be rescored using the original vectors.
* The top `k` rescored candidates will be returned.
Must be >= 1f to indicate oversample factor, or exactly `0` to indicate that no oversampling and rescoring should occur.


See [oversampling and rescoring quantized vectors](docs-content://solutions/search/vector/knn.md#dense-vector-knn-search-rescoring) for details.
Expand Down
257 changes: 257 additions & 0 deletions ...c/src/yamlRestTest/resources/rest-api-spec/test/search.vectors/41_knn_search_bbq_hnsw.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -337,3 +337,260 @@ setup:
- match: { hits.hits.0._score: $rescore_score0 }
- match: { hits.hits.1._score: $rescore_score1 }
- match: { hits.hits.2._score: $rescore_score2 }
---
"Test index configured rescore vector updateable and settable to 0":
- requires:
cluster_features: ["mapper.dense_vector.rescore_zero_vector"]
reason: Needs rescore_zero_vector feature

- do:
indices.create:
index: bbq_rescore_0_hnsw
body:
settings:
index:
number_of_shards: 1
mappings:
properties:
vector:
type: dense_vector
index_options:
type: bbq_hnsw
rescore_vector:
oversample: 0

- do:
indices.create:
index: bbq_rescore_update_hnsw
body:
settings:
index:
number_of_shards: 1
mappings:
properties:
vector:
type: dense_vector
index_options:
type: bbq_hnsw
rescore_vector:
oversample: 1

- do:
indices.put_mapping:
index: bbq_rescore_update_hnsw
body:
properties:
vector:
type: dense_vector
index_options:
type: bbq_hnsw
rescore_vector:
oversample: 0

- do:
indices.get_mapping:
index: bbq_rescore_update_hnsw

- match: { .bbq_rescore_update_hnsw.mappings.properties.vector.index_options.rescore_vector.oversample: 0 }
---
"Test index configured rescore vector score consistency":
- requires:
cluster_features: ["mapper.dense_vector.rescore_zero_vector"]
reason: Needs rescore_zero_vector feature
- skip:
features: "headers"
- do:
indices.create:
index: bbq_rescore_zero_hnsw
body:
settings:
index:
number_of_shards: 1
mappings:
properties:
vector:
type: dense_vector
dims: 64
index: true
similarity: max_inner_product
index_options:
type: bbq_hnsw
rescore_vector:
oversample: 0

- do:
bulk:
index: bbq_rescore_zero_hnsw
refresh: true
body: |
{ "index": {"_id": "1"}}
{ "vector": [0.077, 0.32 , -0.205, 0.63 , 0.032, 0.201, 0.167, -0.313, 0.176, 0.531, -0.375, 0.334, -0.046, 0.078, -0.349, 0.272, 0.307, -0.083, 0.504, 0.255, -0.404, 0.289, -0.226, -0.132, -0.216, 0.49 , 0.039, 0.507, -0.307, 0.107, 0.09 , -0.265, -0.285, 0.336, -0.272, 0.369, -0.282, 0.086, -0.132, 0.475, -0.224, 0.203, 0.439, 0.064, 0.246, -0.396, 0.297, 0.242, -0.028, 0.321, -0.022, -0.009, -0.001 , 0.031, -0.533, 0.45, -0.683, 1.331, 0.194, -0.157, -0.1 , -0.279, -0.098, -0.176] }
{ "index": {"_id": "2"}}
{ "vector": [0.196, 0.514, 0.039, 0.555, -0.042, 0.242, 0.463, -0.348, -0.08 , 0.442, -0.067, -0.05 , -0.001, 0.298, -0.377, 0.048, 0.307, 0.159, 0.278, 0.119, -0.057, 0.333, -0.289, -0.438, -0.014, 0.361, -0.169, 0.292, -0.229, 0.123, 0.031, -0.138, -0.139, 0.315, -0.216, 0.322, -0.445, -0.059, 0.071, 0.429, -0.602, -0.142, 0.11 , 0.192, 0.259, -0.241, 0.181, -0.166, 0.082, 0.107, -0.05 , 0.155, 0.011, 0.161, -0.486, 0.569, -0.489, 0.901, 0.208, 0.011, -0.209, -0.153, -0.27 , -0.013] }
{ "index": {"_id": "3"}}
{ "vector": [0.196, 0.514, 0.039, 0.555, -0.042, 0.242, 0.463, -0.348, -0.08 , 0.442, -0.067, -0.05 , -0.001, 0.298, -0.377, 0.048, 0.307, 0.159, 0.278, 0.119, -0.057, 0.333, -0.289, -0.438, -0.014, 0.361, -0.169, 0.292, -0.229, 0.123, 0.031, -0.138, -0.139, 0.315, -0.216, 0.322, -0.445, -0.059, 0.071, 0.429, -0.602, -0.142, 0.11 , 0.192, 0.259, -0.241, 0.181, -0.166, 0.082, 0.107, -0.05 , 0.155, 0.011, 0.161, -0.486, 0.569, -0.489, 0.901, 0.208, 0.011, -0.209, -0.153, -0.27 , -0.013] }

- do:
headers:
Content-Type: application/json
search:
rest_total_hits_as_int: true
index: bbq_rescore_zero_hnsw
body:
knn:
field: vector
query_vector: [0.128, 0.067, -0.08 , 0.395, -0.11 , -0.259, 0.473, -0.393,
0.292, 0.571, -0.491, 0.444, -0.288, 0.198, -0.343, 0.015,
0.232, 0.088, 0.228, 0.151, -0.136, 0.236, -0.273, -0.259,
-0.217, 0.359, -0.207, 0.352, -0.142, 0.192, -0.061, -0.17 ,
-0.343, 0.189, -0.221, 0.32 , -0.301, -0.1 , 0.005, 0.232,
-0.344, 0.136, 0.252, 0.157, -0.13 , -0.244, 0.193, -0.034,
-0.12 , -0.193, -0.102, 0.252, -0.185, -0.167, -0.575, 0.582,
-0.426, 0.983, 0.212, 0.204, 0.03 , -0.276, -0.425, -0.158]
k: 3
num_candidates: 3

- match: { hits.total: 3 }
- set: { hits.hits.0._score: raw_score0 }
- set: { hits.hits.1._score: raw_score1 }
- set: { hits.hits.2._score: raw_score2 }


- do:
headers:
Content-Type: application/json
search:
rest_total_hits_as_int: true
index: bbq_rescore_zero_hnsw
body:
knn:
field: vector
query_vector: [0.128, 0.067, -0.08 , 0.395, -0.11 , -0.259, 0.473, -0.393,
0.292, 0.571, -0.491, 0.444, -0.288, 0.198, -0.343, 0.015,
0.232, 0.088, 0.228, 0.151, -0.136, 0.236, -0.273, -0.259,
-0.217, 0.359, -0.207, 0.352, -0.142, 0.192, -0.061, -0.17 ,
-0.343, 0.189, -0.221, 0.32 , -0.301, -0.1 , 0.005, 0.232,
-0.344, 0.136, 0.252, 0.157, -0.13 , -0.244, 0.193, -0.034,
-0.12 , -0.193, -0.102, 0.252, -0.185, -0.167, -0.575, 0.582,
-0.426, 0.983, 0.212, 0.204, 0.03 , -0.276, -0.425, -0.158]
k: 3
num_candidates: 3
rescore_vector:
oversample: 2

- match: { hits.total: 3 }
- set: { hits.hits.0._score: override_score0 }
- set: { hits.hits.1._score: override_score1 }
- set: { hits.hits.2._score: override_score2 }

- do:
indices.put_mapping:
index: bbq_rescore_zero_hnsw
body:
properties:
vector:
type: dense_vector
dims: 64
index: true
similarity: max_inner_product
index_options:
type: bbq_hnsw
rescore_vector:
oversample: 2

- do:
headers:
Content-Type: application/json
search:
rest_total_hits_as_int: true
index: bbq_rescore_zero_hnsw
body:
knn:
field: vector
query_vector: [0.128, 0.067, -0.08 , 0.395, -0.11 , -0.259, 0.473, -0.393,
0.292, 0.571, -0.491, 0.444, -0.288, 0.198, -0.343, 0.015,
0.232, 0.088, 0.228, 0.151, -0.136, 0.236, -0.273, -0.259,
-0.217, 0.359, -0.207, 0.352, -0.142, 0.192, -0.061, -0.17 ,
-0.343, 0.189, -0.221, 0.32 , -0.301, -0.1 , 0.005, 0.232,
-0.344, 0.136, 0.252, 0.157, -0.13 , -0.244, 0.193, -0.034,
-0.12 , -0.193, -0.102, 0.252, -0.185, -0.167, -0.575, 0.582,
-0.426, 0.983, 0.212, 0.204, 0.03 , -0.276, -0.425, -0.158]
k: 3
num_candidates: 3

- match: { hits.total: 3 }
- set: { hits.hits.0._score: default_rescore0 }
- set: { hits.hits.1._score: default_rescore1 }
- set: { hits.hits.2._score: default_rescore2 }

- do:
indices.put_mapping:
index: bbq_rescore_zero_hnsw
body:
properties:
vector:
type: dense_vector
dims: 64
index: true
similarity: max_inner_product
index_options:
type: bbq_hnsw
rescore_vector:
oversample: 0

- do:
headers:
Content-Type: application/json
search:
rest_total_hits_as_int: true
index: bbq_rescore_zero_hnsw
body:
query:
script_score:
query: {match_all: {} }
script:
source: "double similarity = dotProduct(params.query_vector, 'vector'); return similarity < 0 ? 1 / (1 + -1 * similarity) : similarity + 1"
params:
query_vector: [0.128, 0.067, -0.08 , 0.395, -0.11 , -0.259, 0.473, -0.393,
0.292, 0.571, -0.491, 0.444, -0.288, 0.198, -0.343, 0.015,
0.232, 0.088, 0.228, 0.151, -0.136, 0.236, -0.273, -0.259,
-0.217, 0.359, -0.207, 0.352, -0.142, 0.192, -0.061, -0.17 ,
-0.343, 0.189, -0.221, 0.32 , -0.301, -0.1 , 0.005, 0.232,
-0.344, 0.136, 0.252, 0.157, -0.13 , -0.244, 0.193, -0.034,
-0.12 , -0.193, -0.102, 0.252, -0.185, -0.167, -0.575, 0.582,
-0.426, 0.983, 0.212, 0.204, 0.03 , -0.276, -0.425, -0.158]

# Compare scores as hit IDs may change depending on how things are distributed
- match: { hits.total: 3 }
- match: { hits.hits.0._score: $override_score0 }
- match: { hits.hits.0._score: $default_rescore0 }
- match: { hits.hits.1._score: $override_score1 }
- match: { hits.hits.1._score: $default_rescore1 }
- match: { hits.hits.2._score: $override_score2 }
- match: { hits.hits.2._score: $default_rescore2 }

- do:
headers:
Content-Type: application/json
search:
rest_total_hits_as_int: true
index: bbq_rescore_zero_hnsw
body:
knn:
field: vector
query_vector: [0.128, 0.067, -0.08 , 0.395, -0.11 , -0.259, 0.473, -0.393,
0.292, 0.571, -0.491, 0.444, -0.288, 0.198, -0.343, 0.015,
0.232, 0.088, 0.228, 0.151, -0.136, 0.236, -0.273, -0.259,
-0.217, 0.359, -0.207, 0.352, -0.142, 0.192, -0.061, -0.17 ,
-0.343, 0.189, -0.221, 0.32 , -0.301, -0.1 , 0.005, 0.232,
-0.344, 0.136, 0.252, 0.157, -0.13 , -0.244, 0.193, -0.034,
-0.12 , -0.193, -0.102, 0.252, -0.185, -0.167, -0.575, 0.582,
-0.426, 0.983, 0.212, 0.204, 0.03 , -0.276, -0.425, -0.158]
k: 3
num_candidates: 3

# Compare scores as hit IDs may change depending on how things are distributed
- match: { hits.total: 3 }
- match: { hits.hits.0._score: $raw_score0 }
- match: { hits.hits.1._score: $raw_score1 }
- match: { hits.hits.2._score: $raw_score2 }
Loading
Loading