liuyu/pgvector
1
0
Fork 0
mirror of https://github.com/pgvector/pgvector.git synced 2026-07-14 00:26:55 +08:00
Code Issues Packages Projects Releases Wiki Activity

Added support for inline filtering with HNSW

Browse Source
This commit is contained in:
Andrew Kane
2024-10-09 19:02:40 -07:00
parent 3126fbdb6f
commit 3ccfab8f92
12 changed files with 567 additions and 128 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
src/hnsw.h
View File

@@ -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
@@ -104,6 +105,8 @@
#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_lock_tranche_id;
@@ -121,6 +124,7 @@ HnswPtrDeclare(HnswElementData, HnswElementRelptr, HnswElementPtr);
HnswPtrDeclare(HnswNeighborArray, HnswNeighborArrayRelptr, HnswNeighborArrayPtr);
HnswPtrDeclare(HnswNeighborArrayPtr, HnswNeighborsRelptr, HnswNeighborsPtr);
HnswPtrDeclare(char, DatumRelptr, DatumPtr);
HnswPtrDeclare(IndexTupleData, IndexTupleRelptr, IndexTuplePtr);
struct HnswElementData
{
@@ -136,6 +140,7 @@ struct HnswElementData
OffsetNumber neighborOffno;
BlockNumber neighborPage;
DatumPtr value;
IndexTuplePtr itup;
LWLock lock;
};
@@ -161,6 +166,7 @@ typedef struct HnswSearchCandidate
pairingheap_node w_node;
HnswElementPtr element;
double distance;
bool matches;
} HnswSearchCandidate;
/* HNSW index options */
@@ -256,15 +262,17 @@ typedef struct HnswBuildState
double reltuples;
/* Support functions */
FmgrInfo *procinfo;
FmgrInfo *procinfo[2];
FmgrInfo *normprocinfo;
Oid collation;
Oid *collation;
/* Variables */
HnswGraph graphData;
HnswGraph *graph;
double ml;
int maxLevel;
bool useIndexTuple;
TupleDesc tupdesc;
/* Memory */
MemoryContext graphCtx;
@@ -333,9 +341,9 @@ typedef struct HnswScanOpaqueData
MemoryContext tmpCtx;
/* Support functions */
FmgrInfo *procinfo;
FmgrInfo *procinfo[2];
FmgrInfo *normprocinfo;
Oid collation;
Oid *collation;
} HnswScanOpaqueData;
typedef HnswScanOpaqueData * HnswScanOpaque;
@@ -353,8 +361,8 @@ typedef struct HnswVacuumState
int efConstruction;
/* Support functions */
FmgrInfo *procinfo;
Oid collation;
FmgrInfo *procinfo[2];
Oid *collation;
/* Variables */
struct tidhash_hash *deleted;
@@ -375,29 +383,31 @@ bool HnswCheckNorm(FmgrInfo *procinfo, Oid collation, Datum value);
Buffer HnswNewBuffer(Relation index, ForkNumber forkNum);
void HnswInitPage(Buffer buf, Page page);
void HnswInit(void);
List *HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement);
List *HnswSearchLayer(char *base, Datum q, IndexTuple qtup, ScanKeyData *keyData, List *ep, int ef, int lc, Relation index, FmgrInfo **procinfo, Oid *collation, int m, bool inserting, HnswElement skipElement, bool inMemory);
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, FmgrInfo *procinfo, Oid collation, int m, int efConstruction, bool existing);
HnswSearchCandidate *HnswEntryCandidate(char *base, HnswElement em, Datum q, Relation rel, FmgrInfo *procinfo, Oid collation, bool loadVec);
void HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo **procinfo, Oid *collation, int m, int efConstruction, bool existing, bool inMemory);
HnswSearchCandidate *HnswEntryCandidate(char *base, HnswElement em, Datum q, IndexTuple qtup, ScanKeyData *keyData, Relation rel, FmgrInfo **procinfo, Oid *collation, 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, Datum value, Datum *values, bool *isnull, ItemPointer heap_tid, bool building);
void HnswUpdateNeighborsOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting, bool building);
void HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec);
void HnswLoadElement(HnswElement element, double *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec, double *maxDistance);
void HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element);
void HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newElement, float distance, int lm, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation);
void HnswUpdateNeighborsOnDisk(Relation index, FmgrInfo **procinfo, Oid *collation, HnswElement e, int m, bool checkExisting, bool building);
void HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec, Relation index);
void HnswLoadElement(HnswElement element, double *distance, bool *matches, Datum *q, IndexTuple qtup, ScanKeyData *keyData, Relation index, FmgrInfo **procinfo, Oid *collation, 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, FmgrInfo **procinfo, Oid *collation);
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);
void HnswInitProcinfo(FmgrInfo **procinfo, Relation index);
bool HnswIndexTupleIsEqual(IndexTuple a, IndexTuple b, TupleDesc tupdesc);
/* Index access methods */
IndexBuildResult *hnswbuild(Relation heap, Relation index, IndexInfo *indexInfo);