RAG in Laravel with pgvector and Embeddings | Mohamed Said [ ![Mohamed Said](https://cdn.msaied.com/01KT78WE565VEMM3PSNQAAB0MH.png) Mohamed Said Laravel Backend Engineer ](https://msaied.com) [ Home ](https://msaied.com) [ Projects ](https://msaied.com/projects) [ Articles ](https://msaied.com/articles) [ Certificates ](https://msaied.com/certificates) [ Contact ](https://msaied.com#contact-section) [ ](https://github.com/EG-Mohamed) [ Home ](https://msaied.com) [ Projects ](https://msaied.com/projects) [ Articles ](https://msaied.com/articles) [ Certificates ](https://msaied.com/certificates) [ Contact ](https://msaied.com#contact-section) [ home ](https://msaied.com) [ articles ](https://msaied.com/articles) Practical RAG in Laravel: pgvector, Embeddings, and Retrieval Pipelines 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) ![Practical RAG in Laravel: pgvector, Embeddings, and Retrieval Pipelines](https://cdn.msaied.com/411/8d5b164ce43b1c6b9b658b7f72a0c369.png) #laravel #ai #pgvector #postgresql Practical RAG in Laravel: pgvector, Embeddings, and Retrieval Pipelines ========================================================================= 11 Jul 2026 4 min read ![Mohamed Said](https://cdn.msaied.com/01KT78WE565VEMM3PSNQAAB0MJ.jpg) Mohamed Said Table of contents 1. [ 01 Why RAG in Laravel Without a Dedicated Vector DB? ](#why-rag-in-laravel-without-a-dedicated-vector-db) 2. [ 02 1. Enable pgvector and Add the Column ](#1-enable-pgvector-and-add-the-column) 3. [ 03 2. The Embedding Service ](#2-the-embedding-service) 4. [ 04 3. Ingestion Pipeline ](#3-ingestion-pipeline) 5. [ 05 4. Retrieval: Cosine Similarity with pgvector ](#4-retrieval-cosine-similarity-with-pgvector) 6. [ 06 5. Prompt Assembly and Generation ](#5-prompt-assembly-and-generation) 7. [ 07 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. Found this useful? [ ](https://twitter.com/intent/tweet?url=https%3A%2F%2Fmsaied.com%2Farticles%2Fpractical-rag-in-laravel-pgvector-embeddings-and-retrieval-pipelines-1&text=Practical+RAG+in+Laravel%3A+pgvector%2C+Embeddings%2C+and+Retrieval+Pipelines) [ ](https://www.linkedin.com/sharing/share-offsite/?url=https%3A%2F%2Fmsaied.com%2Farticles%2Fpractical-rag-in-laravel-pgvector-embeddings-and-retrieval-pipelines-1) Frequently Asked Questions ---------------------------- 3 questions Q01 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. Q02 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. Q03 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. Continue reading More Articles --------------- [ View all ](https://msaied.com/articles) [ ![Filament v3 Table Bulk Actions: Custom Confirmation, Progress Feedback, and Job Dispatch](https://cdn.msaied.com/412/68d290c667a619900211863678fa0b1f.png) filament laravel queues ### Filament v3 Table Bulk Actions: Custom Confirmation, Progress Feedback, and Job Dispatch Go beyond the default delete bulk action. Learn how to build Filament v3 bulk actions with custom confirmation... ![Mohamed Said](https://cdn.msaied.com/01KT78WE565VEMM3PSNQAAB0MJ.jpg) Mohamed Said 11 Jul 2026 3 min read Read ](https://msaied.com/articles/filament-v3-table-bulk-actions-custom-confirmation-progress-feedback-and-job-dispatch) [ ![Laravel Reverb WebSocket Scaling: Channels, Presence, and Horizontal Deployment](https://cdn.msaied.com/410/2698f47a7daff990e9807996fe0f493c.png) laravel reverb websockets ### Laravel Reverb WebSocket Scaling: Channels, Presence, and Horizontal Deployment Move beyond a single Reverb node. Learn how to scale Laravel Reverb horizontally with Redis pub/sub, configure... ![Mohamed Said](https://cdn.msaied.com/01KT78WE565VEMM3PSNQAAB0MJ.jpg) Mohamed Said 11 Jul 2026 4 min read Read ](https://msaied.com/articles/laravel-reverb-websocket-scaling-channels-presence-and-horizontal-deployment) [ ![Laravel Enum Casts, Backed Enums, and Value Semantics in PHP 8.3](https://cdn.msaied.com/408/3534df365ffb2c8f6c430180bfaba8f1.png) laravel php8.3 enums ### Laravel Enum Casts, Backed Enums, and Value Semantics in PHP 8.3 PHP 8.3 backed enums combined with Laravel's native enum casting unlock type-safe domain models. Learn how to... ![Mohamed Said](https://cdn.msaied.com/01KT78WE565VEMM3PSNQAAB0MJ.jpg) Mohamed Said 10 Jul 2026 1 min read Read ](https://msaied.com/articles/laravel-enum-casts-backed-enums-and-value-semantics-in-php-83) [ ![Mohamed Said](https://cdn.msaied.com/01KT78WE565VEMM3PSNQAAB0MH.png) Mohamed Said Laravel Backend Engineer ](https://msaied.com)Senior Backend Engineer specializing in Laravel, scalable SaaS platforms, APIs, and cloud infrastructure. I build secure, high-performance web applications that help businesses grow. Explore - [Home](https://msaied.com) - [Projects](https://msaied.com/projects) - [Articles](https://msaied.com/articles) - [Certificates](https://msaied.com/certificates) - [Contact](https://msaied.com#contact-section) Connect - [ hello@msaied.com ](mailto:hello@msaied.com) - [ +20 109 461 9204 ](tel:+201094619204) © 2026 Mohamed Said. All rights reserved. [ ](https://github.com/EG-Mohamed) [ ](https://www.linkedin.com/in/msaiedm/) [ ](https://wa.me/201094619204) [ ](mailto:hello@msaied.com) [ ](https://drive.google.com/file/u/0/d/1MF20IPRJyzfy32mhEutjL5EpSls0w2Q8/view)