Download the PHP package displace/ext-turbovec without Composer
On this page you can find all versions of the php package displace/ext-turbovec. It is possible to download/install these versions without Composer. Possible dependencies are resolved automatically.
Download displace/ext-turbovec
More information about displace/ext-turbovec
Files in displace/ext-turbovec
Package ext-turbovec
Short Description PHP 8.3+ native, in-process vector indexing and ANN search via TurboQuant.
License MIT
Homepage https://github.com/DisplaceTech/ext-turbovec
FAQ
Example:
In general, it is recommended to use always a project to download your libraries. In an application normally there is more than one library needed.
- Some hosting areas are not accessible by a terminal or SSH. Then it is not possible to use Composer.
- To use Composer is sometimes complicated. Especially for beginners.
- Composer needs much resources. Sometimes they are not available on a simple webspace.
- If you are using private repositories you don't need to share your credentials. You can set up everything on our site and then you provide a simple download link to your team member.
- Simplify your Composer build process. Use our own command line tool to download the vendor folder as binary. This makes your build process faster and you don't need to expose your credentials for private repositories.
Informations about the package ext-turbovec
ext-turbovec
Native vector search for PHP, in-process.
Quantized ANN indexing over millions of embeddings — no vector database, no sidecar, no remote API.
What is ext-turbovec?
ext-turbovec is a PHP 8.3+ extension for in-process vector indexing and
approximate-nearest-neighbor search. It is the retrieval half of a fully
local RAG stack for PHP: ext-infer
generates the embeddings, ext-turbovec indexes and searches them. No
Python sidecar, no vector database, no data leaving the machine.
Under the hood it binds the turbovec
Rust crate by Ryan Codrai — an implementation of Google Research's
TurboQuant quantization algorithm
(Gollapudi et al., arXiv:2504.19874):
data-oblivious 2–4-bit compression with near-optimal distortion, no training
phase, and SIMD search kernels (NEON on ARM, AVX2/AVX-512BW on x86) that
beat FAISS IndexPQFastScan on most configurations. All credit for the
index engine goes upstream — this extension is a downstream bindings
consumer, not a fork.
- 🗜️ 4-bit vectors — a 10M-document corpus that needs 31 GB as float32 fits in ~4 GB.
- ➕ Online ingest — add vectors and they're searchable; no train step, no rebuilds.
- 🔍 Filtered search — pass an id allowlist and the SIMD kernel honors it directly; selective filters get faster, not less accurate.
- 🆔 Stable ids —
IdMapIndexaddresses vectors by your own uint64 ids (SQL primary keys), with O(1)remove(). - 💾 Persistence — versioned on-disk formats (
.tv/.tvim) that round-trip search results bit-exactly. - ⚡ In-process — search latency is the kernel time; there's no IPC or network in the loop.
Quick start
Pair it with ext-infer for end-to-end semantic search — see
examples/semantic-search.php, or
examples/basic-search.php for a standalone,
model-free walkthrough.
The packed-vector contract
Index methods accept vectors as packed little-endian float32 binary
strings — exactly what PHP's pack() produces with the g format code:
strlen($payload) must be a whole multiple of 4 * $dim; anything else
throws DimensionMismatchException. This is deliberately the only input
path — packed strings cross the FFI boundary as a single memcpy-sized blob
instead of millions of PHP zvals, and it's the format ext-infer's
EmbeddingModel will emit natively in its next release. For array-minded
code, Vectors::pack(array $floats): string and
Vectors::unpack(string $packed, int $dim): array are the on-ramp.
Memory math
The index stores bitWidth bits per coordinate plus one float32 scale per
vector. For 100,000 documents at dim 1024 with 4-bit quantization:
bitWidth: 2 halves the codes again when recall requirements allow.
dim must be a positive multiple of 8 (every common embedding size
qualifies: 384, 512, 768, 1024, 1536, 3072, 4096, …).
API surface (v0.1)
| Class | Methods |
|---|---|
Displace\Vector\TurboQuantIndex |
__construct(int $dim, int $bitWidth = 4) · add(string $vectors) · count() · search(string $query, int $k = 10): SearchResult · write(string $path) · static load(string $path) |
Displace\Vector\IdMapIndex |
as above, plus addWithIds(string $vectors, array $ids) · search(string $query, int $k = 10, ?array $allowlist = null) · remove(int $id) |
Displace\Vector\SearchResult |
ids(): array · scores(): array · count(): int · Countable · IteratorAggregate yielding ['id' => int, 'score' => float] |
Displace\Vector\Vectors |
static pack(array $floats): string · static unpack(string $packed, int $dim): array |
Exceptions: VectorException (extends \RuntimeException) with
InvalidArgumentException, DimensionMismatchException, and
IndexIOException beneath it. Full reference with semantics at
turbovec.displace.tech.
Compatibility
| macOS arm64 | Linux x86_64 | Linux arm64 | Windows | |
|---|---|---|---|---|
| PHP 8.3 | ✅ | ✅ | ✅ | — |
| PHP 8.4 | ✅ | ✅ | ✅ | — |
| PHP 8.5 | ✅ | ✅ | ✅ | — |
CPU-only by design. On x86_64 the AVX-512BW kernel engages automatically
when the CPU has it, with an AVX2 fallback (Haswell 2013+) below it.
Linux note: the upstream engine links OpenBLAS — binaries need the
libopenblas0 package at runtime (libopenblas-dev to build from
source). macOS uses the built-in Accelerate framework; nothing to install.
This release pins upstream turbovec 0.9.0.
The pin is exact because the on-disk index formats must stay stable;
upstream bumps are deliberate, documented events (see RELEASE.md).
Roadmap
Shipped (v0.1) TurboQuantIndex · IdMapIndex with allowlist
filtering and O(1) remove · packed-vector fast path · Vectors helpers ·
write/load persistence · typed exceptions · PHPT suite · CI matrix ·
PIE-compatible binary releases.
Next (v0.2) batch search (multi-query in one call) ·
mmap-backed load() · range/threshold search · zero-copy packed handoff
from ext-infer's EmbeddingModel.
Deliberately out of scope Windows · GPU · graph indexes (HNSW-style) — TurboQuant's flat quantized scan is the sweet spot this extension is built around.
License
MIT © 2026 Eric Mann / Displace Technologies. Bundles turbovec © Ryan Codrai, MIT — see THIRD-PARTY-NOTICES.md. TurboQuant is the work of Gollapudi et al., arXiv:2504.19874.
