Contents
pgvector and Qdrant Parity Matrix
This file is generated from docs/user_guide/parity_matrix.data.
Run scripts/generate-parity-matrix.sh after changing the source data.
Status values:
stable: covered by the first production SQL compatibility contract.experimental: SQL-visible or implemented, but outside the production promise.planned: explicitly not part of the first stable surface yet.intentionally different: pgContext deliberately uses PostgreSQL-native semantics.
| Capability | Reference | Status | pgContext release contract | Owning reference |
|---|---|---|---|---|
| Dense vector SQL type, casts, operators, aggregates | pgvector | stable |
Dense vector, including vector(n) typmod metadata and assignment enforcement, is the stable first-release vector surface. |
docs/user_guide/api_reference.md |
| Exact vector search over arrays and registered tables | pgvector,Qdrant | stable |
Exact search is the correctness baseline for SQL search, recall checks, ANN, and hybrid retrieval. | docs/user_guide/vector_search.md |
| Collections over PostgreSQL source tables | Qdrant | stable |
Collections reference authoritative PostgreSQL source tables and pgContext catalog metadata. | docs/user_guide/collections.md |
| Point upsert and delete mappings | Qdrant | stable |
Point APIs map source keys to stable pgContext point IDs without owning source rows. | docs/user_guide/collections.md |
| Filter JSON over ordinary columns and JSONB paths | Qdrant | stable |
Registered fields render through typed SQL predicates and SPI parameters. | docs/user_guide/filters.md |
| Scroll, count, and facet | Qdrant | stable |
Stable APIs operate over active table-backed point mappings with shared filter semantics. | docs/user_guide/api_reference.md |
| Dense plus full-text hybrid query | Qdrant | stable |
pgcontext.query supports dense vector plus PostgreSQL full-text retrieval with reciprocal rank fusion. |
docs/user_guide/hybrid_retrieval.md |
| Telemetry and operational status functions | Qdrant | stable |
Diagnostics expose typed statuses and local counters without vectors, payloads, filters, or literal query text. | docs/user_guide/operations.md |
| Model versions and embedding migrations | Qdrant | stable |
Model-version metadata and migration progress records are stable catalog APIs. | docs/user_guide/collections.md |
| HNSW access method | pgvector,Qdrant | experimental |
pgcontext_hnsw serves dense L2, inner-product, cosine, and L1 kNN through metric-bound persisted PostgreSQL pages, retains only published topology during concurrent inserts, exposes cancellation and hnsw_last_scan_work counters, has no silent exact fallback, resets on rescan, and does not support mark/restore. Table-driven mutation, VACUUM, REINDEX, exact-oracle, and crash/restart coverage runs for every dense metric; Hamming kNN remains unavailable. |
docs/user_guide/indexes.md |
| Filtered ANN serving | Qdrant | experimental |
Filtered table search binds a validated HNSW index and, in one statement snapshot, materializes registered column/JSONB candidates once. Selective masks cross over to exact scoring; broader masks drive one page-backed HNSW traversal using the stored metric. Masked-out nodes remain connectors and sparse masks can expand through ACORN-like second-hop neighbors. Final source joins preserve logical PointId, MVCC/deletion state, ACL/RLS, predicate, and exact-distance rechecks. Selective, broad, empty, stale-stat, deleted, typed JSONB, tenant-isolation, and cancellation cases are covered. | docs/user_guide/vector_search.md |
| SQL halfvec | pgvector | experimental |
halfvec text I/O, dimensions, typmods, exact distance helpers, distance operators, explicit rounding numeric-array casts, aggregates, btree ordering opclass, and L2 pgcontext_hnsw opclass backed by dense vector storage are SQL-visible. |
docs/user_guide/pgvector_migration.md |
| SQL sparsevec | pgvector,Qdrant | experimental |
sparsevec text I/O, dimensions, typmods, structured array construction, dense real[]/vector casts, canonical accessors, exact L2, inner-product, cosine, and L1 helpers/operators, aggregates, btree ordering opclass, L2 pgcontext_hnsw opclass backed by dense vector storage, sparse collection metadata, exact array top-k, and named table search are SQL-visible; non-L2 sparse ANN branches remain planned. |
docs/user_guide/vector_search.md |
| SQL bit vectors | pgvector | experimental |
bitvec text I/O, dimensions, typmods, Hamming/Jaccard distance, distance operators, boolean[] casts, PostgreSQL bit/bit varying casts, pgvector-compatible built-in bit Hamming/Jaccard functions and operators, bitwise OR/AND aggregates, btree ordering opclass, and explicit Hamming pgcontext_hnsw indexing through pgcontext.bitvec_hnsw_hamming_ops are SQL-visible; Jaccard ANN indexing remains planned and default pgcontext_hnsw attempts fail with SQLSTATE 42704. |
docs/user_guide/pgvector_migration.md |
| SQL quantization APIs | pgvector,Qdrant | experimental |
Binary, scalar/SQ8-style, product quantize/reconstruct helpers, and exact quantized-candidate rerank are SQL-visible; quantized HNSW index serving remains planned. | docs/user_guide/indexes.md |
| Named dense vector registration and search | Qdrant | stable |
Named dense vector registration, dimensions, metrics, and search-by-name selection are part of the first stable table-backed search surface. | docs/user_guide/collections.md |
| Per-vector dense index and quantization metadata | Qdrant | experimental |
The experimental collection_vectors and configure_vector functions expose validated metadata containers; HNSW/quantization option semantics and full planner use remain planned. |
docs/user_guide/collections.md |
| Named sparse vectors per collection | Qdrant | experimental |
Sparse vector registration, storage/index/status metadata, exact named sparse table search, and exact dense+sparse RRF query fusion are SQL-visible; sparse ANN/index serving remains planned. | docs/user_guide/collections.md |
| Multi-vector and late-interaction query | Qdrant | experimental |
Exact late-interaction MaxSim rerank over explicit arrays, exact table-backed vector[] search, typed ANN-planner diagnostics, and HNSW token candidate generation with O(1) declared token-dimension validation, source-table exact MaxSim rerank, deleted-point checks, token-table prerequisite failures, planner preflight, and hydrated budget checks are SQL-visible; full memory/latency release gates remain open. |
docs/user_guide/vector_search.md |
| Recommendation search | Qdrant | stable |
Positive/negative point-ID and raw-vector recommendation search uses exact rerank with ACL/RLS and deleted-point checks. | docs/user_guide/vector_search.md |
| Discovery or explore search | Qdrant | stable |
Exact diversity-oriented discover/explore search ranks active rows farthest from visible context examples. | docs/user_guide/vector_search.md |
| Query constructors | Qdrant | stable |
Validated SQL constructors produce JSON plans for nearest, recommend, discover, lookup, prefetch, weighting, thresholds, formulas, and final rerank. | docs/user_guide/vector_search.md |
| Grouped search | Qdrant | stable |
Grouped exact search caps results per registered payload field with deterministic ordering and PostgreSQL ACL/RLS checks. | docs/user_guide/collections.md |
| Payload mutation helpers | Qdrant | stable |
Registered payload fields can be set, deleted, or cleared through documented source-table mutation policy. | docs/user_guide/collections.md |
| Bulk point backfill APIs | Qdrant | stable |
Bulk point upsert, delete, and source-table backfill APIs report bounded per-batch progress diagnostics. | docs/user_guide/collections.md |
| IVFFlat | pgvector | intentionally different |
pgContext does not support IVFFlat in the first production surface; use exact search or HNSW paths, or keep pgvector IVFFlat indexes alongside pgContext during migration. | docs/user_guide/indexes.md |
| PostgreSQL-native ACL, RLS, transactions, and backups | Postgres improvement | intentionally different |
pgContext relies on PostgreSQL source tables, privileges, RLS, transactions, backup, and WAL instead of replacing them. | docs/user_guide/security.md |
| Rebuildable acceleration artifacts | Postgres improvement | intentionally different |
Indexes and segment files are cache artifacts; PostgreSQL tables remain authoritative. | docs/user_guide/storage.md |