RAG in Laravel with pgvector and Embeddings | Mohamed Said [Skip to content](#main) [ ![](https://cdn.msaied.com/01KT78WE565VEMM3PSNQAAB0MH.png) Mohamed SaidLaravel Backend Engineer ](https://www.msaied.com/public) - [Home](https://www.msaied.com/public) - [Projects](https://www.msaied.com/public/projects) - [Articles](https://www.msaied.com/public/articles) - [Certificates](https://www.msaied.com/public/certificates) - [About](https://www.msaied.com/public#about) [ Contact](https://www.msaied.com/public#contact) Menu Menu ---- Close - [HomeStart here](https://www.msaied.com/public) - [ProjectsCase studies](https://www.msaied.com/public/projects) - [ArticlesEngineering notes](https://www.msaied.com/public/articles) - [CertificatesCredentials](https://www.msaied.com/public/certificates) - [AboutHow I work](https://www.msaied.com/public#about) - [ContactGet in touch](https://www.msaied.com/public#contact) [Start a conversation](https://www.msaied.com/public#contact) [WhatsApp](https://wa.me/201094619204) [Email](mailto:hello@msaied.com) 1. [Home](https://www.msaied.com/public) 2. / 3. [Articles](https://www.msaied.com/public/articles) 4. / 5. Practical RAG in Laravel: pgvector, Embeddings, and Retrieval Pipelines Practical RAG in Laravel: pgvector, Embeddings, and Retrieval Pipelines ======================================================================== Build a production-ready retrieval-augmented generation pipeline in Laravel using pgvector, OpenAI embeddings, and a clean retrieval abstraction — without reaching for a dedicated vector database. ![](https://cdn.msaied.com/01M22N44A70A5MC2S599JP0MPH.webp) [Mohamed Said](https://www.msaied.com/public#person) Published 11 Jul 2026 · Updated 11 Jul 2026 · 4 min read ShareCopy linkCopied ![Practical RAG in Laravel: pgvector, Embeddings, and Retrieval Pipelines](https://cdn.msaied.com/411/8d5b164ce43b1c6b9b658b7f72a0c369.png) On this page +1. [Why RAG in Laravel Without a Dedicated Vector DB?](#why-rag-in-laravel-without-a-dedicated-vector-db) 2. [1. Enable pgvector and Add the Column](#1-enable-pgvector-and-add-the-column) 3. [2. The Embedding Service](#2-the-embedding-service) 4. [3. Ingestion Pipeline](#3-ingestion-pipeline) 5. [4. Retrieval: Cosine Similarity with pgvector](#4-retrieval-cosine-similarity-with-pgvector) 6. [5. Prompt Assembly and Generation](#5-prompt-assembly-and-generation) 7. [Key Takeaways](#key-takeaways) Why RAG in Laravel Without a Dedicated Vector DB? ------------------------------------------------- Pinecone, Weaviate, and Qdrant are compelling, but they add operational overhead. If you are already running PostgreSQL, the `pgvector` extension gives you cosine-similarity search with a single `CREATE EXTENSION` and a new column type. For most SaaS workloads — knowledge bases, document Q&A, semantic search — that is more than enough. This article walks through a complete, opinionated RAG pipeline: ingestion, embedding storage, retrieval, and prompt assembly. --- 1. Enable pgvector and Add the Column ------------------------------------- ```sql CREATE EXTENSION IF NOT EXISTS vector; ``` ```php // database/migrations/2024_06_01_create_document_chunks_table.php Schema::create('document_chunks', function (Blueprint $table) { $table->id(); $table->foreignId('document_id')->constrained()->cascadeOnDelete(); $table->text('content'); $table->vector('embedding', 1536); // OpenAI text-embedding-3-small $table->timestamps(); }); ``` Laravel's `Blueprint` does not ship a `vector()` macro out of the box, so register one in a service provider: ```php use Illuminate\Database\Schema\Blueprint; use Illuminate\Support\Facades\DB; Blueprint::macro('vector', function (string $column, int $dimensions = 1536) { /** @var Blueprint $this */ return $this->addColumn('vector', $column, compact('dimensions')); }); // In AppServiceProvider::boot() \Illuminate\Database\Schema\Grammars\PostgresGrammar::macro( 'typeVector', fn ($column) => "vector({$column->dimensions})" ); ``` --- 2. The Embedding Service ------------------------ Keep the OpenAI HTTP call behind a thin interface so you can swap providers or stub in tests. ```php interface EmbeddingProvider { /** @return float[] */ public function embed(string $text): array; } final class OpenAiEmbeddingProvider implements EmbeddingProvider { public function __construct( private readonly \OpenAI\Client $client, private readonly string $model = 'text-embedding-3-small', ) {} public function embed(string $text): array { $response = $this->client->embeddings()->create([ 'model' => $this->model, 'input' => $text, ]); return $response->embeddings[0]->embedding; } } ``` Bind it in the container: ```php $this->app->singleton(EmbeddingProvider::class, fn () => new OpenAiEmbeddingProvider(app(\OpenAI\Client::class)) ); ``` --- 3. Ingestion Pipeline --------------------- Chunk documents before embedding — 512-token chunks with a 64-token overlap is a solid default. ```php final class IngestDocumentAction { public function __construct( private readonly EmbeddingProvider $embedder, ) {} public function handle(Document $document): void { $chunks = $this->chunk($document->body, maxTokens: 512, overlap: 64); foreach ($chunks as $content) { $vector = $this->embedder->embed($content); DB::table('document_chunks')->insert([ 'document_id' => $document->id, 'content' => $content, 'embedding' => '[' . implode(',', $vector) . ']', 'created_at' => now(), 'updated_at' => now(), ]); } } /** @return string[] */ private function chunk(string $text, int $maxTokens, int $overlap): array { // Naive word-boundary chunking; replace with tiktoken FFI for precision. $words = explode(' ', $text); $chunks = []; $step = max(1, $maxTokens - $overlap); for ($i = 0; $i < count($words); $i += $step) { $chunks[] = implode(' ', array_slice($words, $i, $maxTokens)); } return array_filter($chunks); } } ``` --- 4. Retrieval: Cosine Similarity with pgvector --------------------------------------------- ```php final class RetrievalService { public function __construct( private readonly EmbeddingProvider $embedder, ) {} /** @return array */ public function retrieve(string $query, int $topK = 5): array { $vector = '[' . implode(',', $this->embedder->embed($query)) . ']'; return DB::select( "SELECT content, 1 - (embedding ?::vector) AS score FROM document_chunks ORDER BY embedding ?::vector LIMIT ?", [$vector, $vector, $topK] ); } } ``` The `` operator is pgvector's cosine distance. Subtract from 1 to get similarity. Add an `ivfflat` index once your chunk count exceeds ~100k rows: ```sql CREATE INDEX ON document_chunks USING ivfflat (embedding vector_cosine_ops) WITH (lists = 100); ``` --- 5. Prompt Assembly and Generation --------------------------------- ```php final class AnswerQuestionAction { public function __construct( private readonly RetrievalService $retrieval, private readonly \OpenAI\Client $client, ) {} public function handle(string $question): string { $chunks = $this->retrieval->retrieve($question, topK: 4); $context = collect($chunks) ->pluck('content') ->implode("\n\n---\n\n"); $response = $this->client->chat()->create([ 'model' => 'gpt-4o-mini', 'messages' => [ ['role' => 'system', 'content' => "Answer using only the context below.\n\n{$context}"], ['role' => 'user', 'content' => $question], ], ]); return $response->choices[0]->message->content; } } ``` --- Key Takeaways ------------- - **pgvector is production-ready** for most SaaS RAG workloads; skip the dedicated vector DB until you hit scale. - **Chunk with overlap** to avoid splitting context across boundaries; tune chunk size per domain. - **Abstract the embedding provider** behind an interface — it makes testing trivial and provider swaps painless. - **Use `ivfflat` indexes** once chunk counts grow; `lists = sqrt(row_count)` is a reasonable starting heuristic. - **Keep retrieval and generation separate actions** — retrieval is deterministic and cacheable; generation is not. - [laravel](https://www.msaied.com/public/articles?search=laravel) - [ai](https://www.msaied.com/public/articles?search=ai) - [pgvector](https://www.msaied.com/public/articles?search=pgvector) - [postgresql](https://www.msaied.com/public/articles?search=postgresql) Frequently asked questions --------------------------- Do I need a dedicated vector database like Pinecone for RAG in Laravel?Not for most workloads. The pgvector PostgreSQL extension supports cosine-similarity search with ivfflat indexing, which handles millions of vectors efficiently. A dedicated vector DB only becomes necessary at very large scale or when you need advanced filtering that pgvector cannot express. How do I test the embedding and retrieval logic without hitting the OpenAI API?Because the embedding provider is behind an interface, you can bind a fake in tests that returns a fixed float array. Retrieval tests can seed document\_chunks with known vectors and assert that the correct chunks are returned for a given query vector. What chunk size should I use for embeddings?512 tokens with a 64-token overlap is a solid general-purpose default. For technical documentation you may go up to 1024 tokens; for conversational snippets 256 tokens often works better. Measure retrieval precision on your own dataset rather than relying on universal rules. ![Mohamed Said](https://cdn.msaied.com/01M22N44A70A5MC2S599JP0MPH.webp)About the author ---------------- [Mohamed Said](https://www.msaied.com/public#person)Senior Backend Engineer specializing in Laravel, scalable SaaS platforms, APIs, and cloud infrastructure. I build secure, high-performance web applications that help businesses grow. [About](https://www.msaied.com/public#about) [GitHub ↗](https://github.com/EG-Mohamed) [LinkedIn ↗](https://www.linkedin.com/in/msaiedm/) [WhatsApp ↗](https://wa.me/201094619204) [Email Address ↗](mailto:hello@msaied.com) [My CV ↗](https://drive.google.com/file/u/0/d/1MF20IPRJyzfy32mhEutjL5EpSls0w2Q8/view) [Previous articleLaravel Reverb WebSocket Scaling: Channels, Presence, and Horizontal Deployment](https://www.msaied.com/public/articles/laravel-reverb-websocket-scaling-channels-presence-and-horizontal-deployment) [Next articleFilament v3 Table Bulk Actions: Custom Confirmation, Progress Feedback, and Job Dispatch](https://www.msaied.com/public/articles/filament-v3-table-bulk-actions-custom-confirmation-progress-feedback-and-job-dispatch) On this page ------------- 1. [Why RAG in Laravel Without a Dedicated Vector DB?](#why-rag-in-laravel-without-a-dedicated-vector-db) 2. [1. Enable pgvector and Add the Column](#1-enable-pgvector-and-add-the-column) 3. [2. The Embedding Service](#2-the-embedding-service) 4. [3. Ingestion Pipeline](#3-ingestion-pipeline) 5. [4. Retrieval: Cosine Similarity with pgvector](#4-retrieval-cosine-similarity-with-pgvector) 6. [5. Prompt Assembly and Generation](#5-prompt-assembly-and-generation) 7. [Key Takeaways](#key-takeaways) ### Have a technical challenge? Tell me what you’re building. I reply within two working days. [Start a conversation](https://www.msaied.com/public#contact) Related articles ----------------- [ ![](https://cdn.msaied.com/740/cce86edc21eddcbdd2f2454fadaf9c70.png) · 3 min read### The Pipeline Pattern in Laravel: Custom Pipelines Beyond Middleware 5 Oct 2026 ](https://www.msaied.com/public/articles/the-pipeline-pattern-in-laravel-custom-pipelines-beyond-middleware-1) [ ![](https://cdn.msaied.com/739/2d6897fdcdcf090613f96f72a64b8a78.png) · 4 min read### MySQL Full-Text Search in Laravel: Indexes, Relevance Scoring, and Boolean Mode 4 Oct 2026 ](https://www.msaied.com/public/articles/mysql-full-text-search-in-laravel-indexes-relevance-scoring-and-boolean-mode) [ ![](https://cdn.msaied.com/738/073696a3fefe18bec825beec5ac658f5.png) · 4 min read### Laravel Queue Rate-Limited Middleware: Throttling Jobs Without Losing Work 4 Oct 2026 ](https://www.msaied.com/public/articles/laravel-queue-rate-limited-middleware-throttling-jobs-without-losing-work) Have a technical challenge? ---------------------------- Tell me what you’re building. I reply within two working days. [Discuss your project ↗](https://www.msaied.com/public#contact) © 2026 Mohamed Said · Built with Laravel, meant to last.Senior Backend Engineer specializing in Laravel, scalable SaaS platforms, APIs, and cloud infrastructure. I build secure, high-performance web applications that help businesses grow. - [Home](https://www.msaied.com/public) - [Articles](https://www.msaied.com/public/articles) - [Certificates](https://www.msaied.com/public/certificates) - [GitHub](https://github.com/EG-Mohamed) - [LinkedIn](https://www.linkedin.com/in/msaiedm/) - [WhatsApp](https://wa.me/201094619204) - [Email Address](mailto:hello@msaied.com) - [My CV](https://drive.google.com/file/u/0/d/1MF20IPRJyzfy32mhEutjL5EpSls0w2Q8/view) - [Sitemap](https://www.msaied.com/public/sitemap.xml)