feat: Initialize MongoDB store (#51)

* Initialize store

* -

* -

* -

* -

* -

* -

* -

* Update .env

* fix

* -

Author: OskarStark

.env

@@ -17,3 +17,6 @@ AZURE_OPENAI_KEY=
 
 # For using SerpApi (tool)
 SERP_API_KEY=
+
+# For using MongoDB Atlas (store)
+MONGODB_URI=

composer.json

@@ -24,7 +24,7 @@
     },
     "require-dev": {
         "codewithkyrian/chromadb-php": "^0.2.1",
-        "mongodb/mongodb": "^1.19",
+        "mongodb/mongodb": "^1.20",
         "php-cs-fixer/shim": "^3.64",
         "phpstan/phpstan": "^1.12",
         "phpunit/phpunit": "^11.3",
@@ -37,6 +37,9 @@
         "symfony/dotenv": "^6.4 || ^7.1",
         "symfony/var-dumper": "^6.4 || ^7.1"
     },
+    "conflict": {
+        "mongodb/mongodb": "<1.20"
+    },
     "suggest": {
         "codewithkyrian/chromadb-php": "For using the ChromaDB as retrieval vector store.",
         "mongodb/mongodb": "For using MongoDB Atlas as retrieval vector store.",

examples/store-mongodb-similarity-search.php

@@ -0,0 +1,77 @@
+<?php
+
+use MongoDB\Client as MongoDBClient;
+use PhpLlm\LlmChain\Chain;
+use PhpLlm\LlmChain\Document\Document;
+use PhpLlm\LlmChain\Document\Metadata;
+use PhpLlm\LlmChain\DocumentEmbedder;
+use PhpLlm\LlmChain\Message\Message;
+use PhpLlm\LlmChain\Message\MessageBag;
+use PhpLlm\LlmChain\OpenAI\Model\Embeddings;
+use PhpLlm\LlmChain\OpenAI\Model\Gpt;
+use PhpLlm\LlmChain\OpenAI\Model\Gpt\Version;
+use PhpLlm\LlmChain\OpenAI\Platform\OpenAI;
+use PhpLlm\LlmChain\Store\MongoDB\Store;
+use PhpLlm\LlmChain\ToolBox\ChainProcessor;
+use PhpLlm\LlmChain\ToolBox\Tool\SimilaritySearch;
+use PhpLlm\LlmChain\ToolBox\ToolAnalyzer;
+use PhpLlm\LlmChain\ToolBox\ToolBox;
+use Symfony\Component\Dotenv\Dotenv;
+use Symfony\Component\HttpClient\HttpClient;
+use Symfony\Component\Uid\Uuid;
+
+require_once dirname(__DIR__).'/vendor/autoload.php';
+(new Dotenv())->loadEnv(dirname(__DIR__).'/.env');
+
+if (empty($_ENV['OPENAI_API_KEY']) || empty($_ENV['MONGODB_URI'])) {
+    echo 'Please set OPENAI_API_KEY and MONGODB_URI environment variables.'.PHP_EOL;
+    exit(1);
+}
+
+// initialize the store
+$store = new Store(
+    client: new MongoDBClient($_ENV['MONGODB_URI']),
+    databaseName: 'my-database',
+    collectionName: 'my-collection',
+    indexName: 'my-index',
+    vectorFieldName: 'vector',
+);
+
+// our data
+$movies = [
+    ['title' => 'Inception', 'description' => 'A skilled thief is given a chance at redemption if he can successfully perform inception, the act of planting an idea in someone\'s subconscious.', 'regisseur' => 'Christopher Nolan'],
+    ['title' => 'The Matrix', 'description' => 'A hacker discovers the world he lives in is a simulated reality and joins a rebellion to overthrow its controllers.', 'regisseur' => 'The Wachowskis'],
+    ['title' => 'The Godfather', 'description' => 'The aging patriarch of an organized crime dynasty transfers control of his empire to his reluctant son.', 'regisseur' => 'Francis Ford Coppola'],
+];
+
+// create embeddings and documents
+foreach ($movies as $movie) {
+    $documents[] = Document::fromText(
+        id: Uuid::v4(),
+        text: $movie['title'].' '.$movie['description'],
+        metadata: new Metadata($movie),
+    );
+}
+
+// create embeddings for documents
+$platform = new OpenAI(HttpClient::create(), $_ENV['OPENAI_API_KEY']);
+$embedder = new DocumentEmbedder($embeddings = new Embeddings($platform), $store);
+$embedder->embed($documents);
+
+// initialize the index
+$store->initialize();
+
+$llm = new Gpt($platform, Version::gpt4oMini());
+
+$similaritySearch = new SimilaritySearch($embeddings, $store);
+$toolBox = new ToolBox(new ToolAnalyzer(), [$similaritySearch]);
+$processor = new ChainProcessor($toolBox);
+$chain = new Chain($llm, [$processor], [$processor]);
+
+$messages = new MessageBag(
+    Message::forSystem('Please answer all user questions only using SimilaritySearch function.'),
+    Message::ofUser('Which movie fits the theme of the mafia?')
+);
+$response = $chain->call($messages);
+
+echo $response.PHP_EOL;

src/Store/InitializableStoreInterface.php

@@ -0,0 +1,13 @@
+<?php
+
+declare(strict_types=1);
+
+namespace PhpLlm\LlmChain\Store;
+
+interface InitializableStoreInterface extends StoreInterface
+{
+    /**
+     * @param array<mixed> $options
+     */
+    public function initialize(array $options = []): void;
+}

src/Store/MongoDB/Store.php

@@ -7,11 +7,14 @@
 use MongoDB\BSON\Binary;
 use MongoDB\Client;
 use MongoDB\Collection;
+use MongoDB\Driver\Exception\CommandException;
 use PhpLlm\LlmChain\Document\Document;
 use PhpLlm\LlmChain\Document\Metadata;
 use PhpLlm\LlmChain\Document\Vector;
+use PhpLlm\LlmChain\Store\InitializableStoreInterface;
 use PhpLlm\LlmChain\Store\VectorStoreInterface;
 use Psr\Log\LoggerInterface;
+use Psr\Log\NullLogger;
 use Symfony\Component\Uid\Uuid;
 
 /**
@@ -37,7 +40,7 @@
  *
  * @author Oskar Stark <[email protected]>
  */
-final readonly class Store implements VectorStoreInterface
+final readonly class Store implements VectorStoreInterface, InitializableStoreInterface
 {
     /**
      * @param string $databaseName    The name of the database
@@ -48,12 +51,12 @@
      */
     public function __construct(
         private Client $client,
-        private LoggerInterface $logger,
         private string $databaseName,
         private string $collectionName,
         private string $indexName,
         private string $vectorFieldName = 'vector',
         private bool $bulkWrite = false,
+        private LoggerInterface $logger = new NullLogger(),
     ) {
     }
 
@@ -135,6 +138,37 @@ public function query(Vector $vector, array $options = []): array
         return $documents;
     }
 
+    /**
+     * @param array{fields?: array<mixed>} $options
+     */
+    public function initialize(array $options = []): void
+    {
+        try {
+            if ([] !== $options && !array_key_exists('fields', $options)) {
+                throw new \InvalidArgumentException('The only supported option is "fields"');
+            }
+
+            $this->getCollection()->createSearchIndex(
+                [
+                    'fields' => array_merge([
+                        [
+                            'numDimensions' => 1536,
+                            'path' => $this->vectorFieldName,
+                            'similarity' => 'euclidean',
+                            'type' => 'vector',
+                        ],
+                    ], $options['fields'] ?? []),
+                ],
+                [
+                    'name' => $this->indexName,
+                    'type' => 'vectorSearch',
+                ],
+            );
+        } catch (CommandException $e) {
+            $this->logger->warning($e->getMessage());
+        }
+    }
+
     private function getCollection(): Collection
     {
         return $this->client->selectCollection($this->databaseName, $this->collectionName);