PHPackages displace/ai-toolkit - PHPackages - PHPackages [Skip to content](#main-content)[PHPackages](/)[Directory](/)[Categories](/categories)[Trending](/trending)[Leaderboard](/leaderboard)[Changelog](/changelog)[Analyze](/analyze)[Collections](/collections)[Log in](/login)[Sign up](/register) 1. [Directory](/) 2. / 3. [Utility & Helpers](/categories/utility) 4. / 5. displace/ai-toolkit ActiveLibrary[Utility & Helpers](/categories/utility) displace/ai-toolkit =================== Pure-PHP utilities for local-first AI pipelines: text chunkers, packed-vector math, MRL truncation. v0.1.0(1mo ago)0155MITPHPPHP ^8.3CI passing Since Jun 11Pushed 1mo agoCompare [ Source](https://github.com/DisplaceTech/ai-toolkit)[ Packagist](https://packagist.org/packages/displace/ai-toolkit)[ Docs](https://github.com/DisplaceTech/ai-toolkit)[ RSS](/packages/displace-ai-toolkit/feed)WikiDiscussions main Synced 1w ago READMEChangelog (1)Dependencies (3)Versions (2)Used By (0) ai-toolkit ========== [](#ai-toolkit) **Pure-PHP utilities for local-first AI pipelines.** Text chunkers, packed-vector math, Matryoshka truncation — boring on purpose. [![CI](https://github.com/DisplaceTech/ai-toolkit/actions/workflows/ci.yml/badge.svg)](https://github.com/DisplaceTech/ai-toolkit/actions/workflows/ci.yml) [![Packagist](https://camo.githubusercontent.com/e9f932db5add50974549cebe86cc2b74351274e9337912342307581589ed26cd/68747470733a2f2f696d672e736869656c64732e696f2f7061636b61676973742f762f646973706c6163652f61692d746f6f6c6b6974)](https://packagist.org/packages/displace/ai-toolkit) [![PHP 8.3 / 8.4 / 8.5](https://camo.githubusercontent.com/f8c66ec3458748baee370b7844203c334e62735196a3c31b11c504ab609f4be7/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f5048502d382e33253230253743253230382e34253230253743253230382e352d3737374242343f6c6f676f3d706870266c6f676f436f6c6f723d7768697465)](https://camo.githubusercontent.com/f8c66ec3458748baee370b7844203c334e62735196a3c31b11c504ab609f4be7/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f5048502d382e33253230253743253230382e34253230253743253230382e352d3737374242343f6c6f676f3d706870266c6f676f436f6c6f723d7768697465) [![mbstring only](https://camo.githubusercontent.com/2af4a71cdc92e64a6001326652f2dc37fe04ddd9ed935e2e57edecbb6b258c29/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f646570656e64656e636965732d6d62737472696e672532306f6e6c792d627269676874677265656e)](https://camo.githubusercontent.com/2af4a71cdc92e64a6001326652f2dc37fe04ddd9ed935e2e57edecbb6b258c29/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f646570656e64656e636965732d6d62737472696e672532306f6e6c792d627269676874677265656e) [![MIT License](https://camo.githubusercontent.com/5caa455d8debc46fb23abbadb45a733a937f3910a73fc875c2f7820468e1bb54/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f4c6963656e73652d4d49542d677265656e)](LICENSE) --- What is ai-toolkit? ------------------- [](#what-is-ai-toolkit) The plumbing every embed-and-search pipeline needs and no one wants to rewrite: split documents into chunks, move vectors around in the packed float32 format, slice Matryoshka embeddings down to size. Pure PHP, no extension required, no framework, no model downloads. ``` composer require displace/ai-toolkit ``` It pairs with [ext-infer](https://github.com/DisplaceTech/ext-infer)(embeddings), [ext-turbovec](https://github.com/DisplaceTech/ext-turbovec)(vector search), and the [ai-contracts](https://github.com/DisplaceTech/ai-contracts) interfaces — but depends on none of them. Chunkers -------- [](#chunkers) Three strategies behind one `Chunker` interface, sized in characters (multibyte-aware): ``` use Displace\AI\Toolkit\Text\RecursiveCharacterChunker; $chunker = new RecursiveCharacterChunker(size: 1000, overlap: 200); foreach ($chunker->chunk($markdown) as $chunk) { // embed → index } ``` ChunkerStrategyReach for it when`RecursiveCharacterChunker`Split on paragraphs first, then lines, sentences, words; hard-cut lastProse, markdown, HTML-stripped text — **the default**`SentenceChunker`Pack whole sentences; never splits mid-sentence; overlap counted in sentencesTranscripts and clean copy where sentence integrity matters`FixedSizeChunker`Sliding character window, verbatim slicesLogs, minified or OCR text with no useful structurePacked-vector math ------------------ [](#packed-vector-math) Vectors in the Displace stack travel as **packed little-endian float32 binary strings** — the output of `pack('g*', ...$floats)`, batches by plain concatenation. `Packed` is the pure-PHP companion for glue code and tests: ``` use Displace\AI\Toolkit\Vector\Packed; $a = Packed::pack([0.12, 0.48, /* ... */]); // floats → packed buffer $b = Packed::pack([0.33, 0.19, /* ... */]); Packed::cosine($a, $b); // similarity in [-1, 1] Packed::dot($a, $b); // inner product Packed::norm($a); // L2 norm Packed::normalize($batch, dim: 1024); // per-vector unit length Packed::unpack($a, dim: 1024); // packed buffer → floats ``` ### Matryoshka (MRL) truncation [](#matryoshka-mrl-truncation) MRL-trained embedding models (Qwen3-Embedding, ...) pack the most important information into the leading coordinates, so a prefix of the vector is itself a usable embedding. Trade recall for a smaller index by slicing — no re-embedding required: ``` // 1024-dim Qwen3 embeddings down to 256-dim, renormalized per vector: $small = Packed::truncate($vectors, fromDim: 1024, toDim: 256); ``` Only valid for MRL-trained models; truncating an ordinary embedding just throws information away. On the hot path --------------- [](#on-the-hot-path) `Packed` is for correctness, not speed — it's pure PHP. When ext-turbovec is loaded, prefer its native `Displace\Vector\Vectors`pack/unpack and let the index do the scoring; when you only need similarity between a handful of vectors, `Packed` is plenty. Deliberately out of scope ------------------------- [](#deliberately-out-of-scope) **Token-based chunking** — token counts are model-specific and need a tokenizer; character budgets are model-independent and close enough for retrieval (rule of thumb: ~4 characters per English token) · **embedding generation** — that's ext-infer or your API client · **vector storage and ANN search** — that's ext-turbovec or your database · **document loaders/parsers** (PDF, HTML, ...) — bring your own text · **an orchestration framework** — chains and agents belong to the frameworks. License ------- [](#license) [MIT](LICENSE) © 2026 Eric Mann / Displace Technologies ### Health Score 39 — LowBetter than 84% of packages Maintenance91 Actively maintained with recent releases Popularity14 Limited adoption so far Community6 Small or concentrated contributor base Maturity38 Early-stage or recently created project Bus Factor1 Top contributor holds 100% of commits — single point of failure How is this calculated?**Maintenance (25%)** — Last commit recency, latest release date, and issue-to-star ratio. Uses a 2-year decay window. **Popularity (30%)** — Total and monthly downloads, GitHub stars, and forks. Logarithmic scaling prevents top-heavy scores. **Community (15%)** — Contributors, dependents, forks, watchers, and maintainers. Measures real ecosystem engagement. **Maturity (30%)** — Project age, version count, PHP version support, and release stability. ### Release Activity Cadence Unknown Total 1 Last Release 45d ago ### Community Maintainers ![](https://www.gravatar.com/avatar/86bb3fa9fcfe57b8d313e527e9e02bde810951b25722b4717b0953a6c8db41b2?d=identicon)[ericmann](/maintainers/ericmann) --- Top Contributors [![ericmann](https://avatars.githubusercontent.com/u/605474?v=4)](https://github.com/ericmann "ericmann (13 commits)") --- Tags aivectorsembeddingsragchunkingtext-splittermatryoshka ### Code Quality TestsPHPUnit Static AnalysisPHPStan Code StylePHP CS Fixer Type Coverage Yes ### Embed Badge ![Health badge](/badges/displace-ai-toolkit/health.svg) ``` [![Health](https://phpackages.com/badges/displace-ai-toolkit/health.svg)](https://phpackages.com/packages/displace-ai-toolkit) ``` ### Alternatives [maestroerror/laragent Power of AI Agents in your Laravel project 639159.9k](/packages/maestroerror-laragent) PHPackages © 2026 [Directory](/)[Categories](/categories)[Trending](/trending)[Changelog](/changelog)[Analyze](/analyze)