Commit graph

9 commits

Author SHA1 Message Date
Alex Garcia
575371d751 Add DiskANN index for vec0 virtual table
Add DiskANN graph-based index: builds a Vamana graph with configurable R
(max degree) and L (search list size, separate for insert/query), supports
int8 quantization with rescore, lazy reverse-edge replacement, pre-quantized
query optimization, and insert buffer reuse. Includes shadow table management,
delete support, KNN integration, compile flag (SQLITE_VEC_ENABLE_DISKANN),
release-demo workflow, fuzz targets, and tests. Fixes rescore int8
quantization bug.
2026-03-31 01:21:54 -07:00
Alex Garcia
3358e127f6 Add IVF index for vec0 virtual table
Add inverted file (IVF) index type: partitions vectors into clusters via
k-means, quantizes to int8, and scans only the nearest nprobe partitions at
query time. Includes shadow table management, insert/delete, KNN integration,
compile flag (SQLITE_VEC_ENABLE_IVF), fuzz targets, and tests. Removes
superseded ivf-benchmarks/ directory.
2026-03-31 01:18:47 -07:00
Alex Garcia
ba0db0b6d6 Add rescore index for ANN queries
Add rescore index type: stores full-precision float vectors in a rowid-keyed
shadow table, quantizes to int8 for fast initial scan, then rescores top
candidates with original vectors. Includes config parser, shadow table
management, insert/delete support, KNN integration, compile flag
(SQLITE_VEC_ENABLE_RESCORE), fuzz targets, and tests.
2026-03-29 19:45:54 -07:00
Alex Garcia
bf2455f2ba Add ANN search support for vec0 virtual table
Add approximate nearest neighbor infrastructure to vec0: shared distance
dispatch (vec0_distance_full), flat index type with parser, NEON-optimized
cosine/Hamming for float32/int8, amalgamation script, and benchmark suite
(benchmarks-ann/) with ground-truth generation and profiling tools. Remove
unused vec_npy_each/vec_static_blobs code, fix missing stdint.h include.
2026-03-29 19:44:44 -07:00
Alex Garcia
0bca960e9d Add LPAREN, RPAREN, COMMA token types to the scanner
Extends the vec0 tokenizer to recognize '(', ')', and ',' as
single-character tokens, preparing for DiskANN index option parsing.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-02 18:07:57 -08:00
Alex Garcia
aab9b37de2 Add unit tests for distance functions (L2, cosine, hamming)
Add test-only wrappers behind SQLITE_VEC_TEST compile flag to expose
static distance functions for unit testing. Includes tests for
distance_l2_sqr_float (4 cases), distance_cosine_float (3 cases),
and distance_hamming (4 cases). Print active SIMD flags at test start.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-02 18:04:30 -08:00
Alex Garcia
79d5818015 Add regression tests for vec0_parse_vector_column edge cases
Add SQLITE_EMPTY tests for non-vector column inputs (primary key,
partition key, unknown types) and SQLITE_ERROR tests for zero
dimensions and empty brackets. Tighten existing error assertions
from rc != SQLITE_OK to exact expected return codes.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-02 17:50:31 -08:00
Alex Garcia
0659d8848d Update test-unit.c and unittest.rs functions to enforce pre-existing behavior
- Expand sqlite-vec-internal.h with scanner/tokenizer types, vector column
  definition types, and parser function declarations
- Fix min_idx declaration to match actual C signature (add candidates,
  bTaken, k_used params)
- Compile test-unit with -DSQLITE_CORE and link vendor/sqlite3.c so
  sqlite3 API functions (sqlite3_strnicmp, sqlite3_mprintf, etc.) resolve
- Add unit tests for vec0_token_next, Vec0Scanner, and
  vec0_parse_vector_column
- Fix Rust build.rs to define SQLITE_CORE and compile vendor/sqlite3.c
- Fix Rust min_idx FFI signature and wrapper to match actual C function

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-02 17:46:11 -08:00
Alex Garcia
6658624172
PARTITION KEY support (#122)
* initial pass at PARTITION KEY support.

* unit tests

* gha this PR branch

* fixup tests

* doc internal

* fix tests, KNN/rowids in

* define SQLITE_INDEX_CONSTRAINT_OFFSET

* whoops

* update tests, syrupy, use uv

* un ignore pyproject.toml

* dot

* tests/

* type error?

* win: .exe, update error name

* try fix macos python, paren around expr?

* win bash?

* dbg :(

* explicit error

* op

* dbg win

* win ./tests/.venv/Scripts/python.exe

* block UPDATEs on partition key values for now
2024-11-20 00:02:04 -08:00