Merge branch 'master' into hqann2

CHANGELOG.md

@@ -1,7 +1,7 @@
 ## 0.8.0 (unreleased)
 
+- Added support for inline filtering with HNSW
 - Added support for iterative index scans
-- Added `intvec` type
 - Added casts for arrays to `sparsevec`
 - Improved cost estimation
 - Improved performance of HNSW inserts and on-disk index builds

Makefile

@@ -4,8 +4,8 @@ EXTVERSION = 0.7.4
 MODULE_big = vector
 DATA = $(wildcard sql/*--*--*.sql)
 DATA_built = sql/$(EXTENSION)--$(EXTVERSION).sql
-OBJS = src/bitutils.o src/bitvec.o src/halfutils.o src/halfvec.o src/hnsw.o src/hnswbuild.o src/hnswinsert.o src/hnswscan.o src/hnswutils.o src/hnswvacuum.o src/intvec.o src/ivfbuild.o src/ivfflat.o src/ivfinsert.o src/ivfkmeans.o src/ivfscan.o src/ivfutils.o src/ivfvacuum.o src/sparsevec.o src/vector.o
-HEADERS = src/halfvec.h src/intvec.h src/sparsevec.h src/vector.h
+OBJS = src/bitutils.o src/bitvec.o src/halfutils.o src/halfvec.o src/hnsw.o src/hnswbuild.o src/hnswinsert.o src/hnswscan.o src/hnswutils.o src/hnswvacuum.o src/ivfbuild.o src/ivfflat.o src/ivfinsert.o src/ivfkmeans.o src/ivfscan.o src/ivfutils.o src/ivfvacuum.o src/sparsevec.o src/vector.o
+HEADERS = src/halfvec.h src/sparsevec.h src/vector.h
 
 TESTS = $(wildcard test/sql/*.sql)
 REGRESS = $(patsubst test/sql/%.sql,%,$(TESTS))

Makefile.win

@@ -2,8 +2,8 @@ EXTENSION = vector
 EXTVERSION = 0.7.4
 
 DATA_built = sql\$(EXTENSION)--$(EXTVERSION).sql
-OBJS = src\bitutils.obj src\bitvec.obj src\halfutils.obj src\halfvec.obj src\hnsw.obj src\hnswbuild.obj src\hnswinsert.obj src\hnswscan.obj src\hnswutils.obj src\hnswvacuum.obj src\intvec.obj src\ivfbuild.obj src\ivfflat.obj src\ivfinsert.obj src\ivfkmeans.obj src\ivfscan.obj src\ivfutils.obj src\ivfvacuum.obj src\sparsevec.obj src\vector.obj
-HEADERS = src\halfvec.h src\intvec.h src\sparsevec.h src\vector.h
+OBJS = src\bitutils.obj src\bitvec.obj src\halfutils.obj src\halfvec.obj src\hnsw.obj src\hnswbuild.obj src\hnswinsert.obj src\hnswscan.obj src\hnswutils.obj src\hnswvacuum.obj src\ivfbuild.obj src\ivfflat.obj src\ivfinsert.obj src\ivfkmeans.obj src\ivfscan.obj src\ivfutils.obj src\ivfvacuum.obj src\sparsevec.obj src\vector.obj
+HEADERS = src\halfvec.h src\sparsevec.h src\vector.h
 
 REGRESS = bit btree cast copy halfvec hnsw_bit hnsw_halfvec hnsw_sparsevec hnsw_vector ivfflat_bit ivfflat_halfvec ivfflat_vector sparsevec vector_type
 REGRESS_OPTS = --inputdir=test --load-extension=$(EXTENSION)

README.md

@@ -223,7 +223,7 @@ L2 distance
 CREATE INDEX ON items USING hnsw (embedding vector_l2_ops);
 ```
 
-Note: Use `halfvec_l2_ops` for `halfvec`, `intvec_l2_ops` for `intvec`, and `sparsevec_l2_ops` for `sparsevec` (and similar with the other distance functions)
+Note: Use `halfvec_l2_ops` for `halfvec` and `sparsevec_l2_ops` for `sparsevec` (and similar with the other distance functions)
 
 Inner product
 
@@ -259,7 +259,6 @@ Supported types are:
 
 - `vector` - up to 2,000 dimensions
 - `halfvec` - up to 4,000 dimensions (added in 0.7.0)
-- `intvec` - up to 8,000 dimensions (added in 0.8.0)
 - `bit` - up to 64,000 dimensions (added in 0.7.0)
 - `sparsevec` - up to 1,000 non-zero elements (added in 0.7.0)
 
@@ -440,6 +439,12 @@ Create an index on one [or more](https://www.postgresql.org/docs/current/indexes
 CREATE INDEX ON items (category_id);
 ```
 
+Or a composite HNSW index for approximate search (added in 0.8.0)
+
+```sql
+CREATE INDEX ON items USING hnsw (embedding vector_l2_ops, category_id);
+```
+
 Or a [partial index](https://www.postgresql.org/docs/current/indexes-partial.html) on the vector column for approximate search
 
 ```sql
@@ -478,16 +483,6 @@ Get the nearest neighbors
 SELECT * FROM items ORDER BY embedding::halfvec(3) <-> '[1,2,3]' LIMIT 5;
 ```
 
-## Integer Vectors
-
-*Added in 0.8.0*
-
-Use the `intvec` type to store 8-bit integer vectors
-
-```sql
-CREATE TABLE items (id bigserial PRIMARY KEY, embedding intvec(3));
-```
-
 ## Binary Vectors
 
 Use the `bit` type to store binary vectors ([example](https://github.com/pgvector/pgvector-python/blob/master/examples/imagehash/example.py))
@@ -951,30 +946,6 @@ Function | Description | Added
 avg(halfvec) → halfvec | average | 0.7.0
 sum(halfvec) → halfvec | sum | 0.7.0
 
-### Intvec Type
-
-Each int vector takes `dimensions + 8` bytes of storage. Each element is a single byte signed integer. Int vectors can have up to 16,000 dimensions.
-
-### Intvec Operators
-
-Operator | Description | Added
---- | --- | ---
-<-> | Euclidean distance | 0.8.0
-<#> | negative inner product | 0.8.0
-<=> | cosine distance | 0.8.0
-<+> | taxicab distance | 0.8.0
-
-### Intvec Functions
-
-Function | Description | Added
---- | --- | ---
-cosine_distance(intvec, intvec) → double precision | cosine distance | 0.8.0
-inner_product(intvec, intvec) → double precision | inner product | 0.8.0
-l1_distance(intvec, intvec) → double precision | taxicab distance | 0.8.0
-l2_distance(intvec, intvec) → double precision | Euclidean distance | 0.8.0
-l2_norm(intvec) → double precision | Euclidean norm | 0.8.0
-vector_dims(intvec) → integer | number of dimensions | 0.8.0
-
 ### Bit Type
 
 Each bit vector takes `dimensions / 8 + 8` bytes of storage. See the [Postgres docs](https://www.postgresql.org/docs/current/datatype-bit.html) for more info.
@@ -1224,6 +1195,7 @@ Thanks to:
 - [k-means++: The Advantage of Careful Seeding](https://theory.stanford.edu/~sergei/papers/kMeansPP-soda.pdf)
 - [Concept Decompositions for Large Sparse Text Data using Clustering](https://www.cs.utexas.edu/users/inderjit/public_papers/concept_mlj.pdf)
 - [Efficient and Robust Approximate Nearest Neighbor Search using Hierarchical Navigable Small World Graphs](https://arxiv.org/ftp/arxiv/papers/1603/1603.09320.pdf)
+- [HQANN: Efficient and Robust Similarity Search for Hybrid Queries with Structured and Unstructured Constraints](https://arxiv.org/pdf/2207.07940.pdf)
 
 ## History
 

sql/vector--0.7.4--0.8.0.sql

@@ -1,188 +1,6 @@
 -- complain if script is sourced in psql, rather than via CREATE EXTENSION
 \echo Use "ALTER EXTENSION vector UPDATE TO '0.8.0'" to load this file. \quit
 
-CREATE FUNCTION hnsw_intvec_support(internal) RETURNS internal
-	AS 'MODULE_PATHNAME' LANGUAGE C;
-
-CREATE TYPE intvec;
-
-CREATE FUNCTION intvec_in(cstring, oid, integer) RETURNS intvec
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION intvec_out(intvec) RETURNS cstring
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION intvec_typmod_in(cstring[]) RETURNS integer
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION intvec_recv(internal, oid, integer) RETURNS intvec
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION intvec_send(intvec) RETURNS bytea
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE TYPE intvec (
-	INPUT     = intvec_in,
-	OUTPUT    = intvec_out,
-	TYPMOD_IN = intvec_typmod_in,
-	RECEIVE   = intvec_recv,
-	SEND      = intvec_send,
-	STORAGE   = external
-);
-
-CREATE FUNCTION l2_distance(intvec, intvec) RETURNS float8
-	AS 'MODULE_PATHNAME', 'intvec_l2_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION inner_product(intvec, intvec) RETURNS float8
-	AS 'MODULE_PATHNAME', 'intvec_inner_product' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION cosine_distance(intvec, intvec) RETURNS float8
-	AS 'MODULE_PATHNAME', 'intvec_cosine_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION l1_distance(intvec, intvec) RETURNS float8
-	AS 'MODULE_PATHNAME', 'intvec_l1_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION vector_dims(intvec) RETURNS integer
-	AS 'MODULE_PATHNAME', 'intvec_vector_dims' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION l2_norm(intvec) RETURNS float8
-	AS 'MODULE_PATHNAME', 'intvec_l2_norm' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION intvec_lt(intvec, intvec) RETURNS bool
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION intvec_le(intvec, intvec) RETURNS bool
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION intvec_eq(intvec, intvec) RETURNS bool
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION intvec_ne(intvec, intvec) RETURNS bool
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION intvec_ge(intvec, intvec) RETURNS bool
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION intvec_gt(intvec, intvec) RETURNS bool
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION intvec_cmp(intvec, intvec) RETURNS int4
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION intvec_l2_squared_distance(intvec, intvec) RETURNS float8
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION intvec_negative_inner_product(intvec, intvec) RETURNS float8
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION intvec(intvec, integer, boolean) RETURNS intvec
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION array_to_intvec(integer[], integer, boolean) RETURNS intvec
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION intvec_to_integer(intvec, integer, boolean) RETURNS integer[]
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE CAST (intvec AS intvec)
-	WITH FUNCTION intvec(intvec, integer, boolean) AS IMPLICIT;
-
-CREATE CAST (intvec AS integer[])
-	WITH FUNCTION intvec_to_integer(intvec, integer, boolean) AS ASSIGNMENT;
-
-CREATE CAST (integer[] AS intvec)
-	WITH FUNCTION array_to_intvec(integer[], integer, boolean) AS ASSIGNMENT;
-
-CREATE OPERATOR <-> (
-	LEFTARG = intvec, RIGHTARG = intvec, PROCEDURE = l2_distance,
-	COMMUTATOR = '<->'
-);
-
-CREATE OPERATOR <#> (
-	LEFTARG = intvec, RIGHTARG = intvec, PROCEDURE = intvec_negative_inner_product,
-	COMMUTATOR = '<#>'
-);
-
-CREATE OPERATOR <=> (
-	LEFTARG = intvec, RIGHTARG = intvec, PROCEDURE = cosine_distance,
-	COMMUTATOR = '<=>'
-);
-
-CREATE OPERATOR <+> (
-	LEFTARG = intvec, RIGHTARG = intvec, PROCEDURE = l1_distance,
-	COMMUTATOR = '<+>'
-);
-
-CREATE OPERATOR < (
-	LEFTARG = intvec, RIGHTARG = intvec, PROCEDURE = intvec_lt,
-	COMMUTATOR = > , NEGATOR = >= ,
-	RESTRICT = scalarltsel, JOIN = scalarltjoinsel
-);
-
-CREATE OPERATOR <= (
-	LEFTARG = intvec, RIGHTARG = intvec, PROCEDURE = intvec_le,
-	COMMUTATOR = >= , NEGATOR = > ,
-	RESTRICT = scalarlesel, JOIN = scalarlejoinsel
-);
-
-CREATE OPERATOR = (
-	LEFTARG = intvec, RIGHTARG = intvec, PROCEDURE = intvec_eq,
-	COMMUTATOR = = , NEGATOR = <> ,
-	RESTRICT = eqsel, JOIN = eqjoinsel
-);
-
-CREATE OPERATOR <> (
-	LEFTARG = intvec, RIGHTARG = intvec, PROCEDURE = intvec_ne,
-	COMMUTATOR = <> , NEGATOR = = ,
-	RESTRICT = eqsel, JOIN = eqjoinsel
-);
-
-CREATE OPERATOR >= (
-	LEFTARG = intvec, RIGHTARG = intvec, PROCEDURE = intvec_ge,
-	COMMUTATOR = <= , NEGATOR = < ,
-	RESTRICT = scalargesel, JOIN = scalargejoinsel
-);
-
-CREATE OPERATOR > (
-	LEFTARG = intvec, RIGHTARG = intvec, PROCEDURE = intvec_gt,
-	COMMUTATOR = < , NEGATOR = <= ,
-	RESTRICT = scalargtsel, JOIN = scalargtjoinsel
-);
-
-CREATE OPERATOR CLASS intvec_ops
-	DEFAULT FOR TYPE intvec USING btree AS
-	OPERATOR 1 < ,
-	OPERATOR 2 <= ,
-	OPERATOR 3 = ,
-	OPERATOR 4 >= ,
-	OPERATOR 5 > ,
-	FUNCTION 1 intvec_cmp(intvec, intvec);
-
-CREATE OPERATOR CLASS intvec_l2_ops
-	FOR TYPE intvec USING hnsw AS
-	OPERATOR 1 <-> (intvec, intvec) FOR ORDER BY float_ops,
-	FUNCTION 1 intvec_l2_squared_distance(intvec, intvec),
-	FUNCTION 3 hnsw_intvec_support(internal);
-
-CREATE OPERATOR CLASS intvec_ip_ops
-	FOR TYPE intvec USING hnsw AS
-	OPERATOR 1 <#> (intvec, intvec) FOR ORDER BY float_ops,
-	FUNCTION 1 intvec_negative_inner_product(intvec, intvec),
-	FUNCTION 3 hnsw_intvec_support(internal);
-
-CREATE OPERATOR CLASS intvec_cosine_ops
-	FOR TYPE intvec USING hnsw AS
-	OPERATOR 1 <=> (intvec, intvec) FOR ORDER BY float_ops,
-	FUNCTION 1 cosine_distance(intvec, intvec),
-	FUNCTION 2 l2_norm(intvec),
-	FUNCTION 3 hnsw_intvec_support(internal);
-
-CREATE OPERATOR CLASS intvec_l1_ops
-	FOR TYPE intvec USING hnsw AS
-	OPERATOR 1 <+> (intvec, intvec) FOR ORDER BY float_ops,
-	FUNCTION 1 l1_distance(intvec, intvec),
-	FUNCTION 3 hnsw_intvec_support(internal);
-
 CREATE FUNCTION array_to_sparsevec(integer[], integer, boolean) RETURNS sparsevec
 	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
 
@@ -206,3 +24,11 @@ CREATE CAST (double precision[] AS sparsevec)
 
 CREATE CAST (numeric[] AS sparsevec)
 	WITH FUNCTION array_to_sparsevec(numeric[], integer, boolean) AS ASSIGNMENT;
+
+CREATE FUNCTION hnsw_attribute_distance(integer, integer) RETURNS float8
+	AS 'MODULE_PATHNAME', 'hnsw_int4_attribute_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE OPERATOR CLASS vector_integer_ops
+	DEFAULT FOR TYPE integer USING hnsw AS
+	OPERATOR 2 = (integer, integer),
+	FUNCTION 4 hnsw_attribute_distance(integer, integer);

sql/vector.sql

@@ -272,9 +272,6 @@ CREATE FUNCTION ivfflat_bit_support(internal) RETURNS internal
 CREATE FUNCTION hnsw_halfvec_support(internal) RETURNS internal
 	AS 'MODULE_PATHNAME' LANGUAGE C;
 
-CREATE FUNCTION hnsw_intvec_support(internal) RETURNS internal
-	AS 'MODULE_PATHNAME' LANGUAGE C;
-
 CREATE FUNCTION hnsw_bit_support(internal) RETURNS internal
 	AS 'MODULE_PATHNAME' LANGUAGE C;
 
@@ -650,199 +647,6 @@ CREATE OPERATOR CLASS halfvec_l1_ops
 	FUNCTION 1 l1_distance(halfvec, halfvec),
 	FUNCTION 3 hnsw_halfvec_support(internal);
 
--- intvec type
-
-CREATE TYPE intvec;
-
-CREATE FUNCTION intvec_in(cstring, oid, integer) RETURNS intvec
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION intvec_out(intvec) RETURNS cstring
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION intvec_typmod_in(cstring[]) RETURNS integer
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION intvec_recv(internal, oid, integer) RETURNS intvec
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION intvec_send(intvec) RETURNS bytea
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE TYPE intvec (
-	INPUT     = intvec_in,
-	OUTPUT    = intvec_out,
-	TYPMOD_IN = intvec_typmod_in,
-	RECEIVE   = intvec_recv,
-	SEND      = intvec_send,
-	STORAGE   = external
-);
-
--- intvec functions
-
-CREATE FUNCTION l2_distance(intvec, intvec) RETURNS float8
-	AS 'MODULE_PATHNAME', 'intvec_l2_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION inner_product(intvec, intvec) RETURNS float8
-	AS 'MODULE_PATHNAME', 'intvec_inner_product' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION cosine_distance(intvec, intvec) RETURNS float8
-	AS 'MODULE_PATHNAME', 'intvec_cosine_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION l1_distance(intvec, intvec) RETURNS float8
-	AS 'MODULE_PATHNAME', 'intvec_l1_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION vector_dims(intvec) RETURNS integer
-	AS 'MODULE_PATHNAME', 'intvec_vector_dims' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION l2_norm(intvec) RETURNS float8
-	AS 'MODULE_PATHNAME', 'intvec_l2_norm' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
--- intvec private functions
-
-CREATE FUNCTION intvec_lt(intvec, intvec) RETURNS bool
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION intvec_le(intvec, intvec) RETURNS bool
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION intvec_eq(intvec, intvec) RETURNS bool
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION intvec_ne(intvec, intvec) RETURNS bool
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION intvec_ge(intvec, intvec) RETURNS bool
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION intvec_gt(intvec, intvec) RETURNS bool
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION intvec_cmp(intvec, intvec) RETURNS int4
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION intvec_l2_squared_distance(intvec, intvec) RETURNS float8
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION intvec_negative_inner_product(intvec, intvec) RETURNS float8
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
--- intvec cast functions
-
-CREATE FUNCTION intvec(intvec, integer, boolean) RETURNS intvec
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION array_to_intvec(integer[], integer, boolean) RETURNS intvec
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION intvec_to_integer(intvec, integer, boolean) RETURNS integer[]
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
--- intvec casts
-
-CREATE CAST (intvec AS intvec)
-	WITH FUNCTION intvec(intvec, integer, boolean) AS IMPLICIT;
-
-CREATE CAST (intvec AS integer[])
-	WITH FUNCTION intvec_to_integer(intvec, integer, boolean) AS ASSIGNMENT;
-
-CREATE CAST (integer[] AS intvec)
-	WITH FUNCTION array_to_intvec(integer[], integer, boolean) AS ASSIGNMENT;
-
--- intvec operators
-
-CREATE OPERATOR <-> (
-	LEFTARG = intvec, RIGHTARG = intvec, PROCEDURE = l2_distance,
-	COMMUTATOR = '<->'
-);
-
-CREATE OPERATOR <#> (
-	LEFTARG = intvec, RIGHTARG = intvec, PROCEDURE = intvec_negative_inner_product,
-	COMMUTATOR = '<#>'
-);
-
-CREATE OPERATOR <=> (
-	LEFTARG = intvec, RIGHTARG = intvec, PROCEDURE = cosine_distance,
-	COMMUTATOR = '<=>'
-);
-
-CREATE OPERATOR <+> (
-	LEFTARG = intvec, RIGHTARG = intvec, PROCEDURE = l1_distance,
-	COMMUTATOR = '<+>'
-);
-
-CREATE OPERATOR < (
-	LEFTARG = intvec, RIGHTARG = intvec, PROCEDURE = intvec_lt,
-	COMMUTATOR = > , NEGATOR = >= ,
-	RESTRICT = scalarltsel, JOIN = scalarltjoinsel
-);
-
-CREATE OPERATOR <= (
-	LEFTARG = intvec, RIGHTARG = intvec, PROCEDURE = intvec_le,
-	COMMUTATOR = >= , NEGATOR = > ,
-	RESTRICT = scalarlesel, JOIN = scalarlejoinsel
-);
-
-CREATE OPERATOR = (
-	LEFTARG = intvec, RIGHTARG = intvec, PROCEDURE = intvec_eq,
-	COMMUTATOR = = , NEGATOR = <> ,
-	RESTRICT = eqsel, JOIN = eqjoinsel
-);
-
-CREATE OPERATOR <> (
-	LEFTARG = intvec, RIGHTARG = intvec, PROCEDURE = intvec_ne,
-	COMMUTATOR = <> , NEGATOR = = ,
-	RESTRICT = eqsel, JOIN = eqjoinsel
-);
-
-CREATE OPERATOR >= (
-	LEFTARG = intvec, RIGHTARG = intvec, PROCEDURE = intvec_ge,
-	COMMUTATOR = <= , NEGATOR = < ,
-	RESTRICT = scalargesel, JOIN = scalargejoinsel
-);
-
-CREATE OPERATOR > (
-	LEFTARG = intvec, RIGHTARG = intvec, PROCEDURE = intvec_gt,
-	COMMUTATOR = < , NEGATOR = <= ,
-	RESTRICT = scalargtsel, JOIN = scalargtjoinsel
-);
-
--- intvec opclasses
-
-CREATE OPERATOR CLASS intvec_ops
-	DEFAULT FOR TYPE intvec USING btree AS
-	OPERATOR 1 < ,
-	OPERATOR 2 <= ,
-	OPERATOR 3 = ,
-	OPERATOR 4 >= ,
-	OPERATOR 5 > ,
-	FUNCTION 1 intvec_cmp(intvec, intvec);
-
-CREATE OPERATOR CLASS intvec_l2_ops
-	FOR TYPE intvec USING hnsw AS
-	OPERATOR 1 <-> (intvec, intvec) FOR ORDER BY float_ops,
-	FUNCTION 1 intvec_l2_squared_distance(intvec, intvec),
-	FUNCTION 3 hnsw_intvec_support(internal);
-
-CREATE OPERATOR CLASS intvec_ip_ops
-	FOR TYPE intvec USING hnsw AS
-	OPERATOR 1 <#> (intvec, intvec) FOR ORDER BY float_ops,
-	FUNCTION 1 intvec_negative_inner_product(intvec, intvec),
-	FUNCTION 3 hnsw_intvec_support(internal);
-
-CREATE OPERATOR CLASS intvec_cosine_ops
-	FOR TYPE intvec USING hnsw AS
-	OPERATOR 1 <=> (intvec, intvec) FOR ORDER BY float_ops,
-	FUNCTION 1 cosine_distance(intvec, intvec),
-	FUNCTION 2 l2_norm(intvec),
-	FUNCTION 3 hnsw_intvec_support(internal);
-
-CREATE OPERATOR CLASS intvec_l1_ops
-	FOR TYPE intvec USING hnsw AS
-	OPERATOR 1 <+> (intvec, intvec) FOR ORDER BY float_ops,
-	FUNCTION 1 l1_distance(intvec, intvec),
-	FUNCTION 3 hnsw_intvec_support(internal);
-
 -- bit functions
 
 CREATE FUNCTION hamming_distance(bit, bit) RETURNS float8
@@ -1112,3 +916,13 @@ CREATE OPERATOR CLASS sparsevec_l1_ops
 	OPERATOR 1 <+> (sparsevec, sparsevec) FOR ORDER BY float_ops,
 	FUNCTION 1 l1_distance(sparsevec, sparsevec),
 	FUNCTION 3 hnsw_sparsevec_support(internal);
+
+-- hnsw attributes
+
+CREATE FUNCTION hnsw_attribute_distance(integer, integer) RETURNS float8
+	AS 'MODULE_PATHNAME', 'hnsw_int4_attribute_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE OPERATOR CLASS vector_integer_ops
+	DEFAULT FOR TYPE integer USING hnsw AS
+	OPERATOR 2 = (integer, integer),
+	FUNCTION 4 hnsw_attribute_distance(integer, integer);

src/hnsw.c

@@ -20,13 +20,13 @@
 
 static const struct config_enum_entry hnsw_iterative_search_options[] = {
 	{"off", HNSW_ITERATIVE_SEARCH_OFF, false},
-	{"relaxed_order", HNSW_ITERATIVE_SEARCH_RELAXED, false},
-	{"strict_order", HNSW_ITERATIVE_SEARCH_STRICT, false},
+	{"on", HNSW_ITERATIVE_SEARCH_RELAXED, false},
+	{"strict", HNSW_ITERATIVE_SEARCH_STRICT, false},
 	{NULL, 0, false}
 };
 
 int			hnsw_ef_search;
-int			hnsw_max_search_tuples;
+int			hnsw_iterative_search_max_tuples;
 int			hnsw_iterative_search;
 int			hnsw_lock_tranche_id;
 static relopt_kind hnsw_relopt_kind;
@@ -78,13 +78,13 @@ HnswInit(void)
 							"Valid range is 1..1000.", &hnsw_ef_search,
 							HNSW_DEFAULT_EF_SEARCH, HNSW_MIN_EF_SEARCH, HNSW_MAX_EF_SEARCH, PGC_USERSET, 0, NULL, NULL, NULL);
 
-	DefineCustomEnumVariable("hnsw.iterative_search", "Sets the iterative search mode",
+	DefineCustomEnumVariable("hnsw.iterative_search", "Sets iterative search",
 							 NULL, &hnsw_iterative_search,
 							 HNSW_ITERATIVE_SEARCH_OFF, hnsw_iterative_search_options, PGC_USERSET, 0, NULL, NULL, NULL);
 
-	/* This is approximate and does not apply to the initial scan */
-	DefineCustomIntVariable("hnsw.max_search_tuples", "Sets the max number of candidates to visit for iterative search",
-							"-1 means no limit", &hnsw_max_search_tuples,
+	/* TODO Ensure ivfflat.max_probes uses same value for "all" */
+	DefineCustomIntVariable("hnsw.iterative_search_max_tuples", "Sets the max number of candidates to visit for iterative search",
+							"-1 means all", &hnsw_iterative_search_max_tuples,
 							-1, -1, INT_MAX, PGC_USERSET, 0, NULL, NULL, NULL);
 
 	MarkGUCPrefixReserved("hnsw");
@@ -245,13 +245,13 @@ hnswhandler(PG_FUNCTION_ARGS)
 	IndexAmRoutine *amroutine = makeNode(IndexAmRoutine);
 
 	amroutine->amstrategies = 0;
-	amroutine->amsupport = 3;
+	amroutine->amsupport = 4;
 	amroutine->amoptsprocnum = 0;
 	amroutine->amcanorder = false;
 	amroutine->amcanorderbyop = true;
 	amroutine->amcanbackward = false;	/* can change direction mid-scan */
 	amroutine->amcanunique = false;
-	amroutine->amcanmulticol = false;
+	amroutine->amcanmulticol = true;
 	amroutine->amoptionalkey = true;
 	amroutine->amsearcharray = false;
 	amroutine->amsearchnulls = false;
@@ -303,3 +303,17 @@ hnswhandler(PG_FUNCTION_ARGS)
 
 	PG_RETURN_POINTER(amroutine);
 }
+
+/*
+ * Get the distance between two int4 attributes
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(hnsw_int4_attribute_distance);
+Datum
+hnsw_int4_attribute_distance(PG_FUNCTION_ARGS)
+{
+	int32		a = PG_GETARG_INT32(0);
+	int32		b = PG_GETARG_INT32(1);
+	double		distance = ((double) a) - ((double) b);
+
+	PG_RETURN_FLOAT8(distance);
+}

src/hnsw.h

@@ -19,6 +19,7 @@
 #define HNSW_DISTANCE_PROC 1
 #define HNSW_NORM_PROC 2
 #define HNSW_TYPE_INFO_PROC 3
+#define HNSW_ATTRIBUTE_DISTANCE_PROC 4
 
 #define HNSW_VERSION	1
 #define HNSW_MAGIC_NUMBER 0xA953A953
@@ -107,18 +108,20 @@
 #define HnswPtrPointer(hp) (hp).ptr
 #define HnswPtrOffset(hp) relptr_offset((hp).relptr)
 
+#define HnswUseIndexTuple(index) (IndexRelationGetNumberOfAttributes(index) > 1)
+
 /* Variables */
 extern int	hnsw_ef_search;
 extern int	hnsw_iterative_search;
-extern int	hnsw_max_search_tuples;
+extern int	hnsw_iterative_search_max_tuples;
 extern int	hnsw_lock_tranche_id;
 
-typedef enum HnswIterativeSearchMode
+typedef enum HnswIterativeSearchType
 {
 	HNSW_ITERATIVE_SEARCH_OFF,
 	HNSW_ITERATIVE_SEARCH_RELAXED,
 	HNSW_ITERATIVE_SEARCH_STRICT
-}			HnswIterativeSearchMode;
+}			HnswIterativeSearchType;
 
 typedef struct HnswElementData HnswElementData;
 typedef struct HnswNeighborArray HnswNeighborArray;
@@ -133,6 +136,7 @@ HnswPtrDeclare(HnswElementData, HnswElementRelptr, HnswElementPtr);
 HnswPtrDeclare(HnswNeighborArray, HnswNeighborArrayRelptr, HnswNeighborArrayPtr);
 HnswPtrDeclare(HnswNeighborArrayPtr, HnswNeighborsRelptr, HnswNeighborsPtr);
 HnswPtrDeclare(char, DatumRelptr, DatumPtr);
+HnswPtrDeclare(IndexTupleData, IndexTupleRelptr, IndexTuplePtr);
 
 struct HnswElementData
 {
@@ -149,6 +153,7 @@ struct HnswElementData
 	OffsetNumber neighborOffno;
 	BlockNumber neighborPage;
 	DatumPtr	value;
+	IndexTuplePtr itup;
 	LWLock		lock;
 };
 
@@ -174,6 +179,7 @@ typedef struct HnswSearchCandidate
 	pairingheap_node w_node;
 	HnswElementPtr element;
 	double		distance;
+	bool		matches;
 }			HnswSearchCandidate;
 
 /* HNSW index options */
@@ -252,14 +258,16 @@ typedef struct HnswTypeInfo
 
 typedef struct HnswSupport
 {
-	FmgrInfo   *procinfo;
+	FmgrInfo   *procinfo[2];
 	FmgrInfo   *normprocinfo;
-	Oid			collation;
+	Oid		   *collation;
 }			HnswSupport;
 
 typedef struct HnswQuery
 {
 	Datum		value;
+	IndexTuple	itup;
+	ScanKeyData *keyData;
 }			HnswQuery;
 
 typedef struct HnswBuildState
@@ -288,6 +296,8 @@ typedef struct HnswBuildState
 	HnswGraph  *graph;
 	double		ml;
 	int			maxLevel;
+	bool		useIndexTuple;
+	TupleDesc	tupdesc;
 
 	/* Memory */
 	MemoryContext graphCtx;
@@ -415,30 +425,32 @@ bool		HnswCheckNorm(HnswSupport * support, Datum value);
 Buffer		HnswNewBuffer(Relation index, ForkNumber forkNum);
 void		HnswInitPage(Buffer buf, Page page);
 void		HnswInit(void);
-List	   *HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement, visited_hash * v, pairingheap **discarded, bool initVisited, int64 *tuples);
+List	   *HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement, bool inMemory, visited_hash * v, pairingheap **discarded, bool initVisited, int64 *tuples);
 HnswElement HnswGetEntryPoint(Relation index);
 void		HnswGetMetaPageInfo(Relation index, int *m, HnswElement * entryPoint);
 void	   *HnswAlloc(HnswAllocator * allocator, Size size);
 HnswElement HnswInitElement(char *base, ItemPointer tid, int m, double ml, int maxLevel, HnswAllocator * alloc);
 HnswElement HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno);
-void		HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing);
-HnswSearchCandidate *HnswEntryCandidate(char *base, HnswElement em, HnswQuery * q, Relation rel, HnswSupport * support, bool loadVec);
+void		HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing, bool inMemory);
+HnswSearchCandidate *HnswEntryCandidate(char *base, HnswElement em, HnswQuery * q, Relation rel, HnswSupport * support, bool loadVec, bool inMemory);
 void		HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum, bool building);
 void		HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, int m);
 void		HnswAddHeapTid(HnswElement element, ItemPointer heaptid);
 HnswNeighborArray *HnswInitNeighborArray(int lm, HnswAllocator * allocator);
 void		HnswInitNeighbors(char *base, HnswElement element, int m, HnswAllocator * alloc);
-bool		HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPointer heaptid, bool building);
+bool		HnswInsertTupleOnDisk(Relation index, HnswSupport * support, IndexTuple itup, ItemPointer heaptid, bool building, TupleDesc tupdesc);
 void		HnswUpdateNeighborsOnDisk(Relation index, HnswSupport * support, HnswElement e, int m, bool checkExisting, bool building);
-void		HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec);
-void		HnswLoadElement(HnswElement element, double *distance, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance);
-bool		HnswFormIndexValue(Datum *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, HnswSupport * support);
-void		HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element);
+void		HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec, Relation index);
+void		HnswLoadElement(HnswElement element, double *distance, bool *matches, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance);
+void		HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element, bool useIndexTuple);
 void		HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newElement, float distance, int lm, int *updateIdx, Relation index, HnswSupport * support);
+bool		HnswFormIndexTuple(IndexTuple *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, HnswSupport * support, TupleDesc tupdesc);
 bool		HnswLoadNeighborTids(HnswElement element, ItemPointerData *indextids, Relation index, int m, int lm, int lc);
 void		HnswInitLockTranche(void);
 const		HnswTypeInfo *HnswGetTypeInfo(Relation index);
 PGDLLEXPORT void HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc);
+Size		HnswGetElementTupleSize(char *base, HnswElement element, bool useIndexTuple);
+bool		HnswIndexTupleIsEqual(IndexTuple a, IndexTuple b, TupleDesc tupdesc);
 
 /* Index access methods */
 IndexBuildResult *hnswbuild(Relation heap, Relation index, IndexInfo *indexInfo);

src/hnswbuild.c

@@ -148,6 +148,7 @@ CreateGraphPages(HnswBuildState * buildstate)
 	Page		page;
 	HnswElementPtr iter = buildstate->graph->head;
 	char	   *base = buildstate->hnswarea;
+	bool		useIndexTuple = buildstate->useIndexTuple;
 
 	/* Calculate sizes */
 	maxSize = HNSW_MAX_SIZE;
@@ -167,7 +168,6 @@ CreateGraphPages(HnswBuildState * buildstate)
 		Size		etupSize;
 		Size		ntupSize;
 		Size		combinedSize;
-		Pointer		valuePtr = HnswPtrAccess(base, element->value);
 
 		/* Update iterator */
 		iter = element->next;
@@ -176,7 +176,7 @@ CreateGraphPages(HnswBuildState * buildstate)
 		MemSet(etup, 0, HNSW_TUPLE_ALLOC_SIZE);
 
 		/* Calculate sizes */
-		etupSize = HNSW_ELEMENT_TUPLE_SIZE(VARSIZE_ANY(valuePtr));
+		etupSize = HnswGetElementTupleSize(base, element, useIndexTuple);
 		ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(element->level, buildstate->m);
 		combinedSize = etupSize + ntupSize + sizeof(ItemIdData);
 
@@ -186,7 +186,7 @@ CreateGraphPages(HnswBuildState * buildstate)
 					(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
 					 errmsg("index tuple too large")));
 
-		HnswSetElementTuple(base, etup, element);
+		HnswSetElementTuple(base, etup, element, useIndexTuple);
 
 		/* Keep element and neighbors on the same page if possible */
 		if (PageGetFreeSpace(page) < etupSize || (combinedSize <= maxSize && PageGetFreeSpace(page) < combinedSize))
@@ -327,19 +327,18 @@ AddDuplicateInMemory(HnswElement element, HnswElement dup)
  * Find duplicate element
  */
 static bool
-FindDuplicateInMemory(char *base, HnswElement element)
+FindDuplicateInMemory(char *base, HnswElement element, bool useIndexTuple, TupleDesc tupdesc)
 {
 	HnswNeighborArray *neighbors = HnswGetNeighbors(base, element, 0);
-	Datum		value = HnswGetValue(base, element);
+	IndexTuple	itup = HnswPtrAccess(base, element->itup);
 
 	for (int i = 0; i < neighbors->length; i++)
 	{
 		HnswCandidate *neighbor = &neighbors->items[i];
 		HnswElement neighborElement = HnswPtrAccess(base, neighbor->element);
-		Datum		neighborValue = HnswGetValue(base, neighborElement);
 
 		/* Exit early since ordered by distance */
-		if (!datumIsEqual(value, neighborValue, false, -1))
+		if (!HnswIndexTupleIsEqual(itup, HnswPtrAccess(base, neighborElement->itup), tupdesc))
 			return false;
 
 		/* Check for space */
@@ -366,7 +365,7 @@ AddElementInMemory(char *base, HnswGraph * graph, HnswElement element)
  * Update neighbors
  */
 static void
-UpdateNeighborsInMemory(char *base, HnswSupport * support, HnswElement e, int m)
+UpdateNeighborsInMemory(char *base, Relation index, HnswSupport * support, HnswElement e, int m)
 {
 	for (int lc = e->level; lc >= 0; lc--)
 	{
@@ -388,7 +387,7 @@ UpdateNeighborsInMemory(char *base, HnswSupport * support, HnswElement e, int m)
 			Assert(neighborElement);
 
 			LWLockAcquire(&neighborElement->lock, LW_EXCLUSIVE);
-			HnswUpdateConnection(base, HnswGetNeighbors(base, neighborElement, lc), e, hc->distance, lm, NULL, NULL, support);
+			HnswUpdateConnection(base, HnswGetNeighbors(base, neighborElement, lc), e, hc->distance, lm, NULL, index, support);
 			LWLockRelease(&neighborElement->lock);
 		}
 	}
@@ -404,14 +403,14 @@ UpdateGraphInMemory(HnswSupport * support, HnswElement element, int m, int efCon
 	char	   *base = buildstate->hnswarea;
 
 	/* Look for duplicate */
-	if (FindDuplicateInMemory(base, element))
+	if (FindDuplicateInMemory(base, element, buildstate->useIndexTuple, buildstate->tupdesc))
 		return;
 
 	/* Add element */
 	AddElementInMemory(base, graph, element);
 
 	/* Update neighbors */
-	UpdateNeighborsInMemory(base, support, element, m);
+	UpdateNeighborsInMemory(base, buildstate->index, support, element, m);
 
 	/* Update entry point if needed (already have lock) */
 	if (entryPoint == NULL || element->level > entryPoint->level)
@@ -424,6 +423,7 @@ UpdateGraphInMemory(HnswSupport * support, HnswElement element, int m, int efCon
 static void
 InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
 {
+	Relation	index = buildstate->index;
 	HnswGraph  *graph = buildstate->graph;
 	HnswSupport *support = &buildstate->support;
 	HnswElement entryPoint;
@@ -457,7 +457,7 @@ InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
 	}
 
 	/* Find neighbors for element */
-	HnswFindElementNeighbors(base, element, entryPoint, NULL, support, m, efConstruction, false);
+	HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, false, true);
 
 	/* Update graph in memory */
 	UpdateGraphInMemory(support, element, m, efConstruction, entryPoint, buildstate);
@@ -476,18 +476,20 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
 	HnswElement element;
 	HnswAllocator *allocator = &buildstate->allocator;
 	HnswSupport *support = &buildstate->support;
-	Size		valueSize;
-	Pointer		valuePtr;
 	LWLock	   *flushLock = &graph->flushLock;
 	char	   *base = buildstate->hnswarea;
-	Datum		value;
+	TupleDesc	tupdesc = buildstate->tupdesc;
+	IndexTuple	itup;
+	Size		itupSize;
+	IndexTuple	itupShared;
+	bool		unused;
 
-	/* Form index value */
-	if (!HnswFormIndexValue(&value, values, isnull, buildstate->typeInfo, support))
+	/* Form index tuple */
+	if (!HnswFormIndexTuple(&itup, values, isnull, buildstate->typeInfo, support, tupdesc))
 		return false;
 
-	/* Get datum size */
-	valueSize = VARSIZE_ANY(DatumGetPointer(value));
+	/* Get tuple size */
+	itupSize = IndexTupleSize(itup);
 
 	/* Ensure graph not flushed when inserting */
 	LWLockAcquire(flushLock, LW_SHARED);
@@ -497,7 +499,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
 	{
 		LWLockRelease(flushLock);
 
-		return HnswInsertTupleOnDisk(index, support, value, heaptid, true);
+		return HnswInsertTupleOnDisk(index, support, itup, heaptid, true, tupdesc);
 	}
 
 	/*
@@ -529,12 +531,12 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
 
 		LWLockRelease(flushLock);
 
-		return HnswInsertTupleOnDisk(index, support, value, heaptid, true);
+		return HnswInsertTupleOnDisk(index, support, itup, heaptid, true, tupdesc);
 	}
 
 	/* Ok, we can proceed to allocate the element */
 	element = HnswInitElement(base, heaptid, buildstate->m, buildstate->ml, buildstate->maxLevel, allocator);
-	valuePtr = HnswAlloc(allocator, valueSize);
+	itupShared = HnswAlloc(allocator, itupSize);
 
 	/*
 	 * We have now allocated the space needed for the element, so we don't
@@ -543,9 +545,10 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
 	 */
 	LWLockRelease(&graph->allocatorLock);
 
-	/* Copy the datum */
-	memcpy(valuePtr, DatumGetPointer(value), valueSize);
-	HnswPtrStore(base, element->value, valuePtr);
+	/* Copy the tuple */
+	memcpy(itupShared, itup, itupSize);
+	HnswPtrStore(base, element->itup, itupShared);
+	HnswPtrStore(base, element->value, DatumGetPointer(index_getattr(itupShared, 1, tupdesc, &unused)));
 
 	/* Create a lock for the element */
 	LWLockInitialize(&element->lock, hnsw_lock_tranche_id);
@@ -672,6 +675,19 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
 				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
 				 errmsg("type not supported for hnsw index")));
 
+	/* TODO See if needed */
+	if (IndexRelationGetNumberOfKeyAttributes(index) > 2)
+		elog(ERROR, "index cannot have more than two columns");
+
+	if (!OidIsValid(index_getprocid(index, 1, HNSW_DISTANCE_PROC)))
+		elog(ERROR, "first column must be a vector");
+
+	for (int i = 1; i < IndexRelationGetNumberOfKeyAttributes(index); i++)
+	{
+		if (!OidIsValid(index_getprocid(index, i + 1, HNSW_ATTRIBUTE_DISTANCE_PROC)))
+			elog(ERROR, "column %d cannot be a vector", i + 1);
+	}
+
 	/* Require column to have dimensions to be indexed */
 	if (buildstate->dimensions < 0)
 		ereport(ERROR,
@@ -698,6 +714,8 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
 	buildstate->graph = &buildstate->graphData;
 	buildstate->ml = HnswGetMl(buildstate->m);
 	buildstate->maxLevel = HnswGetMaxLevel(buildstate->m);
+	buildstate->useIndexTuple = HnswUseIndexTuple(index);
+	buildstate->tupdesc = RelationGetDescr(index);
 
 	buildstate->graphCtx = GenerationContextCreate(CurrentMemoryContext,
 												   "Hnsw build graph context",

src/hnswinsert.c

@@ -156,9 +156,10 @@ AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, B
 	BlockNumber newInsertPage = InvalidBlockNumber;
 	uint8		tupleVersion;
 	char	   *base = NULL;
+	bool		useIndexTuple = HnswUseIndexTuple(index);
 
 	/* Calculate sizes */
-	etupSize = HNSW_ELEMENT_TUPLE_SIZE(VARSIZE_ANY(HnswPtrAccess(base, e->value)));
+	etupSize = HnswGetElementTupleSize(base, e, useIndexTuple);
 	ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(e->level, m);
 	combinedSize = etupSize + ntupSize + sizeof(ItemIdData);
 	maxSize = HNSW_MAX_SIZE;
@@ -166,7 +167,7 @@ AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, B
 
 	/* Prepare element tuple */
 	etup = palloc0(etupSize);
-	HnswSetElementTuple(base, etup, e);
+	HnswSetElementTuple(base, etup, e, useIndexTuple);
 
 	/* Prepare neighbor tuple */
 	ntup = palloc0(ntupSize);
@@ -383,8 +384,9 @@ LoadElementsForInsert(HnswNeighborArray * neighbors, HnswQuery * q, int *idx, Re
 		HnswCandidate *hc = &neighbors->items[i];
 		HnswElement element = HnswPtrAccess(base, hc->element);
 		double		distance;
+		bool		matches;
 
-		HnswLoadElement(element, &distance, q, index, support, true, NULL);
+		HnswLoadElement(element, &distance, &matches, q, index, support, true, NULL);
 		hc->distance = distance;
 
 		/* Prune element if being deleted */
@@ -428,6 +430,8 @@ GetUpdateIndex(HnswElement element, HnswElement newElement, float distance, int
 		HnswQuery	q;
 
 		q.value = HnswGetValue(base, element);
+		q.itup = HnswPtrAccess(base, element->itup);
+		q.keyData = NULL;
 
 		LoadElementsForInsert(neighbors, &q, &idx, index, support);
 
@@ -633,21 +637,30 @@ AddDuplicateOnDisk(Relation index, HnswElement element, HnswElement dup, bool bu
  * Find duplicate element
  */
 static bool
-FindDuplicateOnDisk(Relation index, HnswElement element, bool building)
+FindDuplicateOnDisk(Relation index, HnswElement element, bool building, TupleDesc tupdesc)
 {
 	char	   *base = NULL;
 	HnswNeighborArray *neighbors = HnswGetNeighbors(base, element, 0);
 	Datum		value = HnswGetValue(base, element);
+	IndexTuple	itup = HnswPtrAccess(base, element->itup);
 
 	for (int i = 0; i < neighbors->length; i++)
 	{
 		HnswCandidate *neighbor = &neighbors->items[i];
 		HnswElement neighborElement = HnswPtrAccess(base, neighbor->element);
-		Datum		neighborValue = HnswGetValue(base, neighborElement);
 
-		/* Exit early since ordered by distance */
-		if (!datumIsEqual(value, neighborValue, false, -1))
-			return false;
+		if (HnswUseIndexTuple(index))
+		{
+			/* Exit early since ordered by distance */
+			if (!HnswIndexTupleIsEqual(itup, HnswPtrAccess(base, neighborElement->itup), tupdesc))
+				return false;
+		}
+		else
+		{
+			/* Exit early since ordered by distance */
+			if (!datumIsEqual(value, HnswGetValue(base, neighborElement), false, -1))
+				return false;
+		}
 
 		if (AddDuplicateOnDisk(index, element, neighborElement, building))
 			return true;
@@ -660,12 +673,12 @@ FindDuplicateOnDisk(Relation index, HnswElement element, bool building)
  * Update graph on disk
  */
 static void
-UpdateGraphOnDisk(Relation index, HnswSupport * support, HnswElement element, int m, int efConstruction, HnswElement entryPoint, bool building)
+UpdateGraphOnDisk(Relation index, HnswSupport * support, HnswElement element, int m, int efConstruction, HnswElement entryPoint, bool building, TupleDesc tupdesc)
 {
 	BlockNumber newInsertPage = InvalidBlockNumber;
 
 	/* Look for duplicate */
-	if (FindDuplicateOnDisk(index, element, building))
+	if (FindDuplicateOnDisk(index, element, building, tupdesc))
 		return;
 
 	/* Add element */
@@ -687,7 +700,7 @@ UpdateGraphOnDisk(Relation index, HnswSupport * support, HnswElement element, in
  * Insert a tuple into the index
  */
 bool
-HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPointer heaptid, bool building)
+HnswInsertTupleOnDisk(Relation index, HnswSupport * support, IndexTuple itup, ItemPointer heaptid, bool building, TupleDesc tupdesc)
 {
 	HnswElement entryPoint;
 	HnswElement element;
@@ -695,6 +708,7 @@ HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPo
 	int			efConstruction = HnswGetEfConstruction(index);
 	LOCKMODE	lockmode = ShareLock;
 	char	   *base = NULL;
+	bool		unused;
 
 	/*
 	 * Get a shared lock. This allows vacuum to ensure no in-flight inserts
@@ -708,7 +722,8 @@ HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPo
 
 	/* Create an element */
 	element = HnswInitElement(base, heaptid, m, HnswGetMl(m), HnswGetMaxLevel(m), NULL);
-	HnswPtrStore(base, element->value, DatumGetPointer(value));
+	HnswPtrStore(base, element->itup, itup);
+	HnswPtrStore(base, element->value, DatumGetPointer(index_getattr(itup, 1, tupdesc, &unused)));
 
 	/* Prevent concurrent inserts when likely updating entry point */
 	if (entryPoint == NULL || element->level > entryPoint->level)
@@ -725,10 +740,10 @@ HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPo
 	}
 
 	/* Find neighbors for element */
-	HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, false);
+	HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, false, false);
 
 	/* Update graph on disk */
-	UpdateGraphOnDisk(index, support, element, m, efConstruction, entryPoint, building);
+	UpdateGraphOnDisk(index, support, element, m, efConstruction, entryPoint, building, tupdesc);
 
 	/* Release lock */
 	UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);
@@ -742,17 +757,18 @@ HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPo
 static void
 HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid)
 {
-	Datum		value;
+	IndexTuple	itup;
 	const		HnswTypeInfo *typeInfo = HnswGetTypeInfo(index);
+	TupleDesc	tupdesc = RelationGetDescr(index);
 	HnswSupport support;
 
 	HnswInitSupport(&support, index);
 
-	/* Form index value */
-	if (!HnswFormIndexValue(&value, values, isnull, typeInfo, &support))
+	/* Form index tuple */
+	if (!HnswFormIndexTuple(&itup, values, isnull, typeInfo, &support, tupdesc))
 		return;
 
-	HnswInsertTupleOnDisk(index, &support, value, heaptid, false);
+	HnswInsertTupleOnDisk(index, &support, itup, heaptid, false, tupdesc);
 }
 
 /*

src/hnswscan.c

@@ -22,26 +22,30 @@ GetScanItems(IndexScanDesc scan, Datum value)
 	int			m;
 	HnswElement entryPoint;
 	char	   *base = NULL;
+	bool		inMemory = false;
 	HnswQuery  *q = &so->q;
 
+	q->value = value;
+	q->itup = NULL;
+	q->keyData = scan->keyData;
+
 	/* Get m and entry point */
 	HnswGetMetaPageInfo(index, &m, &entryPoint);
 
-	q->value = value;
 	so->m = m;
 
 	if (entryPoint == NULL)
 		return NIL;
 
-	ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, support, false));
+	ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, support, false, inMemory));
 
 	for (int lc = entryPoint->level; lc >= 1; lc--)
 	{
-		w = HnswSearchLayer(base, q, ep, 1, lc, index, support, m, false, NULL, NULL, NULL, true, NULL);
+		w = HnswSearchLayer(base, q, ep, 1, lc, index, support, m, false, NULL, inMemory, NULL, NULL, true, NULL);
 		ep = w;
 	}
 
-	return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, support, m, false, NULL, &so->v, hnsw_iterative_search != HNSW_ITERATIVE_SEARCH_OFF ? &so->discarded : NULL, true, &so->tuples);
+	return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, support, m, false, NULL, inMemory, &so->v, hnsw_iterative_search != HNSW_ITERATIVE_SEARCH_OFF ? &so->discarded : NULL, true, &so->tuples);
 }
 
 /*
@@ -72,7 +76,7 @@ ResumeScanItems(IndexScanDesc scan)
 		ep = lappend(ep, sc);
 	}
 
-	return HnswSearchLayer(base, &so->q, ep, batch_size, 0, index, &so->support, so->m, false, NULL, &so->v, &so->discarded, false, &so->tuples);
+	return HnswSearchLayer(base, &so->q, ep, batch_size, 0, index, &so->support, so->m, false, NULL, false, &so->v, &so->discarded, false, &so->tuples);
 }
 
 /*
@@ -96,23 +100,12 @@ GetScanValue(IndexScanDesc scan)
 
 		/* Normalize if needed */
 		if (so->support.normprocinfo != NULL)
-			value = HnswNormValue(so->typeInfo, so->support.collation, value);
+			value = HnswNormValue(so->typeInfo, so->support.collation[0], value);
 	}
 
 	return value;
 }
 
-#if defined(HNSW_MEMORY)
-/*
- * Show memory usage
- */
-static void
-ShowMemoryUsage(HnswScanOpaque so)
-{
-	elog(INFO, "memory: %zu KB, tuples: " INT64_FORMAT, MemoryContextMemAllocated(so->tmpCtx, false) / 1024, so->tuples);
-}
-#endif
-
 /*
  * Prepare for an index scan
  */
@@ -129,14 +122,9 @@ hnswbeginscan(Relation index, int nkeys, int norderbys)
 	so->first = true;
 	so->v.tids = NULL;
 	so->discarded = NULL;
-
-	/*
-	 * Use a lower max allocation size than default to allow scanning more
-	 * tuples for iterative search before exceeding work_mem
-	 */
 	so->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
 									   "Hnsw scan temporary context",
-									   0, 8 * 1024, 512 * 1024);
+									   ALLOCSET_DEFAULT_SIZES);
 
 	/* Set support functions */
 	HnswInitSupport(&so->support, index);
@@ -220,7 +208,7 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 		so->first = false;
 
 #if defined(HNSW_MEMORY)
-		ShowMemoryUsage(so);
+		elog(INFO, "memory: %zu KB", MemoryContextMemAllocated(so->tmpCtx, false) / 1024);
 #endif
 	}
 
@@ -240,8 +228,8 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 			if (so->discarded == NULL)
 				break;
 
-			/* Reached max number of tuples */
-			if (hnsw_max_search_tuples != -1 && so->tuples >= hnsw_max_search_tuples)
+			/* Reached max number of additional tuples */
+			if (hnsw_iterative_search_max_tuples != -1 && so->tuples >= hnsw_iterative_search_max_tuples)
 			{
 				if (pairingheap_is_empty(so->discarded))
 					break;
@@ -282,7 +270,7 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 				UnlockPage(scan->indexRelation, HNSW_SCAN_LOCK, ShareLock);
 
 #if defined(HNSW_MEMORY)
-				ShowMemoryUsage(so);
+				elog(INFO, "memory: %zu KB", MemoryContextMemAllocated(so->tmpCtx, false) / 1024);
 #endif
 			}
 
@@ -294,7 +282,7 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 		element = HnswPtrAccess(base, sc->element);
 
 		/* Move to next element if no valid heap TIDs */
-		if (element->heaptidsLength == 0)
+		if (!sc->matches || element->heaptidsLength == 0)
 		{
 			so->w = list_delete_last(so->w);
 

src/hnswutils.c

@@ -1,6 +1,5 @@
 #include "postgres.h"
 
-#include <float.h>
 #include <math.h>
 
 #include "access/generic_xlog.h"
@@ -147,20 +146,45 @@ HnswOptionalProcInfo(Relation index, uint16 procnum)
 void
 HnswInitSupport(HnswSupport * support, Relation index)
 {
-	support->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
-	support->collation = index->rd_indcollation[0];
+	support->procinfo[0] = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
+
+	if (IndexRelationGetNumberOfKeyAttributes(index) > 1)
+		support->procinfo[1] = index_getprocinfo(index, 2, HNSW_ATTRIBUTE_DISTANCE_PROC);
+
+	support->collation = index->rd_indcollation;
 	support->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
 }
 
+/*
+ * Get element tuple size
+ */
+Size
+HnswGetElementTupleSize(char *base, HnswElement element, bool useIndexTuple)
+{
+	Size		size;
+
+	if (useIndexTuple)
+	{
+		IndexTuple	itup = HnswPtrAccess(base, element->itup);
+
+		size = IndexTupleSize(itup);
+	}
+	else
+	{
+		Pointer		valuePtr = HnswPtrAccess(base, element->value);
+
+		size = VARSIZE_ANY(valuePtr);
+	}
+
+	return HNSW_ELEMENT_TUPLE_SIZE(size);
+}
+
 /*
  * Normalize value
  */
 Datum
 HnswNormValue(const HnswTypeInfo * typeInfo, Oid collation, Datum value)
 {
-	if (!typeInfo->normalize)
-		return value;
-
 	return DirectFunctionCall1Coll(typeInfo->normalize, collation, value);
 }
 
@@ -170,7 +194,38 @@ HnswNormValue(const HnswTypeInfo * typeInfo, Oid collation, Datum value)
 bool
 HnswCheckNorm(HnswSupport * support, Datum value)
 {
-	return DatumGetFloat8(FunctionCall1Coll(support->normprocinfo, support->collation, value)) > 0;
+	return DatumGetFloat8(FunctionCall1Coll(support->normprocinfo, support->collation[0], value)) > 0;
+}
+
+/*
+ * Check if index tuples are equal
+ */
+bool
+HnswIndexTupleIsEqual(IndexTuple a, IndexTuple b, TupleDesc tupdesc)
+{
+	for (int i = 0; i < tupdesc->natts; i++)
+	{
+		bool		nullA;
+		bool		nullB;
+
+		Datum		datumA = index_getattr(a, i + 1, tupdesc, &nullA);
+		Datum		datumB = index_getattr(b, i + 1, tupdesc, &nullB);
+
+		if (nullA || nullB)
+		{
+			if (nullA != nullB)
+				return false;
+		}
+		else
+		{
+			Form_pg_attribute att = TupleDescAttr(tupdesc, i);
+
+			if (!datumIsEqual(datumA, datumB, att->attbyval, att->attlen))
+				return false;
+		}
+	}
+
+	return true;
 }
 
 /*
@@ -261,6 +316,7 @@ HnswInitElement(char *base, ItemPointer heaptid, int m, double ml, int maxLevel,
 	HnswInitNeighbors(base, element, m, allocator);
 
 	HnswPtrStore(base, element->value, (Pointer) NULL);
+	HnswPtrStore(base, element->itup, (IndexTuple) NULL);
 
 	return element;
 }
@@ -287,6 +343,7 @@ HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno)
 	element->offno = offno;
 	HnswPtrStore(base, element->neighbors, (HnswNeighborArrayPtr *) NULL);
 	HnswPtrStore(base, element->value, (Pointer) NULL);
+	HnswPtrStore(base, element->itup, (IndexTuple) NULL);
 	return element;
 }
 
@@ -399,11 +456,13 @@ HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, Bloc
 }
 
 /*
- * Form index value
+ * Form index tuple
  */
 bool
-HnswFormIndexValue(Datum *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, HnswSupport * support)
+HnswFormIndexTuple(IndexTuple *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, HnswSupport * support, TupleDesc tupdesc)
 {
+	Datum		newValues[2];
+
 	/* Detoast once for all calls */
 	Datum		value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
 
@@ -417,10 +476,14 @@ HnswFormIndexValue(Datum *out, Datum *values, bool *isnull, const HnswTypeInfo *
 		if (!HnswCheckNorm(support, value))
 			return false;
 
-		value = HnswNormValue(typeInfo, support->collation, value);
+		value = HnswNormValue(typeInfo, support->collation[0], value);
 	}
 
-	*out = value;
+	newValues[0] = value;
+	for (int i = 1; i < tupdesc->natts; i++)
+		newValues[i] = values[i];
+
+	*out = index_form_tuple(tupdesc, newValues, isnull);
 
 	return true;
 }
@@ -429,10 +492,8 @@ HnswFormIndexValue(Datum *out, Datum *values, bool *isnull, const HnswTypeInfo *
  * Set element tuple, except for neighbor info
  */
 void
-HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element)
+HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element, bool useIndexTuple)
 {
-	Pointer		valuePtr = HnswPtrAccess(base, element->value);
-
 	etup->type = HNSW_ELEMENT_TUPLE_TYPE;
 	etup->level = element->level;
 	etup->deleted = 0;
@@ -444,7 +505,19 @@ HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element)
 		else
 			ItemPointerSetInvalid(&etup->heaptids[i]);
 	}
-	memcpy(&etup->data, valuePtr, VARSIZE_ANY(valuePtr));
+
+	if (useIndexTuple)
+	{
+		IndexTuple	itup = HnswPtrAccess(base, element->itup);
+
+		memcpy(&etup->data, itup, IndexTupleSize(itup));
+	}
+	else
+	{
+		Pointer		valuePtr = HnswPtrAccess(base, element->value);
+
+		memcpy(&etup->data, valuePtr, VARSIZE_ANY(valuePtr));
+	}
 }
 
 /*
@@ -486,7 +559,7 @@ HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, int m)
  * Load an element from a tuple
  */
 void
-HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec)
+HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec, Relation index)
 {
 	element->level = etup->level;
 	element->deleted = etup->deleted;
@@ -510,26 +583,128 @@ HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHe
 	if (loadVec)
 	{
 		char	   *base = NULL;
-		Datum		value = datumCopy(PointerGetDatum(&etup->data), false, -1);
 
-		HnswPtrStore(base, element->value, DatumGetPointer(value));
+		if (HnswUseIndexTuple(index))
+		{
+			IndexTuple	itup = CopyIndexTuple((IndexTuple) &etup->data);
+			TupleDesc	tupdesc = RelationGetDescr(index);
+			bool		unused;
+
+			HnswPtrStore(base, element->itup, itup);
+			HnswPtrStore(base, element->value, DatumGetPointer(index_getattr(itup, 1, tupdesc, &unused)));
+		}
+		else
+		{
+			Datum		value = datumCopy(PointerGetDatum(&etup->data), false, -1);
+
+			HnswPtrStore(base, element->value, DatumGetPointer(value));
+		}
 	}
 }
 
+/*
+ * Get the attribute distance
+ */
+static inline double
+AttributeDistance(double e)
+{
+	/* TODO Better bias */
+	/* must be >> max(w * g) + 1 / log10(2) */
+	double		bias = 4.32;
+
+	return e > 0 ? bias - 1.0 / log10(e + 1) : 0;
+}
+
 /*
  * Calculate the distance between values
  */
-static inline double
-HnswGetDistance(Datum a, Datum b, HnswSupport * support)
+static double
+HnswGetDistance(IndexTuple itup, Datum vec, HnswQuery * q, Relation index, HnswSupport * support, bool *matches)
 {
-	return DatumGetFloat8(FunctionCall2Coll(support->procinfo, support->collation, a, b));
+	double		g;
+
+	if (DatumGetPointer(q->value) == NULL)
+		g = 0;
+	else
+		g = DatumGetFloat8(FunctionCall2Coll(support->procinfo[0], support->collation[0], q->value, vec));
+
+	Assert(PointerIsValid(matches));
+	*matches = true;
+
+	if (IndexRelationGetNumberOfKeyAttributes(index) > 1)
+	{
+		double		w = 0.25;
+		double		e = 0.0;
+		TupleDesc	tupdesc = RelationGetDescr(index);
+
+		if (q->keyData)
+		{
+			/* TODO need to pass length of key data */
+			int			keyCount = 1;
+
+			for (int i = 0; i < keyCount; i++)
+			{
+				ScanKey		key = &q->keyData[i];
+				bool		isnull;
+				Datum		value = index_getattr(itup, key->sk_attno, tupdesc, &isnull);
+				bool		attnull = key->sk_flags & SK_ISNULL;
+
+				if (isnull || attnull)
+				{
+					if (isnull != attnull)
+					{
+						e += 1000;
+						*matches = false;
+					}
+				}
+				else if (!DatumGetBool(FunctionCall2Coll(&key->sk_func, key->sk_collation, value, key->sk_argument)))
+				{
+					double		ei = fabs(DatumGetFloat8(FunctionCall2Coll(support->procinfo[key->sk_attno - 1], support->collation[key->sk_attno - 1], value, key->sk_argument)));
+
+					if (ei > 0)
+						e += ei;
+					else
+						/* Distance is zero for inequality */
+						e += 1000;
+
+					*matches = false;
+				}
+			}
+
+			return w * g + AttributeDistance(e);
+		}
+		else if (q->itup)
+		{
+			int			keyCount = IndexRelationGetNumberOfKeyAttributes(index) - 1;
+
+			for (int i = 0; i < keyCount; i++)
+			{
+				bool		isnull;
+				bool		attnull;
+				Datum		value = index_getattr(itup, i + 2, tupdesc, &isnull);
+				Datum		value2 = index_getattr(q->itup, i + 2, tupdesc, &attnull);
+
+				if (isnull || attnull)
+				{
+					if (isnull != attnull)
+						e += 1000;
+				}
+				else
+					e += fabs(DatumGetFloat8(FunctionCall2Coll(support->procinfo[i + 1], support->collation[i + 1], value, value2)));
+			}
+
+			return w * g + AttributeDistance(e);
+		}
+	}
+
+	return g;
 }
 
 /*
  * Load an element and optionally get its distance from q
  */
 static void
-HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance, HnswElement * element)
+HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, bool *matches, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance, HnswElement * element)
 {
 	Buffer		buf;
 	Page		page;
@@ -547,17 +722,23 @@ HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, Hns
 	/* Calculate distance */
 	if (distance != NULL)
 	{
-		if (DatumGetPointer(q->value) == NULL)
-			*distance = 0;
+		IndexTuple	itup = NULL;
+		Datum		value;
+
+		if (HnswUseIndexTuple(index))
+		{
+			TupleDesc	tupdesc = RelationGetDescr(index);
+			bool		unused;
+
+			itup = (IndexTuple) &etup->data;
+			value = index_getattr(itup, 1, tupdesc, &unused);
+		}
 		else
 		{
-			*distance = HnswGetDistance(q->value, PointerGetDatum(&etup->data), support);
-
-			/* Needed for intvec cosine distance */
-			/* TODO Improve */
-			if (isnan(*distance))
-				*distance = DBL_MAX;
+			value = PointerGetDatum(&etup->data);
 		}
+
+		*distance = HnswGetDistance(itup, value, q, index, support, matches);
 	}
 
 	/* Load element */
@@ -566,7 +747,7 @@ HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, Hns
 		if (*element == NULL)
 			*element = HnswInitElementFromBlock(blkno, offno);
 
-		HnswLoadElementFromTuple(*element, etup, true, loadVec);
+		HnswLoadElementFromTuple(*element, etup, true, loadVec, index);
 	}
 
 	UnlockReleaseBuffer(buf);
@@ -576,50 +757,37 @@ HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, Hns
  * Load an element and optionally get its distance from q
  */
 void
-HnswLoadElement(HnswElement element, double *distance, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance)
+HnswLoadElement(HnswElement element, double *distance, bool *matches, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance)
 {
-	HnswLoadElementImpl(element->blkno, element->offno, distance, q, index, support, loadVec, maxDistance, &element);
+	HnswLoadElementImpl(element->blkno, element->offno, distance, matches, q, index, support, loadVec, maxDistance, &element);
 }
 
 /*
  * Get the distance for an element
  */
 static double
-GetElementDistance(char *base, HnswElement element, HnswQuery * q, HnswSupport * support)
+GetElementDistance(char *base, HnswElement element, bool *matches, HnswQuery * q, Relation index, HnswSupport * support)
 {
 	Datum		value = HnswGetValue(base, element);
+	IndexTuple	itup = HnswPtrAccess(base, element->itup);
 
-	return HnswGetDistance(q->value, value, support);
-}
-
-/*
- * Allocate a search candidate
- */
-static HnswSearchCandidate *
-HnswInitSearchCandidate(char *base, HnswElement element, double distance)
-{
-	HnswSearchCandidate *sc = palloc(sizeof(HnswSearchCandidate));
-
-	HnswPtrStore(base, sc->element, element);
-	sc->distance = distance;
-	return sc;
+	return HnswGetDistance(itup, value, q, index, support, matches);
 }
 
 /*
  * Create a candidate for the entry point
  */
 HnswSearchCandidate *
-HnswEntryCandidate(char *base, HnswElement entryPoint, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec)
+HnswEntryCandidate(char *base, HnswElement entryPoint, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, bool inMemory)
 {
-	bool		inMemory = index == NULL;
-	double		distance;
+	HnswSearchCandidate *sc = palloc(sizeof(HnswSearchCandidate));
 
+	HnswPtrStore(base, sc->element, entryPoint);
 	if (inMemory)
-		distance = GetElementDistance(base, entryPoint, q, support);
+		sc->distance = GetElementDistance(base, entryPoint, &sc->matches, q, index, support);
 	else
-		HnswLoadElement(entryPoint, &distance, q, index, support, loadVec, NULL);
-
-	return HnswInitSearchCandidate(base, entryPoint, distance);
+		HnswLoadElement(entryPoint, &sc->distance, &sc->matches, q, index, support, loadVec, NULL);
+	return sc;
 }
 
 /*
@@ -822,7 +990,7 @@ HnswLoadUnvisitedFromDisk(HnswElement element, HnswUnvisited * unvisited, int *u
  * Algorithm 2 from paper
  */
 List *
-HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement, visited_hash * v, pairingheap **discarded, bool initVisited, int64 *tuples)
+HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement, bool inMemory, visited_hash * v, pairingheap **discarded, bool initVisited, int64 *tuples)
 {
 	List	   *w = NIL;
 	pairingheap *C = pairingheap_allocate(CompareNearestCandidates, NULL);
@@ -835,7 +1003,8 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 	int			lm = HnswGetLayerM(m, lc);
 	HnswUnvisited *unvisited = palloc(lm * sizeof(HnswUnvisited));
 	int			unvisitedLength;
-	bool		inMemory = index == NULL;
+	uint64		additional = 0;
+	uint64		maxAdditional = q->keyData && lc == 0 ? 10000 : 0;
 
 	if (v == NULL)
 	{
@@ -875,6 +1044,10 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 		pairingheap_add(C, &sc->c_node);
 		pairingheap_add(W, &sc->w_node);
 
+		/* Do not count elements that do not match filter towards ef */
+		if (!sc->matches && ++additional <= maxAdditional)
+			continue;
+
 		/*
 		 * Do not count elements being deleted towards ef when vacuuming. It
 		 * would be ideal to do this for inserts as well, but this could
@@ -908,6 +1081,7 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 			HnswElement eElement;
 			HnswSearchCandidate *e;
 			double		eDistance;
+			bool		eMatches;
 			bool		alwaysAdd = wlen < ef;
 
 			f = HnswGetSearchCandidate(w_node, pairingheap_first(W));
@@ -915,7 +1089,7 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 			if (inMemory)
 			{
 				eElement = unvisited[i].element;
-				eDistance = GetElementDistance(base, eElement, q, support);
+				eDistance = GetElementDistance(base, eElement, &eMatches, q, index, support);
 			}
 			else
 			{
@@ -925,7 +1099,7 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 
 				/* Avoid any allocations if not adding */
 				eElement = NULL;
-				HnswLoadElementImpl(blkno, offno, &eDistance, q, index, support, inserting, alwaysAdd || discarded != NULL ? NULL : &f->distance, &eElement);
+				HnswLoadElementImpl(blkno, offno, &eDistance, &eMatches, q, index, support, inserting, alwaysAdd || discarded != NULL ? NULL : &f->distance, &eElement);
 
 				if (eElement == NULL)
 					continue;
@@ -936,7 +1110,9 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 				if (discarded != NULL)
 				{
 					/* Create a new candidate */
-					e = HnswInitSearchCandidate(base, eElement, eDistance);
+					e = palloc(sizeof(HnswSearchCandidate));
+					HnswPtrStore(base, e->element, eElement);
+					e->distance = eDistance;
 					pairingheap_add(*discarded, &e->w_node);
 				}
 
@@ -948,7 +1124,10 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 				continue;
 
 			/* Create a new candidate */
-			e = HnswInitSearchCandidate(base, eElement, eDistance);
+			e = palloc(sizeof(HnswSearchCandidate));
+			HnswPtrStore(base, e->element, eElement);
+			e->distance = eDistance;
+			e->matches = eMatches;
 			pairingheap_add(C, &e->c_node);
 			pairingheap_add(W, &e->w_node);
 
@@ -959,6 +1138,10 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 			 */
 			if (CountElement(skipElement, eElement))
 			{
+				/* Do not count elements that do not match filter towards ef */
+				if (!e->matches && ++additional <= maxAdditional)
+					continue;
+
 				wlen++;
 
 				/* No need to decrement wlen */
@@ -1036,18 +1219,24 @@ CompareCandidateDistancesOffset(const ListCell *a, const ListCell *b)
  * Check if an element is closer to q than any element from R
  */
 static bool
-CheckElementCloser(char *base, HnswCandidate * e, List *r, HnswSupport * support)
+CheckElementCloser(char *base, HnswCandidate * e, List *r, Relation index, HnswSupport * support)
 {
 	HnswElement eElement = HnswPtrAccess(base, e->element);
-	Datum		eValue = HnswGetValue(base, eElement);
+	HnswQuery	q;
 	ListCell   *lc2;
 
+	q.value = HnswGetValue(base, eElement);
+	q.itup = HnswPtrAccess(base, eElement->itup);
+	q.keyData = NULL;
+
 	foreach(lc2, r)
 	{
 		HnswCandidate *ri = lfirst(lc2);
 		HnswElement riElement = HnswPtrAccess(base, ri->element);
 		Datum		riValue = HnswGetValue(base, riElement);
-		float		distance = HnswGetDistance(eValue, riValue, support);
+		IndexTuple	ritup = HnswPtrAccess(base, riElement->itup);
+		bool		matches;
+		float		distance = HnswGetDistance(ritup, riValue, &q, index, support, &matches);
 
 		if (distance <= e->distance)
 			return false;
@@ -1060,7 +1249,7 @@ CheckElementCloser(char *base, HnswCandidate * e, List *r, HnswSupport * support
  * Algorithm 4 from paper
  */
 static List *
-SelectNeighbors(char *base, List *c, int lm, HnswSupport * support, bool *closerSet, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates)
+SelectNeighbors(char *base, List *c, int lm, Relation index, HnswSupport * support, bool *closerSet, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates)
 {
 	List	   *r = NIL;
 	List	   *w = list_copy(c);
@@ -1094,7 +1283,7 @@ SelectNeighbors(char *base, List *c, int lm, HnswSupport * support, bool *closer
 
 		/* Use previous state of r and wd to skip work when possible */
 		if (mustCalculate)
-			e->closer = CheckElementCloser(base, e, r, support);
+			e->closer = CheckElementCloser(base, e, r, index, support);
 		else if (list_length(added) > 0)
 		{
 			/* Keep Valgrind happy for in-memory, parallel builds */
@@ -1107,8 +1296,7 @@ SelectNeighbors(char *base, List *c, int lm, HnswSupport * support, bool *closer
 			 */
 			if (e->closer)
 			{
-				e->closer = CheckElementCloser(base, e, added, support);
-
+				e->closer = CheckElementCloser(base, e, added, index, support);
 				if (!e->closer)
 					removedAny = true;
 			}
@@ -1120,7 +1308,7 @@ SelectNeighbors(char *base, List *c, int lm, HnswSupport * support, bool *closer
 				 */
 				if (removedAny)
 				{
-					e->closer = CheckElementCloser(base, e, r, support);
+					e->closer = CheckElementCloser(base, e, r, index, support);
 					if (e->closer)
 						added = lappend(added, e);
 				}
@@ -1128,7 +1316,7 @@ SelectNeighbors(char *base, List *c, int lm, HnswSupport * support, bool *closer
 		}
 		else if (e == newCandidate)
 		{
-			e->closer = CheckElementCloser(base, e, r, support);
+			e->closer = CheckElementCloser(base, e, r, index, support);
 			if (e->closer)
 				added = lappend(added, e);
 		}
@@ -1205,7 +1393,7 @@ HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newE
 			c = lappend(c, &neighbors->items[i]);
 		c = lappend(c, &newHc);
 
-		SelectNeighbors(base, c, lm, support, &neighbors->closerSet, &newHc, &pruned, true);
+		SelectNeighbors(base, c, lm, index, support, &neighbors->closerSet, &newHc, &pruned, true);
 
 		/* Should not happen */
 		if (pruned == NULL)
@@ -1276,17 +1464,19 @@ PrecomputeHash(char *base, HnswElement element)
  * Algorithm 1 from paper
  */
 void
-HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing)
+HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing, bool inMemory)
 {
 	List	   *ep;
 	List	   *w;
 	int			level = element->level;
 	int			entryLevel;
 	HnswQuery	q;
+
 	HnswElement skipElement = existing ? element : NULL;
-	bool		inMemory = index == NULL;
 
 	q.value = HnswGetValue(base, element);
+	q.itup = HnswPtrAccess(base, element->itup);
+	q.keyData = NULL;
 
 	/* Precompute hash */
 	if (inMemory)
@@ -1297,13 +1487,13 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
 		return;
 
 	/* Get entry point and level */
-	ep = list_make1(HnswEntryCandidate(base, entryPoint, &q, index, support, true));
+	ep = list_make1(HnswEntryCandidate(base, entryPoint, &q, index, support, true, inMemory));
 	entryLevel = entryPoint->level;
 
 	/* 1st phase: greedy search to insert level */
 	for (int lc = entryLevel; lc >= level + 1; lc--)
 	{
-		w = HnswSearchLayer(base, &q, ep, 1, lc, index, support, m, true, skipElement, NULL, NULL, true, NULL);
+		w = HnswSearchLayer(base, &q, ep, 1, lc, index, support, m, true, skipElement, inMemory, NULL, NULL, true, NULL);
 		ep = w;
 	}
 
@@ -1322,7 +1512,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
 		List	   *lw = NIL;
 		ListCell   *lc2;
 
-		w = HnswSearchLayer(base, &q, ep, efConstruction, lc, index, support, m, true, skipElement, NULL, NULL, true, NULL);
+		w = HnswSearchLayer(base, &q, ep, efConstruction, lc, index, support, m, true, skipElement, inMemory, NULL, NULL, true, NULL);
 
 		/* Convert search candidates to candidates */
 		foreach(lc2, w)
@@ -1346,7 +1536,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
 		 * sortCandidates to true for in-memory builds to enable closer
 		 * caching, but there does not seem to be a difference in performance.
 		 */
-		neighbors = SelectNeighbors(base, lw, lm, support, &HnswGetNeighbors(base, element, lc)->closerSet, NULL, NULL, false);
+		neighbors = SelectNeighbors(base, lw, lm, index, support, &HnswGetNeighbors(base, element, lc)->closerSet, NULL, NULL, false);
 
 		AddConnections(base, element, neighbors, lc);
 
@@ -1404,19 +1594,6 @@ hnsw_halfvec_support(PG_FUNCTION_ARGS)
 	PG_RETURN_POINTER(&typeInfo);
 };
 
-FUNCTION_PREFIX PG_FUNCTION_INFO_V1(hnsw_intvec_support);
-Datum
-hnsw_intvec_support(PG_FUNCTION_ARGS)
-{
-	static const HnswTypeInfo typeInfo = {
-		.maxDimensions = HNSW_MAX_DIM * 4,
-		.normalize = NULL,
-		.checkValue = NULL
-	};
-
-	PG_RETURN_POINTER(&typeInfo);
-};
-
 FUNCTION_PREFIX PG_FUNCTION_INFO_V1(hnsw_bit_support);
 Datum
 hnsw_bit_support(PG_FUNCTION_ARGS)

src/hnswvacuum.c

@@ -204,7 +204,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
 	element->heaptidsLength = 0;
 
 	/* Find neighbors for element, skipping itself */
-	HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, true);
+	HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, true, false);
 
 	/* Zero memory for each element */
 	MemSet(ntup, 0, HNSW_TUPLE_ALLOC_SIZE);
@@ -256,7 +256,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
 		LockPage(index, HNSW_UPDATE_LOCK, ShareLock);
 
 		/* Load element */
-		HnswLoadElement(highestPoint, NULL, NULL, index, support, true, NULL);
+		HnswLoadElement(highestPoint, NULL, NULL, NULL, index, support, true, NULL);
 
 		/* Repair if needed */
 		if (NeedsUpdated(vacuumstate, highestPoint))
@@ -294,7 +294,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
 			 * is outdated, this can remove connections at higher levels in
 			 * the graph until they are repaired, but this should be fine.
 			 */
-			HnswLoadElement(entryPoint, NULL, NULL, index, support, true, NULL);
+			HnswLoadElement(entryPoint, NULL, NULL, NULL, index, support, true, NULL);
 
 			if (NeedsUpdated(vacuumstate, entryPoint))
 			{
@@ -370,7 +370,7 @@ RepairGraph(HnswVacuumState * vacuumstate)
 
 			/* Create an element */
 			element = HnswInitElementFromBlock(blkno, offno);
-			HnswLoadElementFromTuple(element, etup, false, true);
+			HnswLoadElementFromTuple(element, etup, false, true, index);
 
 			elements = lappend(elements, element);
 		}
@@ -440,6 +440,7 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 	BlockNumber insertPage = InvalidBlockNumber;
 	Relation	index = vacuumstate->index;
 	BufferAccessStrategy bas = vacuumstate->bas;
+	bool		useIndexTuple = HnswUseIndexTuple(index);
 
 	/*
 	 * Wait for index scans to complete. Scans before this point may contain
@@ -521,7 +522,14 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 
 			/* Overwrite element */
 			etup->deleted = 1;
-			MemSet(&etup->data, 0, VARSIZE_ANY(&etup->data));
+			if (useIndexTuple)
+			{
+				IndexTuple	itup = (IndexTuple) &etup->data;
+
+				MemSet(itup, 0, IndexTupleSize(itup));
+			}
+			else
+				MemSet(&etup->data, 0, VARSIZE_ANY(&etup->data));
 
 			/* Overwrite neighbors */
 			for (int i = 0; i < ntup->count; i++)

src/intvec.c

@@ -1,754 +0,0 @@
-#include "postgres.h"
-
-#include <limits.h>
-#include <math.h>
-
-#include "catalog/pg_type.h"
-#include "fmgr.h"
-#include "intvec.h"
-#include "lib/stringinfo.h"
-#include "libpq/pqformat.h"
-#include "utils/array.h"
-#include "utils/builtins.h"
-#include "utils/lsyscache.h"
-
-/*
- * Ensure same dimensions
- */
-static inline void
-CheckDims(IntVector * a, IntVector * b)
-{
-	if (a->dim != b->dim)
-		ereport(ERROR,
-				(errcode(ERRCODE_DATA_EXCEPTION),
-				 errmsg("different intvec dimensions %d and %d", a->dim, b->dim)));
-}
-
-/*
- * Ensure expected dimensions
- */
-static inline void
-CheckExpectedDim(int32 typmod, int dim)
-{
-	if (typmod != -1 && typmod != dim)
-		ereport(ERROR,
-				(errcode(ERRCODE_DATA_EXCEPTION),
-				 errmsg("expected %d dimensions, not %d", typmod, dim)));
-}
-
-/*
- * Ensure valid dimensions
- */
-static inline void
-CheckDim(int dim)
-{
-	if (dim < 1)
-		ereport(ERROR,
-				(errcode(ERRCODE_DATA_EXCEPTION),
-				 errmsg("intvec must have at least 1 dimension")));
-
-	if (dim > INTVEC_MAX_DIM)
-		ereport(ERROR,
-				(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
-				 errmsg("intvec cannot have more than %d dimensions", INTVEC_MAX_DIM)));
-}
-
-/*
- * Ensure element in range
- */
-static inline void
-CheckElement(long value)
-{
-	if (value < SCHAR_MIN || value > SCHAR_MAX)
-		ereport(ERROR,
-				(errcode(ERRCODE_NUMERIC_VALUE_OUT_OF_RANGE),
-				 errmsg("value \"%ld\" is out of range for type intvec", value)));
-}
-
-/*
- * Allocate and initialize a new int vector
- */
-IntVector *
-InitIntVector(int dim)
-{
-	IntVector  *result;
-	int			size;
-
-	size = INTVEC_SIZE(dim);
-	result = (IntVector *) palloc0(size);
-	SET_VARSIZE(result, size);
-	result->dim = dim;
-
-	return result;
-}
-
-/*
- * Check for whitespace, since array_isspace() is static
- */
-static inline bool
-intvec_isspace(char ch)
-{
-	if (ch == ' ' ||
-		ch == '\t' ||
-		ch == '\n' ||
-		ch == '\r' ||
-		ch == '\v' ||
-		ch == '\f')
-		return true;
-	return false;
-}
-
-/*
- * Convert textual representation to internal representation
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(intvec_in);
-Datum
-intvec_in(PG_FUNCTION_ARGS)
-{
-	char	   *lit = PG_GETARG_CSTRING(0);
-	int32		typmod = PG_GETARG_INT32(2);
-	int8		x[INTVEC_MAX_DIM];
-	int			dim = 0;
-	char	   *pt = lit;
-	IntVector  *result;
-
-	while (intvec_isspace(*pt))
-		pt++;
-
-	if (*pt != '[')
-		ereport(ERROR,
-				(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
-				 errmsg("invalid input syntax for type intvec: \"%s\"", lit),
-				 errdetail("Vector contents must start with \"[\".")));
-
-	pt++;
-
-	while (intvec_isspace(*pt))
-		pt++;
-
-	if (*pt == ']')
-		ereport(ERROR,
-				(errcode(ERRCODE_DATA_EXCEPTION),
-				 errmsg("intvec must have at least 1 dimension")));
-
-	for (;;)
-	{
-		long		val;
-		char	   *stringEnd;
-
-		if (dim == INTVEC_MAX_DIM)
-			ereport(ERROR,
-					(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
-					 errmsg("intvec cannot have more than %d dimensions", VECTOR_MAX_DIM)));
-
-		while (intvec_isspace(*pt))
-			pt++;
-
-		/* Check for empty string like float4in */
-		if (*pt == '\0')
-			ereport(ERROR,
-					(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
-					 errmsg("invalid input syntax for type intvec: \"%s\"", lit)));
-
-		errno = 0;
-
-		/* Use similar logic as int2vectorin */
-		val = strtol(pt, &stringEnd, 10);
-
-		if (stringEnd == pt)
-			ereport(ERROR,
-					(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
-					 errmsg("invalid input syntax for type intvec: \"%s\"", lit)));
-
-		/* Check for range error like float4in */
-		if (errno == ERANGE || val < SCHAR_MIN || val > SCHAR_MAX)
-			ereport(ERROR,
-					(errcode(ERRCODE_NUMERIC_VALUE_OUT_OF_RANGE),
-					 errmsg("\"%s\" is out of range for type intvec", pnstrdup(pt, stringEnd - pt))));
-
-		CheckElement(val);
-		x[dim++] = val;
-
-		pt = stringEnd;
-
-		while (intvec_isspace(*pt))
-			pt++;
-
-		if (*pt == ',')
-			pt++;
-		else if (*pt == ']')
-		{
-			pt++;
-			break;
-		}
-		else
-			ereport(ERROR,
-					(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
-					 errmsg("invalid input syntax for type intvec: \"%s\"", lit)));
-	}
-
-	/* Only whitespace is allowed after the closing brace */
-	while (intvec_isspace(*pt))
-		pt++;
-
-	if (*pt != '\0')
-		ereport(ERROR,
-				(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
-				 errmsg("invalid input syntax for type intvec: \"%s\"", lit),
-				 errdetail("Junk after closing right brace.")));
-
-	CheckDim(dim);
-	CheckExpectedDim(typmod, dim);
-
-	result = InitIntVector(dim);
-	for (int i = 0; i < dim; i++)
-		result->x[i] = x[i];
-
-	PG_RETURN_POINTER(result);
-}
-
-/*
- * Convert internal representation to textual representation
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(intvec_out);
-Datum
-intvec_out(PG_FUNCTION_ARGS)
-{
-	IntVector  *vector = PG_GETARG_INTVEC_P(0);
-	int			dim = vector->dim;
-	char	   *buf;
-	char	   *ptr;
-
-	/*
-	 * Need:
-	 *
-	 * dim * 4 bytes for elements (-128 to 127)
-	 *
-	 * dim - 1 bytes for separator
-	 *
-	 * 3 bytes for [, ], and \0
-	 */
-	buf = (char *) palloc(5 * dim + 2);
-	ptr = buf;
-
-	*ptr = '[';
-	ptr++;
-	for (int i = 0; i < dim; i++)
-	{
-		if (i > 0)
-		{
-			*ptr = ',';
-			ptr++;
-		}
-
-#if PG_VERSION_NUM >= 140000
-		ptr += pg_ltoa(vector->x[i], ptr);
-#else
-		pg_ltoa(vector->x[i], ptr);
-		while (*ptr != '\0')
-			ptr++;
-#endif
-	}
-	*ptr = ']';
-	ptr++;
-	*ptr = '\0';
-
-	PG_FREE_IF_COPY(vector, 0);
-	PG_RETURN_CSTRING(buf);
-}
-
-/*
- * Convert type modifier
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(intvec_typmod_in);
-Datum
-intvec_typmod_in(PG_FUNCTION_ARGS)
-{
-	ArrayType  *ta = PG_GETARG_ARRAYTYPE_P(0);
-	int32	   *tl;
-	int			n;
-
-	tl = ArrayGetIntegerTypmods(ta, &n);
-
-	if (n != 1)
-		ereport(ERROR,
-				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
-				 errmsg("invalid type modifier")));
-
-	if (*tl < 1)
-		ereport(ERROR,
-				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
-				 errmsg("dimensions for type intvec must be at least 1")));
-
-	if (*tl > INTVEC_MAX_DIM)
-		ereport(ERROR,
-				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
-				 errmsg("dimensions for type intvec cannot exceed %d", INTVEC_MAX_DIM)));
-
-	PG_RETURN_INT32(*tl);
-}
-
-/*
- * Convert external binary representation to internal representation
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(intvec_recv);
-Datum
-intvec_recv(PG_FUNCTION_ARGS)
-{
-	StringInfo	buf = (StringInfo) PG_GETARG_POINTER(0);
-	int32		typmod = PG_GETARG_INT32(2);
-	IntVector  *result;
-	int16		dim;
-	int16		unused;
-
-	dim = pq_getmsgint(buf, sizeof(int16));
-	unused = pq_getmsgint(buf, sizeof(int16));
-
-	CheckDim(dim);
-	CheckExpectedDim(typmod, dim);
-
-	if (unused != 0)
-		ereport(ERROR,
-				(errcode(ERRCODE_DATA_EXCEPTION),
-				 errmsg("expected unused to be 0, not %d", unused)));
-
-	result = InitIntVector(dim);
-	for (int i = 0; i < dim; i++)
-		result->x[i] = pq_getmsgint(buf, sizeof(int8));
-
-	PG_RETURN_POINTER(result);
-}
-
-/*
- * Convert internal representation to the external binary representation
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(intvec_send);
-Datum
-intvec_send(PG_FUNCTION_ARGS)
-{
-	IntVector  *vec = PG_GETARG_INTVEC_P(0);
-	StringInfoData buf;
-
-	pq_begintypsend(&buf);
-	pq_sendint(&buf, vec->dim, sizeof(int16));
-	pq_sendint(&buf, vec->unused, sizeof(int16));
-	for (int i = 0; i < vec->dim; i++)
-		pq_sendint8(&buf, vec->x[i]);
-
-	PG_RETURN_BYTEA_P(pq_endtypsend(&buf));
-}
-
-/*
- * Convert int vector to int vector
- * This is needed to check the type modifier
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(intvec);
-Datum
-intvec(PG_FUNCTION_ARGS)
-{
-	IntVector  *vec = PG_GETARG_INTVEC_P(0);
-	int32		typmod = PG_GETARG_INT32(1);
-
-	CheckExpectedDim(typmod, vec->dim);
-
-	PG_RETURN_POINTER(vec);
-}
-
-/*
- * Convert array to intvec vector
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(array_to_intvec);
-Datum
-array_to_intvec(PG_FUNCTION_ARGS)
-{
-	ArrayType  *array = PG_GETARG_ARRAYTYPE_P(0);
-	int32		typmod = PG_GETARG_INT32(1);
-	IntVector  *result;
-	int16		typlen;
-	bool		typbyval;
-	char		typalign;
-	Datum	   *elemsp;
-	int			nelemsp;
-
-	if (ARR_NDIM(array) > 1)
-		ereport(ERROR,
-				(errcode(ERRCODE_DATA_EXCEPTION),
-				 errmsg("array must be 1-D")));
-
-	if (ARR_HASNULL(array) && array_contains_nulls(array))
-		ereport(ERROR,
-				(errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED),
-				 errmsg("array must not contain nulls")));
-
-	get_typlenbyvalalign(ARR_ELEMTYPE(array), &typlen, &typbyval, &typalign);
-	deconstruct_array(array, ARR_ELEMTYPE(array), typlen, typbyval, typalign, &elemsp, NULL, &nelemsp);
-
-	CheckDim(nelemsp);
-	CheckExpectedDim(typmod, nelemsp);
-
-	result = InitIntVector(nelemsp);
-
-	if (ARR_ELEMTYPE(array) == INT4OID)
-	{
-		for (int i = 0; i < nelemsp; i++)
-		{
-			long		l = DatumGetInt32(elemsp[i]);
-
-			CheckElement(l);
-
-			result->x[i] = l;
-		}
-	}
-	else
-	{
-		ereport(ERROR,
-				(errcode(ERRCODE_DATA_EXCEPTION),
-				 errmsg("unsupported array type")));
-	}
-
-	/*
-	 * Free allocation from deconstruct_array. Do not free individual elements
-	 * when pass-by-reference since they point to original array.
-	 */
-	pfree(elemsp);
-
-	PG_RETURN_POINTER(result);
-}
-
-/*
- * Convert int vector to integer[]
- */
-FUNCTION_PREFIX PG_FUNCTION_INFO_V1(intvec_to_integer);
-Datum
-intvec_to_integer(PG_FUNCTION_ARGS)
-{
-	IntVector  *vec = PG_GETARG_INTVEC_P(0);
-	Datum	   *datums;
-	ArrayType  *result;
-
-	datums = (Datum *) palloc(sizeof(Datum) * vec->dim);
-
-	for (int i = 0; i < vec->dim; i++)
-		datums[i] = Int32GetDatum((int) vec->x[i]);
-
-	result = construct_array(datums, vec->dim, INT4OID, sizeof(int32), true, TYPALIGN_INT);
-
-	pfree(datums);
-
-	PG_RETURN_POINTER(result);
-}
-
-static int
-IntvecL2SquaredDistance(int dim, int8 *ax, int8 *bx)
-{
-	int			distance = 0;
-
-	/* Auto-vectorized */
-	for (int i = 0; i < dim; i++)
-	{
-		int			diff = (int) ax[i] - (int) bx[i];
-
-		distance += diff * diff;
-	}
-
-	return distance;
-}
-
-/*
- * Get the L2 distance between int vectors
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(intvec_l2_distance);
-Datum
-intvec_l2_distance(PG_FUNCTION_ARGS)
-{
-	IntVector  *a = PG_GETARG_INTVEC_P(0);
-	IntVector  *b = PG_GETARG_INTVEC_P(1);
-
-	CheckDims(a, b);
-
-	PG_RETURN_FLOAT8(sqrt((double) IntvecL2SquaredDistance(a->dim, a->x, b->x)));
-}
-
-/*
- * Get the L2 squared distance between int vectors
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(intvec_l2_squared_distance);
-Datum
-intvec_l2_squared_distance(PG_FUNCTION_ARGS)
-{
-	IntVector  *a = PG_GETARG_INTVEC_P(0);
-	IntVector  *b = PG_GETARG_INTVEC_P(1);
-
-	CheckDims(a, b);
-
-	PG_RETURN_FLOAT8((double) IntvecL2SquaredDistance(a->dim, a->x, b->x));
-}
-
-static int
-IntvecInnerProduct(int dim, int8 *ax, int8 *bx)
-{
-	int			distance = 0;
-
-	/* Auto-vectorized */
-	for (int i = 0; i < dim; i++)
-		distance += (int) ax[i] * (int) bx[i];
-
-	return distance;
-}
-
-/*
- * Get the inner product of two int vectors
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(intvec_inner_product);
-Datum
-intvec_inner_product(PG_FUNCTION_ARGS)
-{
-	IntVector  *a = PG_GETARG_INTVEC_P(0);
-	IntVector  *b = PG_GETARG_INTVEC_P(1);
-
-	CheckDims(a, b);
-
-	PG_RETURN_FLOAT8((double) IntvecInnerProduct(a->dim, a->x, b->x));
-}
-
-/*
- * Get the negative inner product of two int vectors
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(intvec_negative_inner_product);
-Datum
-intvec_negative_inner_product(PG_FUNCTION_ARGS)
-{
-	IntVector  *a = PG_GETARG_INTVEC_P(0);
-	IntVector  *b = PG_GETARG_INTVEC_P(1);
-
-	CheckDims(a, b);
-
-	PG_RETURN_FLOAT8((double) -IntvecInnerProduct(a->dim, a->x, b->x));
-}
-
-static double
-IntvecCosineSimilarity(int dim, int8 *ax, int8 *bx)
-{
-	int			similarity = 0;
-	int			norma = 0;
-	int			normb = 0;
-
-	/* Auto-vectorized */
-	for (int i = 0; i < dim; i++)
-	{
-		int			axi = ax[i];
-		int			bxi = bx[i];
-
-		similarity += axi * bxi;
-		norma += axi * axi;
-		normb += bxi * bxi;
-	}
-
-	/* Use sqrt(a * b) over sqrt(a) * sqrt(b) */
-	return (double) similarity / sqrt((double) norma * (double) normb);
-}
-
-/*
- * Get the cosine distance between two int vectors
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(intvec_cosine_distance);
-Datum
-intvec_cosine_distance(PG_FUNCTION_ARGS)
-{
-	IntVector  *a = PG_GETARG_INTVEC_P(0);
-	IntVector  *b = PG_GETARG_INTVEC_P(1);
-	double		similarity;
-
-	CheckDims(a, b);
-
-	similarity = IntvecCosineSimilarity(a->dim, a->x, b->x);
-
-#ifdef _MSC_VER
-	/* /fp:fast may not propagate NaN */
-	if (isnan(similarity))
-		PG_RETURN_FLOAT8(NAN);
-#endif
-
-	/* Keep in range */
-	if (similarity > 1)
-		similarity = 1;
-	else if (similarity < -1)
-		similarity = -1;
-
-	PG_RETURN_FLOAT8(1 - similarity);
-}
-
-static int
-IntvecL1Distance(int dim, int8 *ax, int8 *bx)
-{
-	int			distance = 0;
-
-	/* Auto-vectorized */
-	for (int i = 0; i < dim; i++)
-		distance += abs((int) ax[i] - (int) bx[i]);
-
-	return distance;
-}
-
-/*
- * Get the L1 distance between two int vectors
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(intvec_l1_distance);
-Datum
-intvec_l1_distance(PG_FUNCTION_ARGS)
-{
-	IntVector  *a = PG_GETARG_INTVEC_P(0);
-	IntVector  *b = PG_GETARG_INTVEC_P(1);
-
-	CheckDims(a, b);
-
-	PG_RETURN_FLOAT8((double) IntvecL1Distance(a->dim, a->x, b->x));
-}
-
-/*
- * Get the dimensions of an int vector
- */
-FUNCTION_PREFIX PG_FUNCTION_INFO_V1(intvec_vector_dims);
-Datum
-intvec_vector_dims(PG_FUNCTION_ARGS)
-{
-	IntVector  *a = PG_GETARG_INTVEC_P(0);
-
-	PG_RETURN_INT32(a->dim);
-}
-
-/*
- * Get the L2 norm of an int vector
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(intvec_l2_norm);
-Datum
-intvec_l2_norm(PG_FUNCTION_ARGS)
-{
-	IntVector  *a = PG_GETARG_INTVEC_P(0);
-	int8	   *ax = a->x;
-	int			norm = 0;
-
-	/* Auto-vectorized */
-	for (int i = 0; i < a->dim; i++)
-		norm += (int) ax[i] * (int) ax[i];
-
-	PG_RETURN_FLOAT8(sqrt((double) norm));
-}
-
-/*
- * Internal helper to compare int vectors
- */
-static int
-intvec_cmp_internal(IntVector * a, IntVector * b)
-{
-	int			dim = Min(a->dim, b->dim);
-
-	/* Check values before dimensions to be consistent with Postgres arrays */
-	for (int i = 0; i < dim; i++)
-	{
-		if (a->x[i] < b->x[i])
-			return -1;
-
-		if (a->x[i] > b->x[i])
-			return 1;
-	}
-
-	if (a->dim < b->dim)
-		return -1;
-
-	if (a->dim > b->dim)
-		return 1;
-
-	return 0;
-}
-
-/*
- * Less than
- */
-FUNCTION_PREFIX PG_FUNCTION_INFO_V1(intvec_lt);
-Datum
-intvec_lt(PG_FUNCTION_ARGS)
-{
-	IntVector  *a = PG_GETARG_INTVEC_P(0);
-	IntVector  *b = PG_GETARG_INTVEC_P(1);
-
-	PG_RETURN_BOOL(intvec_cmp_internal(a, b) < 0);
-}
-
-/*
- * Less than or equal
- */
-FUNCTION_PREFIX PG_FUNCTION_INFO_V1(intvec_le);
-Datum
-intvec_le(PG_FUNCTION_ARGS)
-{
-	IntVector  *a = PG_GETARG_INTVEC_P(0);
-	IntVector  *b = PG_GETARG_INTVEC_P(1);
-
-	PG_RETURN_BOOL(intvec_cmp_internal(a, b) <= 0);
-}
-
-/*
- * Equal
- */
-FUNCTION_PREFIX PG_FUNCTION_INFO_V1(intvec_eq);
-Datum
-intvec_eq(PG_FUNCTION_ARGS)
-{
-	IntVector  *a = PG_GETARG_INTVEC_P(0);
-	IntVector  *b = PG_GETARG_INTVEC_P(1);
-
-	PG_RETURN_BOOL(intvec_cmp_internal(a, b) == 0);
-}
-
-/*
- * Not equal
- */
-FUNCTION_PREFIX PG_FUNCTION_INFO_V1(intvec_ne);
-Datum
-intvec_ne(PG_FUNCTION_ARGS)
-{
-	IntVector  *a = PG_GETARG_INTVEC_P(0);
-	IntVector  *b = PG_GETARG_INTVEC_P(1);
-
-	PG_RETURN_BOOL(intvec_cmp_internal(a, b) != 0);
-}
-
-/*
- * Greater than or equal
- */
-FUNCTION_PREFIX PG_FUNCTION_INFO_V1(intvec_ge);
-Datum
-intvec_ge(PG_FUNCTION_ARGS)
-{
-	IntVector  *a = PG_GETARG_INTVEC_P(0);
-	IntVector  *b = PG_GETARG_INTVEC_P(1);
-
-	PG_RETURN_BOOL(intvec_cmp_internal(a, b) >= 0);
-}
-
-/*
- * Greater than
- */
-FUNCTION_PREFIX PG_FUNCTION_INFO_V1(intvec_gt);
-Datum
-intvec_gt(PG_FUNCTION_ARGS)
-{
-	IntVector  *a = PG_GETARG_INTVEC_P(0);
-	IntVector  *b = PG_GETARG_INTVEC_P(1);
-
-	PG_RETURN_BOOL(intvec_cmp_internal(a, b) > 0);
-}
-
-/*
- * Compare int vectors
- */
-FUNCTION_PREFIX PG_FUNCTION_INFO_V1(intvec_cmp);
-Datum
-intvec_cmp(PG_FUNCTION_ARGS)
-{
-	IntVector  *a = PG_GETARG_INTVEC_P(0);
-	IntVector  *b = PG_GETARG_INTVEC_P(1);
-
-	PG_RETURN_INT32(intvec_cmp_internal(a, b));
-}

src/intvec.h

@@ -1,23 +0,0 @@
-#ifndef INTVEC_H
-#define INTVEC_H
-
-#include "vector.h"
-
-#define INTVEC_MAX_DIM VECTOR_MAX_DIM
-
-#define INTVEC_SIZE(_dim)		(offsetof(IntVector, x) + sizeof(int8)*(_dim))
-#define DatumGetIntVector(x)	((IntVector *) PG_DETOAST_DATUM(x))
-#define PG_GETARG_INTVEC_P(x)	DatumGetIntVector(PG_GETARG_DATUM(x))
-#define PG_RETURN_INTVEC_P(x)	PG_RETURN_POINTER(x)
-
-typedef struct IntVector
-{
-	int32		vl_len_;		/* varlena header (do not touch directly!) */
-	int16		dim;			/* number of dimensions */
-	int16		unused;
-	int8		x[FLEXIBLE_ARRAY_MEMBER];
-}			IntVector;
-
-IntVector  *InitIntVector(int dim);
-
-#endif

src/ivfbuild.c

@@ -138,7 +138,7 @@ SampleRows(IvfflatBuildState * buildstate)
  * Add tuple to sort
  */
 static void
-AddTupleToSort(Relation index, ItemPointer tid, Datum *values, IvfflatBuildState * buildstate)
+AddTupleToSort(Relation index, ItemPointer tid, Datum *values, bool *isnull, IvfflatBuildState * buildstate)
 {
 	double		distance;
 	double		minDistance = DBL_MAX;
@@ -184,6 +184,11 @@ AddTupleToSort(Relation index, ItemPointer tid, Datum *values, IvfflatBuildState
 	slot->tts_isnull[1] = false;
 	slot->tts_values[2] = value;
 	slot->tts_isnull[2] = false;
+	for (int i = 1; i < buildstate->tupdesc->natts; i++)
+	{
+		slot->tts_values[2 + i] = values[i];
+		slot->tts_isnull[2 + i] = isnull[i];
+	}
 	ExecStoreVirtualTuple(slot);
 
 	/*
@@ -215,7 +220,7 @@ BuildCallback(Relation index, ItemPointer tid, Datum *values,
 	oldCtx = MemoryContextSwitchTo(buildstate->tmpCtx);
 
 	/* Add tuple to sort */
-	AddTupleToSort(index, tid, values, buildstate);
+	AddTupleToSort(index, tid, values, isnull, buildstate);
 
 	/* Reset memory context */
 	MemoryContextSwitchTo(oldCtx);
@@ -226,19 +231,20 @@ BuildCallback(Relation index, ItemPointer tid, Datum *values,
  * Get index tuple from sort state
  */
 static inline void
-GetNextTuple(Tuplesortstate *sortstate, TupleDesc tupdesc, TupleTableSlot *slot, IndexTuple *itup, int *list)
+GetNextTuple(Tuplesortstate *sortstate, TupleDesc tupdesc, TupleTableSlot *slot, Datum *values, bool *isnull, IndexTuple *itup, int *list)
 {
 	if (tuplesort_gettupleslot(sortstate, true, false, slot, NULL))
 	{
-		Datum		value;
-		bool		isnull;
+		bool		unused;
 
-		*list = DatumGetInt32(slot_getattr(slot, 1, &isnull));
-		value = slot_getattr(slot, 3, &isnull);
+		*list = DatumGetInt32(slot_getattr(slot, 1, &unused));
+
+		for (int i = 0; i < tupdesc->natts; i++)
+			values[i] = slot_getattr(slot, 3 + i, &isnull[i]);
 
 		/* Form the index tuple */
-		*itup = index_form_tuple(tupdesc, &value, &isnull);
-		(*itup)->t_tid = *((ItemPointer) DatumGetPointer(slot_getattr(slot, 2, &isnull)));
+		*itup = index_form_tuple(tupdesc, values, isnull);
+		(*itup)->t_tid = *((ItemPointer) DatumGetPointer(slot_getattr(slot, 2, &unused)));
 	}
 	else
 		*list = -1;
@@ -256,12 +262,14 @@ InsertTuples(Relation index, IvfflatBuildState * buildstate, ForkNumber forkNum)
 
 	TupleTableSlot *slot = MakeSingleTupleTableSlot(buildstate->sortdesc, &TTSOpsMinimalTuple);
 	TupleDesc	tupdesc = buildstate->tupdesc;
+	Datum	   *values = palloc(tupdesc->natts * sizeof(Datum));
+	bool	   *isnull = palloc(tupdesc->natts * sizeof(bool));
 
 	pgstat_progress_update_param(PROGRESS_CREATEIDX_SUBPHASE, PROGRESS_IVFFLAT_PHASE_LOAD);
 
 	pgstat_progress_update_param(PROGRESS_CREATEIDX_TUPLES_TOTAL, buildstate->indtuples);
 
-	GetNextTuple(buildstate->sortstate, tupdesc, slot, &itup, &list);
+	GetNextTuple(buildstate->sortstate, tupdesc, slot, values, isnull, &itup, &list);
 
 	for (int i = 0; i < buildstate->centers->length; i++)
 	{
@@ -297,7 +305,7 @@ InsertTuples(Relation index, IvfflatBuildState * buildstate, ForkNumber forkNum)
 
 			pgstat_progress_update_param(PROGRESS_CREATEIDX_TUPLES_DONE, ++inserted);
 
-			GetNextTuple(buildstate->sortstate, tupdesc, slot, &itup, &list);
+			GetNextTuple(buildstate->sortstate, tupdesc, slot, values, isnull, &itup, &list);
 		}
 
 		insertPage = BufferGetBlockNumber(buf);
@@ -307,6 +315,9 @@ InsertTuples(Relation index, IvfflatBuildState * buildstate, ForkNumber forkNum)
 		/* Set the start and insert pages */
 		IvfflatUpdateList(index, buildstate->listInfo[i], insertPage, InvalidBlockNumber, startPage, forkNum);
 	}
+
+	pfree(values);
+	pfree(isnull);
 }
 
 /*
@@ -357,10 +368,11 @@ InitBuildState(IvfflatBuildState * buildstate, Relation heap, Relation index, In
 				 errmsg("dimensions must be greater than one for this opclass")));
 
 	/* Create tuple description for sorting */
-	buildstate->sortdesc = CreateTemplateTupleDesc(3);
+	buildstate->sortdesc = CreateTemplateTupleDesc(2 + buildstate->tupdesc->natts);
 	TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 1, "list", INT4OID, -1, 0);
 	TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 2, "tid", TIDOID, -1, 0);
-	TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 3, "vector", buildstate->tupdesc->attrs[0].atttypid, -1, 0);
+	for (int i = 0; i < buildstate->tupdesc->natts; i++)
+		TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) (3 + i), NULL, buildstate->tupdesc->attrs[i].atttypid, -1, 0);
 
 	buildstate->slot = MakeSingleTupleTableSlot(buildstate->sortdesc, &TTSOpsVirtual);
 

src/ivfflat.c

@@ -18,12 +18,12 @@
 
 int			ivfflat_probes;
 int			ivfflat_iterative_search;
-int			ivfflat_max_probes;
+int			ivfflat_iterative_search_max_probes;
 static relopt_kind ivfflat_relopt_kind;
 
 static const struct config_enum_entry ivfflat_iterative_search_options[] = {
 	{"off", IVFFLAT_ITERATIVE_SEARCH_OFF, false},
-	{"relaxed_order", IVFFLAT_ITERATIVE_SEARCH_RELAXED, false},
+	{"on", IVFFLAT_ITERATIVE_SEARCH_RELAXED, false},
 	{NULL, 0, false}
 };
 
@@ -41,14 +41,13 @@ IvfflatInit(void)
 							"Valid range is 1..lists.", &ivfflat_probes,
 							IVFFLAT_DEFAULT_PROBES, IVFFLAT_MIN_LISTS, IVFFLAT_MAX_LISTS, PGC_USERSET, 0, NULL, NULL, NULL);
 
-	DefineCustomEnumVariable("ivfflat.iterative_search", "Sets the iterative search mode",
+	DefineCustomEnumVariable("ivfflat.iterative_search", "Sets whether to use iterative search",
 							 NULL, &ivfflat_iterative_search,
 							 IVFFLAT_ITERATIVE_SEARCH_OFF, ivfflat_iterative_search_options, PGC_USERSET, 0, NULL, NULL, NULL);
 
-	/* If this is less than probes, probes is used */
-	DefineCustomIntVariable("ivfflat.max_probes", "Sets the max number of probes for iterative search",
-							"-1 means no limit", &ivfflat_max_probes,
-							-1, -1, IVFFLAT_MAX_LISTS, PGC_USERSET, 0, NULL, NULL, NULL);
+	DefineCustomIntVariable("ivfflat.iterative_search_max_probes", "Sets the max number of probes for iterative search",
+							"Zero sets to the number of lists", &ivfflat_iterative_search_max_probes,
+							0, 0, IVFFLAT_MAX_LISTS, PGC_USERSET, 0, NULL, NULL, NULL);
 
 	MarkGUCPrefixReserved("ivfflat");
 }

src/ivfflat.h

@@ -81,13 +81,13 @@
 /* Variables */
 extern int	ivfflat_probes;
 extern int	ivfflat_iterative_search;
-extern int	ivfflat_max_probes;
+extern int	ivfflat_iterative_search_max_probes;
 
-typedef enum IvfflatIterativeSearchMode
+typedef enum IvfflatIterativeSearchType
 {
 	IVFFLAT_ITERATIVE_SEARCH_OFF,
 	IVFFLAT_ITERATIVE_SEARCH_RELAXED
-}			IvfflatIterativeSearchMode;
+}			IvfflatIterativeSearchType;
 
 typedef struct VectorArrayData
 {
@@ -260,7 +260,6 @@ typedef struct IvfflatScanOpaqueData
 	int			dimensions;
 	bool		first;
 	Datum		value;
-	MemoryContext tmpCtx;
 
 	/* Sorting */
 	Tuplesortstate *sortstate;
@@ -279,7 +278,7 @@ typedef struct IvfflatScanOpaqueData
 	pairingheap *listQueue;
 	BlockNumber *listPages;
 	int			listIndex;
-	IvfflatScanList *lists;
+	IvfflatScanList lists[FLEXIBLE_ARRAY_MEMBER];	/* must come last */
 }			IvfflatScanOpaqueData;
 
 typedef IvfflatScanOpaqueData * IvfflatScanOpaque;

src/ivfinsert.c

@@ -78,6 +78,8 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, R
 	BlockNumber insertPage = InvalidBlockNumber;
 	ListInfo	listInfo;
 	BlockNumber originalInsertPage;
+	TupleDesc	tupdesc = RelationGetDescr(index);
+	Datum	   *newValues = palloc(tupdesc->natts * sizeof(Datum));
 
 	/* Detoast once for all calls */
 	value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
@@ -102,8 +104,12 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, R
 	Assert(BlockNumberIsValid(insertPage));
 	originalInsertPage = insertPage;
 
+	newValues[0] = value;
+	for (int i = 1; i < tupdesc->natts; i++)
+		newValues[i] = values[i];
+
 	/* Form tuple */
-	itup = index_form_tuple(RelationGetDescr(index), &value, isnull);
+	itup = index_form_tuple(tupdesc, newValues, isnull);
 	itup->t_tid = *heap_tid;
 
 	/* Get tuple size */

src/ivfscan.c

@@ -10,7 +10,10 @@
 #include "miscadmin.h"
 #include "pgstat.h"
 #include "storage/bufmgr.h"
+
+#ifdef IVFFLAT_MEMORY
 #include "utils/memutils.h"
+#endif
 
 #define GetScanList(ptr) pairingheap_container(IvfflatScanList, ph_node, ptr)
 #define GetScanListConst(ptr) pairingheap_const_container(IvfflatScanList, ph_node, ptr)
@@ -218,13 +221,7 @@ GetScanValue(IndexScanDesc scan)
 
 		/* Normalize if needed */
 		if (so->normprocinfo != NULL)
-		{
-			MemoryContext oldCtx = MemoryContextSwitchTo(so->tmpCtx);
-
 			value = IvfflatNormValue(so->typeInfo, so->collation, value);
-
-			MemoryContextSwitchTo(oldCtx);
-		}
 	}
 
 	return value;
@@ -256,35 +253,26 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 	int			dimensions;
 	int			probes = ivfflat_probes;
 	int			maxProbes;
-	MemoryContext oldCtx;
 
 	scan = RelationGetIndexScan(index, nkeys, norderbys);
 
 	/* Get lists and dimensions from metapage */
 	IvfflatGetMetaPageInfo(index, &lists, &dimensions);
 
+	if (probes > lists)
+		probes = lists;
+
 	if (ivfflat_iterative_search != IVFFLAT_ITERATIVE_SEARCH_OFF)
 	{
-		maxProbes = ivfflat_max_probes;
-
-		if (maxProbes < 0)
+		if (ivfflat_iterative_search_max_probes == 0)
 			maxProbes = lists;
-		else if (maxProbes < probes)
-		{
-			/* TODO Show notice */
-			maxProbes = probes;
-		}
+		else
+			maxProbes = Min(ivfflat_iterative_search_max_probes, lists);
 	}
 	else
 		maxProbes = probes;
 
-	if (probes > lists)
-		probes = lists;
-
-	if (maxProbes > lists)
-		maxProbes = lists;
-
-	so = (IvfflatScanOpaque) palloc(sizeof(IvfflatScanOpaqueData));
+	so = (IvfflatScanOpaque) palloc(offsetof(IvfflatScanOpaqueData, lists) + maxProbes * sizeof(IvfflatScanList));
 	so->typeInfo = IvfflatGetTypeInfo(index);
 	so->first = true;
 	so->probes = probes;
@@ -296,12 +284,6 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 	so->normprocinfo = IvfflatOptionalProcInfo(index, IVFFLAT_NORM_PROC);
 	so->collation = index->rd_indcollation[0];
 
-	so->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
-									   "Ivfflat scan temporary context",
-									   ALLOCSET_DEFAULT_SIZES);
-
-	oldCtx = MemoryContextSwitchTo(so->tmpCtx);
-
 	/* Create tuple description for sorting */
 	so->tupdesc = CreateTemplateTupleDesc(2);
 	TupleDescInitEntry(so->tupdesc, (AttrNumber) 1, "distance", FLOAT8OID, -1, 0);
@@ -324,9 +306,6 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 	so->listQueue = pairingheap_allocate(CompareLists, scan);
 	so->listPages = palloc(maxProbes * sizeof(BlockNumber));
 	so->listIndex = 0;
-	so->lists = palloc(maxProbes * sizeof(IvfflatScanList));
-
-	MemoryContextSwitchTo(oldCtx);
 
 	scan->opaque = so;
 
@@ -389,6 +368,8 @@ ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
 		IvfflatBench("GetScanItems", GetScanItems(scan, value));
 		so->first = false;
 		so->value = value;
+
+		/* TODO clean up if we allocated a new value */
 	}
 
 	while (!tuplesort_gettupleslot(so->sortstate, true, false, so->mslot, NULL))
@@ -415,10 +396,13 @@ ivfflatendscan(IndexScanDesc scan)
 {
 	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
 
-	/* Free any temporary files */
+	pairingheap_free(so->listQueue);
+	pfree(so->listPages);
 	tuplesort_end(so->sortstate);
+	FreeAccessStrategy(so->bas);
+	FreeTupleDesc(so->tupdesc);
 
-	MemoryContextDelete(so->tmpCtx);
+	/* TODO Free vslot and mslot without freeing TupleDesc */
 
 	pfree(so);
 	scan->opaque = NULL;

test/expected/cast.out

@@ -140,34 +140,6 @@ SELECT '{1e-8,-1e-8}'::real[]::halfvec;
  [0,-0]
 (1 row)
 
-SELECT '[1,2,3]'::intvec::integer[];
-  int4   
----------
- {1,2,3}
-(1 row)
-
-SELECT '{1,2,3}'::integer[]::intvec;
- intvec  
----------
- [1,2,3]
-(1 row)
-
-SELECT '{1,2,3}'::integer[]::intvec(3);
- intvec  
----------
- [1,2,3]
-(1 row)
-
-SELECT '{1,2,3}'::integer[]::intvec(2);
-ERROR:  expected 2 dimensions, not 3
-SELECT '{127,-128}'::integer[]::intvec;
-   intvec   
-------------
- [127,-128]
-(1 row)
-
-SELECT '{128,-129}'::integer[]::intvec;
-ERROR:  value "128" is out of range for type intvec
 SELECT '[0,1.5,0,3.5,0]'::vector::sparsevec;
     sparsevec    
 -----------------

test/expected/copy.out

@@ -30,23 +30,6 @@ SELECT * FROM t2 ORDER BY val;
  
 (4 rows)
 
-DROP TABLE t;
-DROP TABLE t2;
--- intvec
-CREATE TABLE t (val intvec(3));
-INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
-CREATE TABLE t2 (val intvec(3));
-\copy t TO 'results/intvec.bin' WITH (FORMAT binary)
-\copy t2 FROM 'results/intvec.bin' WITH (FORMAT binary)
-SELECT * FROM t2 ORDER BY val;
-   val   
----------
- [0,0,0]
- [1,1,1]
- [1,2,3]
- 
-(4 rows)
-
 DROP TABLE t;
 DROP TABLE t2;
 -- sparsevec

test/expected/hnsw_intvec.out

@@ -1,102 +0,0 @@
-SET enable_seqscan = off;
--- L2
-CREATE TABLE t (val intvec(3));
-INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
-CREATE INDEX ON t USING hnsw (val intvec_l2_ops);
-INSERT INTO t (val) VALUES ('[1,2,4]');
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
-   val   
----------
- [1,2,3]
- [1,2,4]
- [1,1,1]
- [0,0,0]
-(4 rows)
-
-SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <-> (SELECT NULL::intvec)) t2;
- count 
--------
-     4
-(1 row)
-
-SELECT COUNT(*) FROM t;
- count 
--------
-     5
-(1 row)
-
-TRUNCATE t;
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
- val 
------
-(0 rows)
-
-DROP TABLE t;
--- inner product
-CREATE TABLE t (val intvec(3));
-INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
-CREATE INDEX ON t USING hnsw (val intvec_ip_ops);
-INSERT INTO t (val) VALUES ('[1,2,4]');
-SELECT * FROM t ORDER BY val <#> '[3,3,3]';
-   val   
----------
- [1,2,4]
- [1,2,3]
- [1,1,1]
- [0,0,0]
-(4 rows)
-
-SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <#> (SELECT NULL::intvec)) t2;
- count 
--------
-     4
-(1 row)
-
-DROP TABLE t;
--- cosine
-CREATE TABLE t (val intvec(3));
-INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
-CREATE INDEX ON t USING hnsw (val intvec_cosine_ops);
-INSERT INTO t (val) VALUES ('[1,2,4]');
-SELECT * FROM t ORDER BY val <=> '[3,3,3]';
-   val   
----------
- [1,1,1]
- [1,2,3]
- [1,2,4]
-(3 rows)
-
-SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> '[0,0,0]') t2;
- count 
--------
-     3
-(1 row)
-
-SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> (SELECT NULL::intvec)) t2;
- count 
--------
-     3
-(1 row)
-
-DROP TABLE t;
--- L1
-CREATE TABLE t (val intvec(3));
-INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
-CREATE INDEX ON t USING hnsw (val intvec_l1_ops);
-INSERT INTO t (val) VALUES ('[1,2,4]');
-SELECT * FROM t ORDER BY val <+> '[3,3,3]';
-   val   
----------
- [1,2,3]
- [1,2,4]
- [1,1,1]
- [0,0,0]
-(4 rows)
-
-SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <+> (SELECT NULL::intvec)) t2;
- count 
--------
-     4
-(1 row)
-
-DROP TABLE t;

test/expected/hnsw_vector.out

@@ -99,32 +99,6 @@ SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <+> (SELECT NULL::vector)) t2
      4
 (1 row)
 
-DROP TABLE t;
--- iterative
-CREATE TABLE t (val vector(3));
-INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
-CREATE INDEX ON t USING hnsw (val vector_l2_ops);
-SET hnsw.iterative_search = strict_order;
-SET hnsw.ef_search = 1;
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
-   val   
----------
- [1,2,3]
- [1,1,1]
- [0,0,0]
-(3 rows)
-
-SET hnsw.iterative_search = relaxed_order;
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
-   val   
----------
- [1,2,3]
- [1,1,1]
- [0,0,0]
-(3 rows)
-
-RESET hnsw.iterative_search;
-RESET hnsw.ef_search;
 DROP TABLE t;
 -- unlogged
 CREATE UNLOGGED TABLE t (val vector(3));
@@ -165,21 +139,4 @@ SET hnsw.ef_search = 0;
 ERROR:  0 is outside the valid range for parameter "hnsw.ef_search" (1 .. 1000)
 SET hnsw.ef_search = 1001;
 ERROR:  1001 is outside the valid range for parameter "hnsw.ef_search" (1 .. 1000)
-SHOW hnsw.iterative_search;
- hnsw.iterative_search 
------------------------
- off
-(1 row)
-
-SET hnsw.iterative_search = on;
-ERROR:  invalid value for parameter "hnsw.iterative_search": "on"
-HINT:  Available values: off, relaxed_order, strict_order.
-SHOW hnsw.max_search_tuples;
- hnsw.max_search_tuples 
-------------------------
- -1
-(1 row)
-
-SET hnsw.max_search_tuples = -2;
-ERROR:  -2 is outside the valid range for parameter "hnsw.max_search_tuples" (-1 .. 2147483647)
 DROP TABLE t;

test/expected/intvec.out

@@ -1,328 +0,0 @@
-SELECT '[1,2,3]'::intvec;
- intvec  
----------
- [1,2,3]
-(1 row)
-
-SELECT '[-1,-2,-3]'::intvec;
-   intvec   
-------------
- [-1,-2,-3]
-(1 row)
-
-SELECT ' [ 1,  2 ,    3  ] '::intvec;
- intvec  
----------
- [1,2,3]
-(1 row)
-
-SELECT '[1.23456]'::intvec;
-ERROR:  invalid input syntax for type intvec: "[1.23456]"
-LINE 1: SELECT '[1.23456]'::intvec;
-               ^
-SELECT '[hello,1]'::intvec;
-ERROR:  invalid input syntax for type intvec: "[hello,1]"
-LINE 1: SELECT '[hello,1]'::intvec;
-               ^
-SELECT '[127,-128]'::intvec;
-   intvec   
-------------
- [127,-128]
-(1 row)
-
-SELECT '[128,-129]'::intvec;
-ERROR:  "128" is out of range for type intvec
-LINE 1: SELECT '[128,-129]'::intvec;
-               ^
-SELECT '[1,2,3'::intvec;
-ERROR:  invalid input syntax for type intvec: "[1,2,3"
-LINE 1: SELECT '[1,2,3'::intvec;
-               ^
-SELECT '[1,2,3]9'::intvec;
-ERROR:  invalid input syntax for type intvec: "[1,2,3]9"
-LINE 1: SELECT '[1,2,3]9'::intvec;
-               ^
-DETAIL:  Junk after closing right brace.
-SELECT '1,2,3'::intvec;
-ERROR:  invalid input syntax for type intvec: "1,2,3"
-LINE 1: SELECT '1,2,3'::intvec;
-               ^
-DETAIL:  Vector contents must start with "[".
-SELECT ''::intvec;
-ERROR:  invalid input syntax for type intvec: ""
-LINE 1: SELECT ''::intvec;
-               ^
-DETAIL:  Vector contents must start with "[".
-SELECT '['::intvec;
-ERROR:  invalid input syntax for type intvec: "["
-LINE 1: SELECT '['::intvec;
-               ^
-SELECT '[,'::intvec;
-ERROR:  invalid input syntax for type intvec: "[,"
-LINE 1: SELECT '[,'::intvec;
-               ^
-SELECT '[]'::intvec;
-ERROR:  intvec must have at least 1 dimension
-LINE 1: SELECT '[]'::intvec;
-               ^
-SELECT '[1,]'::intvec;
-ERROR:  invalid input syntax for type intvec: "[1,]"
-LINE 1: SELECT '[1,]'::intvec;
-               ^
-SELECT '[1a]'::intvec;
-ERROR:  invalid input syntax for type intvec: "[1a]"
-LINE 1: SELECT '[1a]'::intvec;
-               ^
-SELECT '[1,,3]'::intvec;
-ERROR:  invalid input syntax for type intvec: "[1,,3]"
-LINE 1: SELECT '[1,,3]'::intvec;
-               ^
-SELECT '[1, ,3]'::intvec;
-ERROR:  invalid input syntax for type intvec: "[1, ,3]"
-LINE 1: SELECT '[1, ,3]'::intvec;
-               ^
-SELECT '[1,2,3]'::intvec(3);
- intvec  
----------
- [1,2,3]
-(1 row)
-
-SELECT '[1,2,3]'::intvec(2);
-ERROR:  expected 2 dimensions, not 3
-SELECT '[1,2,3]'::intvec(3, 2);
-ERROR:  invalid type modifier
-LINE 1: SELECT '[1,2,3]'::intvec(3, 2);
-                          ^
-SELECT '[1,2,3]'::intvec('a');
-ERROR:  invalid input syntax for type integer: "a"
-LINE 1: SELECT '[1,2,3]'::intvec('a');
-                          ^
-SELECT '[1,2,3]'::intvec(0);
-ERROR:  dimensions for type intvec must be at least 1
-LINE 1: SELECT '[1,2,3]'::intvec(0);
-                          ^
-SELECT '[1,2,3]'::intvec(16001);
-ERROR:  dimensions for type intvec cannot exceed 16000
-LINE 1: SELECT '[1,2,3]'::intvec(16001);
-                          ^
-SELECT unnest('{"[1,2,3]", "[4,5,6]"}'::intvec[]);
- unnest  
----------
- [1,2,3]
- [4,5,6]
-(2 rows)
-
-SELECT '{"[1,2,3]"}'::intvec(2)[];
-ERROR:  expected 2 dimensions, not 3
-SELECT '[1,2,3]'::intvec < '[1,2,3]';
- ?column? 
-----------
- f
-(1 row)
-
-SELECT '[1,2,3]'::intvec < '[1,2]';
- ?column? 
-----------
- f
-(1 row)
-
-SELECT '[1,2,3]'::intvec <= '[1,2,3]';
- ?column? 
-----------
- t
-(1 row)
-
-SELECT '[1,2,3]'::intvec <= '[1,2]';
- ?column? 
-----------
- f
-(1 row)
-
-SELECT '[1,2,3]'::intvec = '[1,2,3]';
- ?column? 
-----------
- t
-(1 row)
-
-SELECT '[1,2,3]'::intvec = '[1,2]';
- ?column? 
-----------
- f
-(1 row)
-
-SELECT '[1,2,3]'::intvec != '[1,2,3]';
- ?column? 
-----------
- f
-(1 row)
-
-SELECT '[1,2,3]'::intvec != '[1,2]';
- ?column? 
-----------
- t
-(1 row)
-
-SELECT '[1,2,3]'::intvec >= '[1,2,3]';
- ?column? 
-----------
- t
-(1 row)
-
-SELECT '[1,2,3]'::intvec >= '[1,2]';
- ?column? 
-----------
- t
-(1 row)
-
-SELECT '[1,2,3]'::intvec > '[1,2,3]';
- ?column? 
-----------
- f
-(1 row)
-
-SELECT '[1,2,3]'::intvec > '[1,2]';
- ?column? 
-----------
- t
-(1 row)
-
-SELECT intvec_cmp('[1,2,3]', '[1,2,3]');
- intvec_cmp 
-------------
-          0
-(1 row)
-
-SELECT intvec_cmp('[1,2,3]', '[0,0,0]');
- intvec_cmp 
-------------
-          1
-(1 row)
-
-SELECT intvec_cmp('[0,0,0]', '[1,2,3]');
- intvec_cmp 
-------------
-         -1
-(1 row)
-
-SELECT intvec_cmp('[1,2]', '[1,2,3]');
- intvec_cmp 
-------------
-         -1
-(1 row)
-
-SELECT intvec_cmp('[1,2,3]', '[1,2]');
- intvec_cmp 
-------------
-          1
-(1 row)
-
-SELECT intvec_cmp('[1,2]', '[2,3,4]');
- intvec_cmp 
-------------
-         -1
-(1 row)
-
-SELECT intvec_cmp('[2,3]', '[1,2,3]');
- intvec_cmp 
-------------
-          1
-(1 row)
-
-SELECT vector_dims('[1,2,3]'::intvec);
- vector_dims 
--------------
-           3
-(1 row)
-
-SELECT l2_distance('[0,0]'::intvec, '[3,4]');
- l2_distance 
--------------
-           5
-(1 row)
-
-SELECT l2_distance('[0,0]'::intvec, '[0,1]');
- l2_distance 
--------------
-           1
-(1 row)
-
-SELECT l2_distance('[1,2]'::intvec, '[3]');
-ERROR:  different intvec dimensions 2 and 1
-SELECT '[0,0]'::intvec <-> '[3,4]';
- ?column? 
-----------
-        5
-(1 row)
-
-SELECT inner_product('[1,2]'::intvec, '[3,4]');
- inner_product 
----------------
-            11
-(1 row)
-
-SELECT inner_product('[1,2]'::intvec, '[3]');
-ERROR:  different intvec dimensions 2 and 1
-SELECT inner_product('[127]'::intvec, '[127]');
- inner_product 
----------------
-         16129
-(1 row)
-
-SELECT '[1,2]'::intvec <#> '[3,4]';
- ?column? 
-----------
-      -11
-(1 row)
-
-SELECT cosine_distance('[1,2]'::intvec, '[2,4]');
- cosine_distance 
------------------
-               0
-(1 row)
-
-SELECT cosine_distance('[1,2]'::intvec, '[0,0]');
- cosine_distance 
------------------
-             NaN
-(1 row)
-
-SELECT cosine_distance('[1,1]'::intvec, '[1,1]');
- cosine_distance 
------------------
-               0
-(1 row)
-
-SELECT cosine_distance('[1,0]'::intvec, '[0,2]');
- cosine_distance 
------------------
-               1
-(1 row)
-
-SELECT cosine_distance('[1,1]'::intvec, '[-1,-1]');
- cosine_distance 
------------------
-               2
-(1 row)
-
-SELECT cosine_distance('[1,2]'::intvec, '[3]');
-ERROR:  different intvec dimensions 2 and 1
-SELECT '[1,2]'::intvec <=> '[2,4]';
- ?column? 
-----------
-        0
-(1 row)
-
-SELECT l1_distance('[0,0]'::intvec, '[3,4]');
- l1_distance 
--------------
-           7
-(1 row)
-
-SELECT l1_distance('[0,0]'::intvec, '[0,1]');
- l1_distance 
--------------
-           1
-(1 row)
-
-SELECT l1_distance('[1,2]'::intvec, '[3]');
-ERROR:  different intvec dimensions 2 and 1

test/expected/ivfflat_vector.out

@@ -81,44 +81,6 @@ SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> (SELECT NULL::vector)) t2
      3
 (1 row)
 
-DROP TABLE t;
--- iterative
-CREATE TABLE t (val vector(3));
-INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
-CREATE INDEX ON t USING ivfflat (val vector_l2_ops) WITH (lists = 3);
-SET ivfflat.iterative_search = relaxed_order;
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
-   val   
----------
- [1,2,3]
- [1,1,1]
- [0,0,0]
-(3 rows)
-
-SET ivfflat.max_probes = 0;
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
-   val   
----------
- [1,2,3]
-(1 row)
-
-SET ivfflat.max_probes = 1;
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
-   val   
----------
- [1,2,3]
-(1 row)
-
-SET ivfflat.max_probes = 2;
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
-   val   
----------
- [1,2,3]
- [1,1,1]
-(2 rows)
-
-RESET ivfflat.iterative_search;
-RESET ivfflat.max_probes;
 DROP TABLE t;
 -- unlogged
 CREATE UNLOGGED TABLE t (val vector(3));
@@ -147,27 +109,4 @@ SHOW ivfflat.probes;
  1
 (1 row)
 
-SET ivfflat.probes = 0;
-ERROR:  0 is outside the valid range for parameter "ivfflat.probes" (1 .. 32768)
-SET ivfflat.probes = 32769;
-ERROR:  32769 is outside the valid range for parameter "ivfflat.probes" (1 .. 32768)
-SHOW ivfflat.iterative_search;
- ivfflat.iterative_search 
---------------------------
- off
-(1 row)
-
-SET ivfflat.iterative_search = on;
-ERROR:  invalid value for parameter "ivfflat.iterative_search": "on"
-HINT:  Available values: off, relaxed_order.
-SHOW ivfflat.max_probes;
- ivfflat.max_probes 
---------------------
- -1
-(1 row)
-
-SET ivfflat.max_probes = -2;
-ERROR:  -2 is outside the valid range for parameter "ivfflat.max_probes" (-1 .. 32768)
-SET ivfflat.max_probes = 32769;
-ERROR:  32769 is outside the valid range for parameter "ivfflat.max_probes" (-1 .. 32768)
 DROP TABLE t;

test/sql/cast.sql

@@ -38,14 +38,6 @@ SELECT '{1,2,3}'::real[]::halfvec(2);
 SELECT '{65520,-65520}'::real[]::halfvec;
 SELECT '{1e-8,-1e-8}'::real[]::halfvec;
 
-SELECT '[1,2,3]'::intvec::integer[];
-
-SELECT '{1,2,3}'::integer[]::intvec;
-SELECT '{1,2,3}'::integer[]::intvec(3);
-SELECT '{1,2,3}'::integer[]::intvec(2);
-SELECT '{127,-128}'::integer[]::intvec;
-SELECT '{128,-129}'::integer[]::intvec;
-
 SELECT '[0,1.5,0,3.5,0]'::vector::sparsevec;
 SELECT '[0,1.5,0,3.5,0]'::vector::sparsevec(5);
 SELECT '[0,1.5,0,3.5,0]'::vector::sparsevec(4);

test/sql/copy.sql

@@ -28,21 +28,6 @@ SELECT * FROM t2 ORDER BY val;
 DROP TABLE t;
 DROP TABLE t2;
 
--- intvec
-
-CREATE TABLE t (val intvec(3));
-INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
-
-CREATE TABLE t2 (val intvec(3));
-
-\copy t TO 'results/intvec.bin' WITH (FORMAT binary)
-\copy t2 FROM 'results/intvec.bin' WITH (FORMAT binary)
-
-SELECT * FROM t2 ORDER BY val;
-
-DROP TABLE t;
-DROP TABLE t2;
-
 -- sparsevec
 
 CREATE TABLE t (val sparsevec(3));

test/sql/hnsw_intvec.sql

@@ -1,58 +0,0 @@
-SET enable_seqscan = off;
-
--- L2
-
-CREATE TABLE t (val intvec(3));
-INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
-CREATE INDEX ON t USING hnsw (val intvec_l2_ops);
-
-INSERT INTO t (val) VALUES ('[1,2,4]');
-
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
-SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <-> (SELECT NULL::intvec)) t2;
-SELECT COUNT(*) FROM t;
-
-TRUNCATE t;
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
-
-DROP TABLE t;
-
--- inner product
-
-CREATE TABLE t (val intvec(3));
-INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
-CREATE INDEX ON t USING hnsw (val intvec_ip_ops);
-
-INSERT INTO t (val) VALUES ('[1,2,4]');
-
-SELECT * FROM t ORDER BY val <#> '[3,3,3]';
-SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <#> (SELECT NULL::intvec)) t2;
-
-DROP TABLE t;
-
--- cosine
-
-CREATE TABLE t (val intvec(3));
-INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
-CREATE INDEX ON t USING hnsw (val intvec_cosine_ops);
-
-INSERT INTO t (val) VALUES ('[1,2,4]');
-
-SELECT * FROM t ORDER BY val <=> '[3,3,3]';
-SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> '[0,0,0]') t2;
-SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> (SELECT NULL::intvec)) t2;
-
-DROP TABLE t;
-
--- L1
-
-CREATE TABLE t (val intvec(3));
-INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
-CREATE INDEX ON t USING hnsw (val intvec_l1_ops);
-
-INSERT INTO t (val) VALUES ('[1,2,4]');
-
-SELECT * FROM t ORDER BY val <+> '[3,3,3]';
-SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <+> (SELECT NULL::intvec)) t2;
-
-DROP TABLE t;

test/sql/hnsw_vector.sql

@@ -57,23 +57,6 @@ SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <+> (SELECT NULL::vector)) t2
 
 DROP TABLE t;
 
--- iterative
-
-CREATE TABLE t (val vector(3));
-INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
-CREATE INDEX ON t USING hnsw (val vector_l2_ops);
-
-SET hnsw.iterative_search = strict_order;
-SET hnsw.ef_search = 1;
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
-
-SET hnsw.iterative_search = relaxed_order;
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
-
-RESET hnsw.iterative_search;
-RESET hnsw.ef_search;
-DROP TABLE t;
-
 -- unlogged
 
 CREATE UNLOGGED TABLE t (val vector(3));
@@ -98,12 +81,4 @@ SHOW hnsw.ef_search;
 SET hnsw.ef_search = 0;
 SET hnsw.ef_search = 1001;
 
-SHOW hnsw.iterative_search;
-
-SET hnsw.iterative_search = on;
-
-SHOW hnsw.max_search_tuples;
-
-SET hnsw.max_search_tuples = -2;
-
 DROP TABLE t;

test/sql/intvec.sql

@@ -1,73 +0,0 @@
-SELECT '[1,2,3]'::intvec;
-SELECT '[-1,-2,-3]'::intvec;
-SELECT ' [ 1,  2 ,    3  ] '::intvec;
-SELECT '[1.23456]'::intvec;
-SELECT '[hello,1]'::intvec;
-SELECT '[127,-128]'::intvec;
-SELECT '[128,-129]'::intvec;
-SELECT '[1,2,3'::intvec;
-SELECT '[1,2,3]9'::intvec;
-SELECT '1,2,3'::intvec;
-SELECT ''::intvec;
-SELECT '['::intvec;
-SELECT '[,'::intvec;
-SELECT '[]'::intvec;
-SELECT '[1,]'::intvec;
-SELECT '[1a]'::intvec;
-SELECT '[1,,3]'::intvec;
-SELECT '[1, ,3]'::intvec;
-
-SELECT '[1,2,3]'::intvec(3);
-SELECT '[1,2,3]'::intvec(2);
-SELECT '[1,2,3]'::intvec(3, 2);
-SELECT '[1,2,3]'::intvec('a');
-SELECT '[1,2,3]'::intvec(0);
-SELECT '[1,2,3]'::intvec(16001);
-
-SELECT unnest('{"[1,2,3]", "[4,5,6]"}'::intvec[]);
-SELECT '{"[1,2,3]"}'::intvec(2)[];
-
-SELECT '[1,2,3]'::intvec < '[1,2,3]';
-SELECT '[1,2,3]'::intvec < '[1,2]';
-SELECT '[1,2,3]'::intvec <= '[1,2,3]';
-SELECT '[1,2,3]'::intvec <= '[1,2]';
-SELECT '[1,2,3]'::intvec = '[1,2,3]';
-SELECT '[1,2,3]'::intvec = '[1,2]';
-SELECT '[1,2,3]'::intvec != '[1,2,3]';
-SELECT '[1,2,3]'::intvec != '[1,2]';
-SELECT '[1,2,3]'::intvec >= '[1,2,3]';
-SELECT '[1,2,3]'::intvec >= '[1,2]';
-SELECT '[1,2,3]'::intvec > '[1,2,3]';
-SELECT '[1,2,3]'::intvec > '[1,2]';
-
-SELECT intvec_cmp('[1,2,3]', '[1,2,3]');
-SELECT intvec_cmp('[1,2,3]', '[0,0,0]');
-SELECT intvec_cmp('[0,0,0]', '[1,2,3]');
-SELECT intvec_cmp('[1,2]', '[1,2,3]');
-SELECT intvec_cmp('[1,2,3]', '[1,2]');
-SELECT intvec_cmp('[1,2]', '[2,3,4]');
-SELECT intvec_cmp('[2,3]', '[1,2,3]');
-
-SELECT vector_dims('[1,2,3]'::intvec);
-
-SELECT l2_distance('[0,0]'::intvec, '[3,4]');
-SELECT l2_distance('[0,0]'::intvec, '[0,1]');
-SELECT l2_distance('[1,2]'::intvec, '[3]');
-SELECT '[0,0]'::intvec <-> '[3,4]';
-
-SELECT inner_product('[1,2]'::intvec, '[3,4]');
-SELECT inner_product('[1,2]'::intvec, '[3]');
-SELECT inner_product('[127]'::intvec, '[127]');
-SELECT '[1,2]'::intvec <#> '[3,4]';
-
-SELECT cosine_distance('[1,2]'::intvec, '[2,4]');
-SELECT cosine_distance('[1,2]'::intvec, '[0,0]');
-SELECT cosine_distance('[1,1]'::intvec, '[1,1]');
-SELECT cosine_distance('[1,0]'::intvec, '[0,2]');
-SELECT cosine_distance('[1,1]'::intvec, '[-1,-1]');
-SELECT cosine_distance('[1,2]'::intvec, '[3]');
-SELECT '[1,2]'::intvec <=> '[2,4]';
-
-SELECT l1_distance('[0,0]'::intvec, '[3,4]');
-SELECT l1_distance('[0,0]'::intvec, '[0,1]');
-SELECT l1_distance('[1,2]'::intvec, '[3]');

test/sql/ivfflat_vector.sql

@@ -44,28 +44,6 @@ SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> (SELECT NULL::vector)) t2
 
 DROP TABLE t;
 
--- iterative
-
-CREATE TABLE t (val vector(3));
-INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
-CREATE INDEX ON t USING ivfflat (val vector_l2_ops) WITH (lists = 3);
-
-SET ivfflat.iterative_search = relaxed_order;
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
-
-SET ivfflat.max_probes = 0;
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
-
-SET ivfflat.max_probes = 1;
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
-
-SET ivfflat.max_probes = 2;
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
-
-RESET ivfflat.iterative_search;
-RESET ivfflat.max_probes;
-DROP TABLE t;
-
 -- unlogged
 
 CREATE UNLOGGED TABLE t (val vector(3));
@@ -84,16 +62,4 @@ CREATE INDEX ON t USING ivfflat (val vector_l2_ops) WITH (lists = 32769);
 
 SHOW ivfflat.probes;
 
-SET ivfflat.probes = 0;
-SET ivfflat.probes = 32769;
-
-SHOW ivfflat.iterative_search;
-
-SET ivfflat.iterative_search = on;
-
-SHOW ivfflat.max_probes;
-
-SET ivfflat.max_probes = -2;
-SET ivfflat.max_probes = 32769;
-
 DROP TABLE t;

test/t/033_comparison.pl

@@ -40,10 +40,6 @@ for (1 .. 50)
 	$actual = $node->safe_psql("postgres", "SELECT halfvec_cmp(v::halfvec, '$query'::real[]::halfvec) FROM tst");
 	is($expected, $actual);
 
-	# Test intvec
-	$actual = $node->safe_psql("postgres", "SELECT intvec_cmp(v::integer[]::intvec, '$query'::integer[]::intvec) FROM tst");
-	is($expected, $actual);
-
 	# Test sparsevec
 	$actual = $node->safe_psql("postgres", "SELECT sparsevec_cmp(v::vector::sparsevec, '$query'::real[]::vector::sparsevec) FROM tst");
 	is($expected, $actual);

test/t/034_distance_functions.pl

@@ -45,10 +45,6 @@ for my $function (@functions)
 		my $actual = $node->safe_psql("postgres", "SELECT $function(v::halfvec, '$query'::vector::halfvec) FROM tst");
 		is($expected, $actual, "halfvec $function");
 
-		# Test intvec
-		$actual = $node->safe_psql("postgres", "SELECT $function(v::real[]::integer[]::intvec, '$query'::vector::real[]::integer[]::intvec) FROM tst");
-		is($expected, $actual, "intvec $function");
-
 		# Test sparsevec
 		$actual = $node->safe_psql("postgres", "SELECT $function(v::sparsevec, '$query'::vector::sparsevec) FROM tst");
 		is($expected, $actual, "sparsevec $function");

test/t/037_inputs.pl

@@ -12,8 +12,8 @@ $node->start;
 # Create extension
 $node->safe_psql("postgres", "CREATE EXTENSION vector;");
 
-my @types = ("vector", "halfvec", "intvec", "sparsevec");
-my @inputs = ("[1.23,4.56,7.89]", "[1.23,4.56,7.89]", "[1,2,3]", "{1:1.23,2:4.56,3:7.89}/3");
+my @types = ("vector", "halfvec", "sparsevec");
+my @inputs = ("[1.23,4.56,7.89]", "[1.23,4.56,7.89]", "{1:1.23,2:4.56,3:7.89}/3");
 my @subs = (" ", " ", ",", ":", "-", "1", "9", "\0", "2147483648", "-2147483649");
 
 for my $i (0 .. $#types)

test/t/041_ivfflat_iterative_search.pl

@@ -23,7 +23,7 @@ $node->safe_psql("postgres", "CREATE INDEX ON tst USING ivfflat (v vector_l2_ops
 my $count = $node->safe_psql("postgres", qq(
 	SET enable_seqscan = off;
 	SET ivfflat.probes = 10;
-	SET ivfflat.iterative_search = relaxed_order;
+	SET ivfflat.iterative_search = on;
 	SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;
 ));
 is($count, 10);
@@ -39,8 +39,8 @@ foreach ((30, 50, 70))
 		$count = $node->safe_psql("postgres", qq(
 			SET enable_seqscan = off;
 			SET ivfflat.probes = 10;
-			SET ivfflat.iterative_search = relaxed_order;
-			SET ivfflat.max_probes = $max_probes;
+			SET ivfflat.iterative_search = on;
+			SET ivfflat.iterative_search_max_probes = $max_probes;
 			SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst WHERE i = $i) LIMIT 11) t;
 		));
 		$sum += $count;

test/t/042_ivfflat_iterative_search_recall.pl

@@ -19,7 +19,7 @@ sub test_recall
 	my $explain = $node->safe_psql("postgres", qq(
 		SET enable_seqscan = off;
 		SET ivfflat.probes = $probes;
-		SET ivfflat.iterative_search = relaxed_order;
+		SET ivfflat.iterative_search = on;
 		EXPLAIN ANALYZE SELECT i FROM tst WHERE i % $c = 0 ORDER BY v $operator '$queries[0]' LIMIT $limit;
 	));
 	like($explain, qr/Index Scan using idx on tst/);
@@ -29,7 +29,7 @@ sub test_recall
 		my $actual = $node->safe_psql("postgres", qq(
 			SET enable_seqscan = off;
 			SET ivfflat.probes = $probes;
-			SET ivfflat.iterative_search = relaxed_order;
+			SET ivfflat.iterative_search = on;
 			SELECT i FROM tst WHERE i % $c = 0 ORDER BY v $operator '$queries[$i]' LIMIT $limit;
 		));
 		my @actual_ids = split("\n", $actual);
@@ -48,7 +48,7 @@ sub test_recall
 		$total += $limit;
 	}
 
-	cmp_ok($correct / $total, ">=", $min, "$operator $c");
+	cmp_ok($correct / $total, ">=", $min, $operator);
 }
 
 # Initialize node
@@ -103,7 +103,7 @@ for my $i (0 .. $#operators)
 
 		if ($c == 100)
 		{
-			test_recall($c, 1, 0.57, $operator);
+			test_recall($c, 1, 0.58, $operator);
 			test_recall($c, 10, 0.98, $operator);
 		}
 		else

test/t/043_hnsw_iterative_search.pl

@@ -26,7 +26,7 @@ $node->safe_psql("postgres", qq(
 
 my $count = $node->safe_psql("postgres", qq(
 	SET enable_seqscan = off;
-	SET hnsw.iterative_search = relaxed_order;
+	SET hnsw.iterative_search = on;
 	SET work_mem = '8MB';
 	SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;
 ));
@@ -42,8 +42,8 @@ foreach ((30000, 50000, 70000))
 	{
 		$count = $node->safe_psql("postgres", qq(
 			SET enable_seqscan = off;
-			SET hnsw.iterative_search = relaxed_order;
-			SET hnsw.max_search_tuples = $max_tuples;
+			SET hnsw.iterative_search = on;
+			SET hnsw.iterative_search_max_tuples = $max_tuples;
 			SET work_mem = '8MB';
 			SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst WHERE i = $i) LIMIT 11) t;
 		));
@@ -57,7 +57,7 @@ foreach ((30000, 50000, 70000))
 
 my ($ret, $stdout, $stderr) = $node->psql("postgres", qq(
 	SET enable_seqscan = off;
-	SET hnsw.iterative_search = relaxed_order;
+	SET hnsw.iterative_search = on;
 	SET client_min_messages = debug1;
 	SET work_mem = '2MB';
 	SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;

test/t/044_hnsw_iterative_search_recall.pl

@@ -10,18 +10,18 @@ my @expected;
 my $limit = 20;
 my $dim = 3;
 my $array_sql = join(",", ('random()') x $dim);
-my @cs = (50, 500);
+my @cs = (100, 1000);
 
 sub test_recall
 {
-	my ($c, $ef_search, $min, $operator, $mode) = @_;
+	my ($c, $ef_search, $min, $operator) = @_;
 	my $correct = 0;
 	my $total = 0;
 
 	my $explain = $node->safe_psql("postgres", qq(
 		SET enable_seqscan = off;
 		SET hnsw.ef_search = $ef_search;
-		SET hnsw.iterative_search = $mode;
+		SET hnsw.iterative_search = on;
 		EXPLAIN ANALYZE SELECT i FROM tst WHERE i % $c = 0 ORDER BY v $operator '$queries[0]' LIMIT $limit;
 	));
 	like($explain, qr/Index Scan using idx on tst/);
@@ -31,7 +31,7 @@ sub test_recall
 		my $actual = $node->safe_psql("postgres", qq(
 			SET enable_seqscan = off;
 			SET hnsw.ef_search = $ef_search;
-			SET hnsw.iterative_search = $mode;
+			SET hnsw.iterative_search = on;
 			SELECT i FROM tst WHERE i % $c = 0 ORDER BY v $operator '$queries[$i]' LIMIT $limit;
 		));
 		my @actual_ids = split("\n", $actual);
@@ -50,7 +50,7 @@ sub test_recall
 		$total += $limit;
 	}
 
-	cmp_ok($correct / $total, ">=", $min, "$operator $mode $c");
+	cmp_ok($correct / $total, ">=", $min, $operator);
 }
 
 # Initialize node
@@ -62,7 +62,7 @@ $node->start;
 $node->safe_psql("postgres", "CREATE EXTENSION vector;");
 $node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim));");
 $node->safe_psql("postgres",
-	"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 50000) i;"
+	"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
 );
 
 # Generate queries
@@ -108,8 +108,21 @@ for my $i (0 .. $#operators)
 			push(@expected, $res);
 		}
 
-		test_recall($c, 40, 0.99, $operator, "strict_order");
-		test_recall($c, 40, 0.99, $operator, "relaxed_order");
+		if ($c == 100)
+		{
+			test_recall($c, 40, 0.99, $operator);
+		}
+		else
+		{
+			if ($operator eq "<->")
+			{
+				test_recall($c, 40, 0.99, $operator);
+			}
+			else
+			{
+				test_recall($c, 40, 0.99, $operator);
+			}
+		}
 	}
 
 	$node->safe_psql("postgres", "DROP INDEX idx;");

test/t/045_hnsw_hqann.pl

@@ -0,0 +1,113 @@
+use strict;
+use warnings FATAL => 'all';
+use PostgreSQL::Test::Cluster;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+my $node;
+my @queries = ();
+my @cs = ();
+my @expected;
+my $limit = 20;
+my $dim = 3;
+my $array_sql = join(",", ('random()') x $dim);
+my $nc = 1000;
+
+sub test_recall
+{
+	my ($min, $operator) = @_;
+	my $correct = 0;
+	my $total = 0;
+
+	my $explain = $node->safe_psql("postgres", qq(
+		SET enable_seqscan = off;
+		EXPLAIN ANALYZE SELECT i FROM tst WHERE c = $cs[0] ORDER BY v $operator '$queries[0]' LIMIT $limit;
+	));
+	like($explain, qr/Index Cond/);
+
+	for my $i (0 .. $#queries)
+	{
+		my $actual = $node->safe_psql("postgres", qq(
+			SET enable_seqscan = off;
+			SELECT i FROM tst WHERE c = $cs[$i] ORDER BY v $operator '$queries[$i]' LIMIT $limit;
+		));
+		my @actual_ids = split("\n", $actual);
+		my %actual_set = map { $_ => 1 } @actual_ids;
+
+		is(scalar(@actual_ids), $limit);
+
+		my @expected_ids = split("\n", $expected[$i]);
+
+		foreach (@expected_ids)
+		{
+			if (exists($actual_set{$_}))
+			{
+				$correct++;
+			}
+			$total++;
+		}
+	}
+
+	cmp_ok($correct / $total, ">=", $min, $operator);
+}
+
+# Initialize node
+$node = PostgreSQL::Test::Cluster->new('node');
+$node->init;
+$node->start;
+
+# Create table
+$node->safe_psql("postgres", "CREATE EXTENSION vector;");
+$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim), c int4);");
+$node->safe_psql("postgres",
+	"INSERT INTO tst SELECT i, ARRAY[$array_sql], i % $nc FROM generate_series(1, 20000) i;"
+);
+
+# Generate queries
+for (1 .. 20)
+{
+	my @r = ();
+	for (1 .. $dim)
+	{
+		push(@r, rand());
+	}
+	push(@queries, "[" . join(",", @r) . "]");
+	push(@cs, int(rand() * $nc));
+}
+
+# Get exact results
+@expected = ();
+for my $i (0 .. $#queries)
+{
+	my $res = $node->safe_psql("postgres", "SELECT i FROM tst WHERE c = $cs[$i] ORDER BY v <=> '$queries[$i]' LIMIT $limit;");
+	push(@expected, $res);
+}
+
+# Add index
+$node->safe_psql("postgres", qq(
+	SET maintenance_work_mem = '256MB';
+	SET max_parallel_maintenance_workers = 2;
+	CREATE INDEX ON tst USING hnsw (v vector_cosine_ops, c);
+));
+
+# Test recall
+test_recall(0.99, '<=>');
+
+# Test vacuum
+$node->safe_psql("postgres", "DELETE FROM tst WHERE c > 5;");
+$node->safe_psql("postgres", "VACUUM tst;");
+
+# Test columns
+my ($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (c);");
+like($stderr, qr/first column must be a vector/);
+
+($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (c, v vector_cosine_ops);");
+like($stderr, qr/first column must be a vector/);
+
+($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_cosine_ops, c, c);");
+like($stderr, qr/index cannot have more than two columns/);
+
+($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_cosine_ops, v vector_cosine_ops);");
+like($stderr, qr/column 2 cannot be a vector/);
+
+done_testing();

test/t/045_hnsw_intvec_build_recall.pl

@@ -1,132 +0,0 @@
-use strict;
-use warnings FATAL => 'all';
-use PostgreSQL::Test::Cluster;
-use PostgreSQL::Test::Utils;
-use Test::More;
-
-my $node;
-my @queries = ();
-my @expected;
-my $limit = 20;
-my $dim = 10;
-my $array_sql = join(",", ('(random() * 255)::int - 128') x $dim);
-
-sub test_recall
-{
-	my ($min, $operator) = @_;
-	my $correct = 0;
-	my $total = 0;
-
-	my $explain = $node->safe_psql("postgres", qq(
-		SET enable_seqscan = off;
-		EXPLAIN ANALYZE SELECT i FROM tst ORDER BY v $operator '$queries[0]' LIMIT $limit;
-	));
-	like($explain, qr/Index Scan/);
-
-	for my $i (0 .. $#queries)
-	{
-		my $actual = $node->safe_psql("postgres", qq(
-			SET enable_seqscan = off;
-			SELECT i FROM tst ORDER BY v $operator '$queries[$i]' LIMIT $limit;
-		));
-		my @actual_ids = split("\n", $actual);
-		my %actual_set = map { $_ => 1 } @actual_ids;
-
-		my @expected_ids = split("\n", $expected[$i]);
-
-		foreach (@expected_ids)
-		{
-			if (exists($actual_set{$_}))
-			{
-				$correct++;
-			}
-			$total++;
-		}
-	}
-
-	cmp_ok($correct / $total, ">=", $min, $operator);
-}
-
-# Initialize node
-$node = PostgreSQL::Test::Cluster->new('node');
-$node->init;
-$node->start;
-
-# Create table
-$node->safe_psql("postgres", "CREATE EXTENSION vector;");
-$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v intvec($dim));");
-$node->safe_psql("postgres",
-	"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 10000) i;"
-);
-
-# Generate queries
-for (1 .. 20)
-{
-	my @r = ();
-	for (1 .. $dim)
-	{
-		push(@r, int(rand(256)) - 128);
-	}
-	push(@queries, "[" . join(",", @r) . "]");
-}
-
-# Check each index type
-my @operators = ("<->", "<#>", "<=>", "<+>");
-my @opclasses = ("intvec_l2_ops", "intvec_ip_ops", "intvec_cosine_ops", "intvec_l1_ops");
-
-for my $i (0 .. $#operators)
-{
-	my $operator = $operators[$i];
-	my $opclass = $opclasses[$i];
-
-	# Get exact results
-	@expected = ();
-	foreach (@queries)
-	{
-		my $res = $node->safe_psql("postgres", "SELECT i FROM tst ORDER BY v $operator '$_' LIMIT $limit;");
-		push(@expected, $res);
-	}
-
-	# Build index serially
-	$node->safe_psql("postgres", qq(
-		SET max_parallel_maintenance_workers = 0;
-		CREATE INDEX idx ON tst USING hnsw (v $opclass);
-	));
-
-	# Test approximate results
-	my $min = 0.98;
-	test_recall($min, $operator);
-
-	$node->safe_psql("postgres", "DROP INDEX idx;");
-
-	# Build index in parallel in memory
-	my ($ret, $stdout, $stderr) = $node->psql("postgres", qq(
-		SET client_min_messages = DEBUG;
-		SET min_parallel_table_scan_size = 1;
-		CREATE INDEX idx ON tst USING hnsw (v $opclass);
-	));
-	is($ret, 0, $stderr);
-	like($stderr, qr/using \d+ parallel workers/);
-
-	# Test approximate results
-	test_recall($min, $operator);
-
-	$node->safe_psql("postgres", "DROP INDEX idx;");
-
-	# Build index in parallel on disk
-	# Set parallel_workers on table to use workers with low maintenance_work_mem
-	($ret, $stdout, $stderr) = $node->psql("postgres", qq(
-		ALTER TABLE tst SET (parallel_workers = 2);
-		SET client_min_messages = DEBUG;
-		SET maintenance_work_mem = '4MB';
-		CREATE INDEX idx ON tst USING hnsw (v $opclass);
-		ALTER TABLE tst RESET (parallel_workers);
-	));
-	is($ret, 0, $stderr);
-	like($stderr, qr/using \d+ parallel workers/);
-	like($stderr, qr/hnsw graph no longer fits into maintenance_work_mem/);
-
-	$node->safe_psql("postgres", "DROP INDEX idx;");
-}
-
-done_testing();

test/t/046_hnsw_intvec_insert_recall.pl

@@ -1,113 +0,0 @@
-use strict;
-use warnings FATAL => 'all';
-use PostgreSQL::Test::Cluster;
-use PostgreSQL::Test::Utils;
-use Test::More;
-
-my $node;
-my @queries = ();
-my @expected;
-my $limit = 20;
-my $dim = 10;
-my $array_sql = join(",", ('(random() * 255)::int - 128') x $dim);
-
-sub test_recall
-{
-	my ($min, $operator) = @_;
-	my $correct = 0;
-	my $total = 0;
-
-	my $explain = $node->safe_psql("postgres", qq(
-		SET enable_seqscan = off;
-		EXPLAIN ANALYZE SELECT i FROM tst ORDER BY v $operator '$queries[0]' LIMIT $limit;
-	));
-	like($explain, qr/Index Scan/);
-
-	for my $i (0 .. $#queries)
-	{
-		my $actual = $node->safe_psql("postgres", qq(
-			SET enable_seqscan = off;
-			SELECT i FROM tst ORDER BY v $operator '$queries[$i]' LIMIT $limit;
-		));
-		my @actual_ids = split("\n", $actual);
-		my %actual_set = map { $_ => 1 } @actual_ids;
-
-		my @expected_ids = split("\n", $expected[$i]);
-
-		foreach (@expected_ids)
-		{
-			if (exists($actual_set{$_}))
-			{
-				$correct++;
-			}
-			$total++;
-		}
-	}
-
-	cmp_ok($correct / $total, ">=", $min, $operator);
-}
-
-# Initialize node
-$node = PostgreSQL::Test::Cluster->new('node');
-$node->init;
-$node->start;
-
-# Create table
-$node->safe_psql("postgres", "CREATE EXTENSION vector;");
-$node->safe_psql("postgres", "CREATE TABLE tst (i serial, v intvec($dim));");
-
-# Generate queries
-for (1 .. 20)
-{
-	my @r = ();
-	for (1 .. $dim)
-	{
-		push(@r, int(rand(256)) - 128);
-	}
-	push(@queries, "[" . join(",", @r) . "]");
-}
-
-# Check each index type
-my @operators = ("<->", "<#>", "<=>", "<+>");
-my @opclasses = ("intvec_l2_ops", "intvec_ip_ops", "intvec_cosine_ops", "intvec_l1_ops");
-
-for my $i (0 .. $#operators)
-{
-	my $operator = $operators[$i];
-	my $opclass = $opclasses[$i];
-
-	# Add index
-	$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING hnsw (v $opclass);");
-
-	# Use concurrent inserts
-	$node->pgbench(
-		"--no-vacuum --client=10 --transactions=1000",
-		0,
-		[qr{actually processed}],
-		[qr{^$}],
-		"concurrent INSERTs",
-		{
-			"040_hnsw_intvec_insert_recall_$opclass" => "INSERT INTO tst (v) VALUES (ARRAY[$array_sql]);"
-		}
-	);
-
-	# Get exact results
-	@expected = ();
-	foreach (@queries)
-	{
-		my $res = $node->safe_psql("postgres", qq(
-			SET enable_indexscan = off;
-			SELECT i FROM tst ORDER BY v $operator '$_' LIMIT $limit;
-		));
-		push(@expected, $res);
-	}
-
-	# Test approximate results
-	my $min = 0.98;
-	test_recall($min, $operator);
-
-	$node->safe_psql("postgres", "DROP INDEX idx;");
-	$node->safe_psql("postgres", "TRUNCATE tst;");
-}
-
-done_testing();

test/t/047_hnsw_intvec_vacuum_recall.pl

@@ -1,101 +0,0 @@
-use strict;
-use warnings FATAL => 'all';
-use PostgreSQL::Test::Cluster;
-use PostgreSQL::Test::Utils;
-use Test::More;
-
-my $node;
-my @queries = ();
-my @expected;
-my $limit = 20;
-my $dim = 10;
-my $array_sql = join(",", ('(random() * 255)::int - 128') x $dim);
-
-sub test_recall
-{
-	my ($min, $ef_search, $test_name) = @_;
-	my $correct = 0;
-	my $total = 0;
-
-	my $explain = $node->safe_psql("postgres", qq(
-		SET enable_seqscan = off;
-		SET hnsw.ef_search = $ef_search;
-		EXPLAIN ANALYZE SELECT i FROM tst ORDER BY v <-> '$queries[0]' LIMIT $limit;
-	));
-	like($explain, qr/Index Scan/);
-
-	for my $i (0 .. $#queries)
-	{
-		my $actual = $node->safe_psql("postgres", qq(
-			SET enable_seqscan = off;
-			SET hnsw.ef_search = $ef_search;
-			SELECT i FROM tst ORDER BY v <-> '$queries[$i]' LIMIT $limit;
-		));
-		my @actual_ids = split("\n", $actual);
-		my %actual_set = map { $_ => 1 } @actual_ids;
-
-		my @expected_ids = split("\n", $expected[$i]);
-
-		foreach (@expected_ids)
-		{
-			if (exists($actual_set{$_}))
-			{
-				$correct++;
-			}
-			$total++;
-		}
-	}
-
-	cmp_ok($correct / $total, ">=", $min, $test_name);
-}
-
-# Initialize node
-$node = PostgreSQL::Test::Cluster->new('node');
-$node->init;
-$node->start;
-
-# Create table
-$node->safe_psql("postgres", "CREATE EXTENSION vector;");
-$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v intvec($dim));");
-$node->safe_psql("postgres", "ALTER TABLE tst SET (autovacuum_enabled = false);");
-$node->safe_psql("postgres",
-	"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 10000) i;"
-);
-
-# Add index
-$node->safe_psql("postgres", "CREATE INDEX ON tst USING hnsw (v intvec_l2_ops) WITH (m = 4, ef_construction = 8);");
-
-# Delete data
-$node->safe_psql("postgres", "DELETE FROM tst WHERE i > 2500;");
-
-# Generate queries
-for (1 .. 20)
-{
-	my @r = ();
-	for (1 .. $dim)
-	{
-		push(@r, int(rand(256)) - 128);
-	}
-	push(@queries, "[" . join(",", @r) . "]");
-}
-
-# Get exact results
-@expected = ();
-foreach (@queries)
-{
-	my $res = $node->safe_psql("postgres", qq(
-		SET enable_indexscan = off;
-		SELECT i FROM tst ORDER BY v <-> '$_' LIMIT $limit;
-	));
-	push(@expected, $res);
-}
-
-test_recall(0.18, $limit, "before vacuum");
-test_recall(0.84, 100, "before vacuum");
-
-# TODO Test concurrent inserts with vacuum
-$node->safe_psql("postgres", "VACUUM tst;");
-
-test_recall(0.84, $limit, "after vacuum");
-
-done_testing();

test/t/048_hnsw_intvec_duplicates.pl

@@ -1,58 +0,0 @@
-use strict;
-use warnings FATAL => 'all';
-use PostgreSQL::Test::Cluster;
-use PostgreSQL::Test::Utils;
-use Test::More;
-
-# Initialize node
-my $node = PostgreSQL::Test::Cluster->new('node');
-$node->init;
-$node->start;
-
-# Create table
-$node->safe_psql("postgres", "CREATE EXTENSION vector;");
-$node->safe_psql("postgres", "CREATE TABLE tst (v intvec(3));");
-
-sub insert_vectors
-{
-	for my $i (1 .. 20)
-	{
-		$node->safe_psql("postgres", "INSERT INTO tst VALUES ('[1,1,1]');");
-	}
-}
-
-sub test_duplicates
-{
-	my $res = $node->safe_psql("postgres", qq(
-		SET enable_seqscan = off;
-		SET hnsw.ef_search = 1;
-		SELECT COUNT(*) FROM (SELECT * FROM tst ORDER BY v <-> '[1,1,1]') t;
-	));
-	is($res, 10);
-}
-
-# Test duplicates with build
-insert_vectors();
-$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING hnsw (v intvec_l2_ops);");
-test_duplicates();
-
-# Reset
-$node->safe_psql("postgres", "TRUNCATE tst;");
-
-# Test duplicates with inserts
-insert_vectors();
-test_duplicates();
-
-# Test fallback path for inserts
-$node->pgbench(
-	"--no-vacuum --client=5 --transactions=100",
-	0,
-	[qr{actually processed}],
-	[qr{^$}],
-	"concurrent INSERTs",
-	{
-		"042_hnsw_intvec_duplicates" => "INSERT INTO tst VALUES ('[1,1,1]');"
-	}
-);
-
-done_testing();