feat: native vector search support - #146
Open
rebasedming wants to merge 2 commits into
Open
Conversation
rebasedming
requested review from
isaacvando,
mdashti,
philippemnoel and
stuhood
as code owners
July 25, 2026 17:25
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## paradedb-am #146 +/- ##
===============================================
+ Coverage 87.96% 88.60% +0.64%
===============================================
Files 9 10 +1
Lines 1188 1264 +76
Branches 249 260 +11
===============================================
+ Hits 1045 1120 +75
Misses 85 85
- Partials 58 59 +1
Flags with carried forward coverage won't be shown. Click here to find out more.
🚀 New features to boost your workflow:
|
|
|
||
| The SQL-generation tests are unit tests that don't require a database. | ||
| Integration tests are gated on bm25 vector opclass support, which is not | ||
| yet in a released pg_search (it lives on branch ``mvp/vector-search``). |
|
|
||
| ## Vector Search | ||
|
|
||
| ParadeDB indexes pgvector `vector` columns inside its BM25 index and serves Top-K nearest-neighbor queries. django-paradedb ships native support — no pgvector Python package needed. |
Member
There was a problem hiding this comment.
see my comment on EF Core PR
rebasedming
force-pushed
the
vector-search
branch
from
July 27, 2026 15:29
657f416 to
0907deb
Compare
rebasedming
force-pushed
the
vector-search
branch
from
July 27, 2026 15:58
0907deb to
e0949a6
Compare
rebasedming
force-pushed
the
vector-search
branch
from
July 27, 2026 18:43
e0949a6 to
c75cc22
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Implements paradedb/paradedb#5685: native vector search support with no pgvector-python dependency.
VectorField(dimensions=n)model field for pgvectorvector(n)with migration serializationL2Distance/CosineDistance/InnerProductexpressions (<->,<=>,<#>) for.order_by()/.annotate()metricoption onBM25Indexemitting vector opclasses (vector_l2_opsetc.)hybrid_rrfexample off pgvector-python; newvector_searchexample; integration tests capability-gated until a release ships vector-in-bm25The distance operators are intentionally not in
api.json5— they are pgvector operators, not pg_search schema symbols, and schema-compat validates against released schemas.Why
ParadeDB indexes pgvector columns inside the bm25 index, so users should get the full query surface from this package alone.
Tests
Full suite passes against 0.24.2 (302 passed; 3 vector integration tests skip via capability gate). ruff/mypy/schema-compat/api-coverage all clean.