High Level Graph RAG Gemini Embedding

composer require google-gemini-php/client

# .env file
GEMINI_API_KEY="your_google_ai_studio_api_key"

php artisan make:config gemini

// config/gemini.php
return [
    'api_key' => env('GEMINI_API_KEY'),
];

// In app/Jobs/ProcessDocumentJob.php

namespace App\Jobs;

use App\Models\Document;
use Gemini\Laravel\Facades\Gemini; // Using the Laravel facade for simplicity
use Illuminate\Bus\Queueable;
// ... other use statements
use Illuminate\Support\Facades\DB;
use Illuminate\Support\Facades\Http;
use Illuminate\Support\Facades\Storage;

class ProcessDocumentJob implements ShouldQueue
{
    // ... (constructor and properties remain the same)

    public function handle(): void
    {
        try {
            // 1. Update Status & Fetch File
            $this->document->update(['status' => 'processing']);
            $fileContents = Storage::disk('s3')->get($this->document->storage_path);

            // 2. Call Docling API
            $doclingResponse = Http::post('http://your-docling-api.com/process', ['file' => $fileContents]);
            $data = $doclingResponse->json();

            // 3. Create Vector Embeddings and Save to Supabase (The new part)
            $this->document->update(['status' => 'creating_embeddings']);
            $this->generateAndStoreEmbeddings($data['chunks']); // <-- MODIFIED LINE

            // 4. Create Knowledge Graph in Neo4j
            $this->document->update(['status' => 'building_graph']);
            $this->saveGraphToNeo4j($data['entities'], $data['relationships']);

            // 5. Final Success Status
            $this->document->update(['status' => 'completed']);

        } catch (\Throwable $e) {
            $this->document->update([
                'status' => 'failed',
                'error_message' => $e->getMessage()
            ]);
            throw $e;
        }
    }

    /**
     * Generates embeddings for text chunks using Gemini and saves them to Supabase.
     */
    private function generateAndStoreEmbeddings(array $chunks): void
    {
        // 1. Extract just the text content for the API call
        $textContents = array_column($chunks, 'content');
        if (empty($textContents)) {
            return; // Nothing to process
        }

        // 2. Call Gemini API in batch mode
        // The client handles making one or more requests if the batch is too large.
        $response = Gemini::embedContent($textContents);

        // 3. Prepare data for bulk insert
        $vectorsToInsert = [];
        foreach ($response->getEmbeddings() as $index => $embedding) {
            // The pgvector extension expects vectors as a string like '[1.2,3.4,-5.6]'
            $vectorString = '[' . implode(',', $embedding->getValues()) . ']';

            $vectorsToInsert[] = [
                'document_id' => $this->document->id,
                'content'     => $textContents[$index], // Match the embedding to its original text
                'embedding'   => $vectorString,
                'created_at'  => now(),
                'updated_at'  => now(),
            ];
        }

        // 4. Perform a single, efficient bulk insert operation
        if (!empty($vectorsToInsert)) {
            // Assumes you have a 'supabase' connection in config/database.php
            // that points to your Supabase Postgres instance.
            DB::connection('supabase')->table('document_chunks')->insert($vectorsToInsert);
        }
    }

    // ... (saveGraphToNeo4j method remains the same)
}

// config/database.php
'connections' => [
    // ... your default mysql/pgsql connection
    'supabase' => [
        'driver' => 'pgsql',
        'host' => env('SUPABASE_DB_HOST'),
        'port' => env('SUPABASE_DB_PORT'),
        'database' => env('SUPABASE_DB_DATABASE'),
        'username' => env('SUPABASE_DB_USERNAME'),
        'password' => env('SUPABASE_DB_PASSWORD'),
        'charset' => 'utf8',
        'prefix' => '',
        'schema' => 'public',
        'sslmode' => 'prefer',
    ],
]