Fix outdated code references across documentation

- Fix class names: CachedPlatform→CachePlatform, OllamaApiCatalog→ModelCatalog, Indexer→DocumentIndexer/SourceIndexer, Store\Vector→Platform\Vector\Vector - Fix namespaces: TokenUsage, MemoryInputProcessor, ConfiguredSourceIndexer, SourceIndexer, DocumentIndexer, StructuredOutputSerializer - Fix method calls: asText()→getContent(), private property access→getters - Fix API signatures: StoreInterface::query() now requires QueryInterface, ChromaDb\Store constructor updated, Ollama PlatformFactory simplified - Remove unused imports: Gpt, Embeddings, VertexAi Model - Fix incorrect file reference: _model-listing.php→_model.php - Fix incorrect link target: Crawler Tool→firecrawl-crawl.php - Fix MessageBagInterface→MessageBag (interface doesn't exist)
2026-03-23 23:42:18 +01:00 · 2026-03-20 13:58:41 +01:00
parent 9dab2aeafb
commit 17eaefb768
12 changed files with 60 additions and 72 deletions
--- a/UPGRADE.md
+++ b/UPGRADE.md
@@ -104,7 +104,7 @@ AI Bundle
   +$container->get('ai.toolbox.my_agent.subagent.research_agent');
   ```

- * An indexer configured with a `source`, now wraps the indexer with a `Symfony\AI\Store\ConfiguredSourceIndexer` decorator. This is
+ * An indexer configured with a `source`, now wraps the indexer with a `Symfony\AI\Store\Indexer\ConfiguredSourceIndexer` decorator. This is
   transparent - the configured source is still used by default, but can be overridden by passing a source to `index()`.

 * The `host_url` parameter for `Ollama` platform has been renamed `endpoint`.
@@ -120,12 +120,12 @@ Store
 -----

 * The `Symfony\AI\Store\Indexer` class has been replaced with two specialized implementations:
-   - `Symfony\AI\Store\SourceIndexer`: For indexing from sources (file paths, URLs, etc.) using a `LoaderInterface`
-   - `Symfony\AI\Store\DocumentIndexer`: For indexing documents directly without a loader
+   - `Symfony\AI\Store\Indexer\SourceIndexer`: For indexing from sources (file paths, URLs, etc.) using a `LoaderInterface`
+   - `Symfony\AI\Store\Indexer\DocumentIndexer`: For indexing documents directly without a loader

   ```diff
   -use Symfony\AI\Store\Indexer;
-   +use Symfony\AI\Store\SourceIndexer;
+   +use Symfony\AI\Store\Indexer\SourceIndexer;

   -$indexer = new Indexer($loader, $vectorizer, $store, '/path/to/source');
   -$indexer->index();
@@ -143,11 +143,11 @@ Store
   $indexer->index([$document1, $document2]);
   ```

- * The `Symfony\AI\Store\ConfiguredIndexer` class has been renamed to `Symfony\AI\Store\ConfiguredSourceIndexer`:
+ * The `Symfony\AI\Store\ConfiguredIndexer` class has been renamed to `Symfony\AI\Store\Indexer\ConfiguredSourceIndexer`:

   ```diff
   -use Symfony\AI\Store\ConfiguredIndexer;
-   +use Symfony\AI\Store\ConfiguredSourceIndexer;
+   +use Symfony\AI\Store\Indexer\ConfiguredSourceIndexer;

   -$indexer = new ConfiguredIndexer($innerIndexer, 'default-source');
   +$indexer = new ConfiguredSourceIndexer($sourceIndexer, 'default-source');
@@ -260,7 +260,7 @@ Platform
     * Run `composer require symfony/ai-cache-platform`
     * Change `Symfony\AI\Platform\CachedPlatform` namespace usages to `Symfony\AI\Platform\Bridge\Cache\CachePlatform`
     * The `ttl` option can be used in the configuration
- * Adopt usage of class `Symfony\AI\Platform\Serializer\StructuredOuputSerializer` to `Symfony\AI\Platform\StructuredOutput\Serializer`
+ * Adopt usage of class `Symfony\AI\Platform\Serializer\StructuredOutputSerializer` to `Symfony\AI\Platform\StructuredOutput\Serializer`

 UPGRADE FROM 0.1 to 0.2
 =======================
@@ -285,7 +285,7 @@ Agent
 * Constructor of `MemoryInputProcessor` now accepts an iterable of inputs instead of variadic arguments.

   ```php
-   use Symfony\AI\Agent\InputProcessor\MemoryInputProcessor;
+   use Symfony\AI\Agent\Memory\MemoryInputProcessor;

   // Before
   $processor = new MemoryInputProcessor($input1, $input2);
--- a/docs/bundles/ai-bundle.rst
+++ b/docs/bundles/ai-bundle.rst
@@ -798,7 +798,7 @@ Use the :class:`Symfony\\AI\\Agent\\Agent` service to leverage models and tools:
                Message::ofUser($message),
            );

-            return $this->agent->call($messages)->asText();
+            return $this->agent->call($messages)->getContent();
        }
    }

@@ -943,7 +943,7 @@ The token usage information can be accessed from the result metadata::
    use Symfony\AI\Agent\AgentInterface;
    use Symfony\AI\Platform\Message\Message;
    use Symfony\AI\Platform\Message\MessageBag;
-    use Symfony\AI\Platform\Result\Metadata\TokenUsage\TokenUsage;
+    use Symfony\AI\Platform\TokenUsage\TokenUsage;

    final readonly class MyService
    {
--- a/docs/components/agent.rst
+++ b/docs/components/agent.rst
@@ -16,10 +16,9 @@ Basic Usage
 -----------

 To instantiate an agent, you need to pass a :class:`Symfony\\AI\\Platform\\PlatformInterface` and a
-:class:`Symfony\\AI\\Platform\\Model` instance to the :class:`Symfony\\AI\\Agent\\Agent` class::
+model name to the :class:`Symfony\\AI\\Agent\\Agent` class::

    use Symfony\AI\Agent\Agent;
-    use Symfony\AI\Platform\Bridge\OpenAi\Gpt;
    use Symfony\AI\Platform\Bridge\OpenAi\PlatformFactory;

    $platform = PlatformFactory::create($apiKey);
@@ -27,7 +26,7 @@ To instantiate an agent, you need to pass a :class:`Symfony\\AI\\Platform\\Platf

    $agent = new Agent($platform, $model);

-You can then run the agent with a :class:`Symfony\\AI\\Platform\\Message\\MessageBagInterface` instance as input and an optional
+You can then run the agent with a :class:`Symfony\\AI\\Platform\\Message\\MessageBag` instance as input and an optional
 array of options::

    use Symfony\AI\Agent\Agent;
@@ -780,7 +779,7 @@ Code Examples
 .. _`Anthropic Toolbox Example`: https://github.com/symfony/ai/blob/main/examples/anthropic/toolcall.php
 .. _`Brave Tool`: https://github.com/symfony/ai/blob/main/examples/toolbox/brave.php
 .. _`Clock Tool`: https://github.com/symfony/ai/blob/main/examples/toolbox/clock.php
-.. _`Crawler Tool`: https://github.com/symfony/ai/blob/main/examples/toolbox/brave.php
+.. _`Crawler Tool`: https://github.com/symfony/ai/blob/main/examples/toolbox/firecrawl-crawl.php
 .. _`Mapbox Geocode Tool`: https://github.com/symfony/ai/blob/main/examples/toolbox/mapbox-geocode.php
 .. _`Mapbox Reverse Geocode Tool`: https://github.com/symfony/ai/blob/main/examples/toolbox/mapbox-reverse-geocode.php
 .. _`SerpAPI Tool`: https://github.com/symfony/ai/blob/main/examples/toolbox/serpapi.php
--- a/docs/components/chat.rst
+++ b/docs/components/chat.rst
@@ -20,7 +20,6 @@ with a ``Symfony\AI\Agent\AgentInterface`` and a ``Symfony\AI\Chat\MessageStoreI
    use Symfony\AI\Agent\Agent;
    use Symfony\AI\Chat\Chat;
    use Symfony\AI\Chat\InMemory\Store as InMemoryStore;
-    use Symfony\AI\Platform\Bridge\OpenAi\Gpt;
    use Symfony\AI\Platform\Bridge\OpenAi\PlatformFactory;
    use Symfony\AI\Platform\Message\Message;

--- a/docs/components/platform.rst
+++ b/docs/components/platform.rst
@@ -28,8 +28,6 @@ OpenAI, Anthropic, Google, Replicate, and others.

 For example, to use the OpenAI provider, you would typically do something like this::

-    use Symfony\AI\Platform\Bridge\OpenAi\Embeddings;
-    use Symfony\AI\Platform\Bridge\OpenAi\Gpt;
    use Symfony\AI\Platform\Bridge\OpenAi\PlatformFactory;

    $platform = PlatformFactory::create(env('OPENAI_API_KEY'));
@@ -37,7 +35,7 @@ For example, to use the OpenAI provider, you would typically do something like t
 With this :class:`Symfony\\AI\\Platform\\PlatformInterface` instance you can now interact with the LLM::

    // Generate a vector embedding for a text, returns a Symfony\AI\Platform\Result\VectorResult
-    $vectorResult = $platform->invoke($embeddings, 'What is the capital of France?');
+    $vectorResult = $platform->invoke('text-embedding-3-small', 'What is the capital of France?');

    // Generate a text completion with GPT, returns a Symfony\AI\Platform\Result\TextResult
    $result = $platform->invoke('gpt-4o-mini', new MessageBag(Message::ofUser('What is the capital of France?')));
@@ -81,30 +79,18 @@ Custom models
 ~~~~~~~~~~~~~

 For providers like Ollama, you can use custom models (built on top of ``Modelfile``), as those models are not listed in
-the default catalog, you can use the built-in ``OllamaApiCatalog`` to query the model information from the API rather
-than the default catalog::
+the default catalog. The ``ModelCatalog`` automatically queries the model information from the Ollama API::

-    use Symfony\AI\Platform\Bridge\Ollama\OllamaApiCatalog;
    use Symfony\AI\Platform\Bridge\Ollama\PlatformFactory;
    use Symfony\AI\Platform\Message\Message;
    use Symfony\AI\Platform\Message\MessageBag;

-    $platform = PlatformFactory::create('http://127.0.0.1:11434', HttpClient::create(), new OllamaApiCatalog(
-        'http://127.0.0.1:11434',
-        HttpClient::create(),
-    ));
+    $platform = PlatformFactory::create('http://127.0.0.1:11434');

    $platform->invoke('your_custom_model_name', new MessageBag(
        Message::ofUser(...)
    ));

-When using the bundle, the usage of ``OllamaApiCatalog`` is available via the ``api_catalog`` option::
-
-    ai:
-        platform:
-            ollama:
-                api_catalog: true
-
 Supported Models & Platforms
 ----------------------------

@@ -131,7 +117,7 @@ Supported Models & Platforms
  * `OpenAI's Whisper`_ with `OpenAI`_ and `Azure`_ as Platform
  * `LM Studio Catalog`_ and `HuggingFace`_ Models  with `LM Studio`_ as Platform.
  * All models provided by `HuggingFace`_ can be listed with a command in the examples folder,
-    and also filtered, e.g. ``php examples/huggingface/_model-listing.php --provider=hf-inference --task=object-detection``
+    and also filtered, e.g. ``php examples/huggingface/_model.php --provider=hf-inference --task=object-detection``
 * **Voice Models**
  * `ElevenLabs TTS`_ with `ElevenLabs`_ as Platform
  * `ElevenLabs STT`_ with `ElevenLabs`_ as Platform
@@ -556,7 +542,7 @@ Embeddings

 Creating embeddings of word, sentences, or paragraphs is a typical use case around the interaction with LLMs.

-The standalone usage results in a :class:`Symfony\\AI\\Store\\Vector` instance::
+The standalone usage results in a :class:`Symfony\\AI\\Platform\\Vector\\Vector` instance::

    use Symfony\AI\Platform\Bridge\OpenAi\Embeddings;

@@ -677,7 +663,7 @@ Cached Platform Calls
 Thanks to Symfony's Cache component, platform calls can be cached to reduce calls and resources consumption::

    use Symfony\AI\Agent\Agent;
-    use Symfony\AI\Platform\Bridge\Cache\CachedPlatform;
+    use Symfony\AI\Platform\Bridge\Cache\CachePlatform;
    use Symfony\AI\Platform\Bridge\OpenAi\PlatformFactory;
    use Symfony\AI\Platform\Message\Message;
    use Symfony\AI\Platform\Message\MessageBag;
@@ -686,13 +672,13 @@ Thanks to Symfony's Cache component, platform calls can be cached to reduce call
    use Symfony\Component\HttpClient\HttpClient;

    $platform = PlatformFactory::create($apiKey, HttpClient::create());
-    $cachedPlatform = new CachedPlatform($platform, cache: new TagAwareAdapter(new ArrayAdapter()));
+    $cachePlatform = new CachePlatform($platform, cache: new TagAwareAdapter(new ArrayAdapter()));

-    $firstResult = $cachedPlatform->invoke('gpt-4o-mini', new MessageBag(Message::ofUser('What is the capital of France?')));
+    $firstResult = $cachePlatform->invoke('gpt-4o-mini', new MessageBag(Message::ofUser('What is the capital of France?')));

    echo $firstResult->getContent().\PHP_EOL;

-    $secondResult = $cachedPlatform->invoke('gpt-4o-mini', new MessageBag(Message::ofUser('What is the capital of France?')));
+    $secondResult = $cachePlatform->invoke('gpt-4o-mini', new MessageBag(Message::ofUser('What is the capital of France?')));

    echo $secondResult->getContent().\PHP_EOL;

--- a/docs/components/platform/vertexai.rst
+++ b/docs/components/platform/vertexai.rst
@@ -46,7 +46,6 @@ Configure your Google Cloud project and location:

 Basic usage example::

-    use Symfony\AI\Platform\Bridge\VertexAi\Gemini\Model;
    use Symfony\AI\Platform\Bridge\VertexAi\PlatformFactory;
    use Symfony\AI\Platform\Message\Message;
    use Symfony\AI\Platform\Message\MessageBag;
--- a/docs/components/store.rst
+++ b/docs/components/store.rst
@@ -22,15 +22,18 @@ for documents.
 Indexing
 --------

-One higher level feature is the :class:`Symfony\\AI\\Store\\Indexer`. The purpose of this service is to populate a store with documents.
+One higher level feature is the :class:`Symfony\\AI\\Store\\Indexer\\DocumentIndexer`. The purpose of this service is to populate a store with documents.
 Therefore it accepts one or multiple :class:`Symfony\\AI\\Store\\Document\\TextDocument` objects, converts them into embeddings and stores them in the
 used vector store::

    use Symfony\AI\Store\Document\TextDocument;
-    use Symfony\AI\Store\Indexer;
+    use Symfony\AI\Store\Document\Vectorizer;
+    use Symfony\AI\Store\Indexer\DocumentIndexer;
+    use Symfony\AI\Store\Indexer\DocumentProcessor;

-    $indexer = new Indexer($platform, $model, $store);
-    $document = new TextDocument('This is a sample document.');
+    $vectorizer = new Vectorizer($platform, $model);
+    $indexer = new DocumentIndexer(new DocumentProcessor($vectorizer, $store));
+    $document = new TextDocument('id-1', 'This is a sample document.');
    $indexer->index($document);

 You can find more advanced usage in combination with an Agent using the store for RAG in the examples folder.
--- a/docs/components/store/local.rst
+++ b/docs/components/store/local.rst
@@ -14,10 +14,11 @@ InMemoryStore
 Stores vectors in a PHP array. Data is not persisted and is lost when the PHP process ends::

    use Symfony\AI\Store\InMemory\Store;
+    use Symfony\AI\Store\Query\VectorQuery;

    $store = new Store();
    $store->add([$document1, $document2]);
-    $results = $store->query($vector);
+    $results = $store->query(new VectorQuery($vector));

 CacheStore
 ----------
@@ -30,7 +31,7 @@ Stores vectors using a PSR-6 cache implementation. Persistence depends on the ca
    $cache = new FilesystemAdapter();
    $store = new Store($cache);
    $store->add([$document1, $document2]);
-    $results = $store->query($vector);
+    $results = $store->query(new VectorQuery($vector));

 Distance Strategies
 -------------------
@@ -70,7 +71,7 @@ candidates are kept, reducing peak memory from O(N) to O(maxItems + batchSize)::
    $store = new Store($calculator);

    // Batch processing is activated when both batchSize and maxItems are set
-    $results = $store->query($vector, [
+    $results = $store->query($vectorQuery, [
        'maxItems' => 10,
    ]);

@@ -87,34 +88,34 @@ Both stores support filtering search results based on document metadata using a

    use Symfony\AI\Store\Document\VectorDocument;

-    $results = $store->query($vector, [
-        'filter' => fn(VectorDocument $doc) => $doc->metadata['category'] === 'products',
+    $results = $store->query($vectorQuery, [
+        'filter' => fn(VectorDocument $doc) => $doc->getMetadata()['category'] === 'products',
    ]);

 You can combine multiple conditions::

-    $results = $store->query($vector, [
+    $results = $store->query($vectorQuery, [
        'filter' => fn(VectorDocument $doc) =>
-            $doc->metadata['price'] <= 100
-            && $doc->metadata['stock'] > 0
-            && $doc->metadata['enabled'] === true,
+            $doc->getMetadata()['price'] <= 100
+            && $doc->getMetadata()['stock'] > 0
+            && $doc->getMetadata()['enabled'] === true,
        'maxItems' => 10,
    ]);

 Filter nested metadata::

-    $results = $store->query($vector, [
+    $results = $store->query($vectorQuery, [
        'filter' => fn(VectorDocument $doc) =>
-            $doc->metadata['options']['size'] === 'S'
-            && $doc->metadata['options']['color'] === 'blue',
+            $doc->getMetadata()['options']['size'] === 'S'
+            && $doc->getMetadata()['options']['color'] === 'blue',
    ]);

 Use array functions for complex filtering::

    $allowedBrands = ['Nike', 'Adidas', 'Puma'];
-    $results = $store->query($vector, [
+    $results = $store->query($vectorQuery, [
        'filter' => fn(VectorDocument $doc) =>
-            \in_array($doc->metadata['brand'] ?? '', $allowedBrands, true),
+            \in_array($doc->getMetadata()['brand'] ?? '', $allowedBrands, true),
    ]);

 .. note::
@@ -131,7 +132,7 @@ Both stores support the following query options:

 Example combining both options::

-    $results = $store->query($vector, [
+    $results = $store->query($vectorQuery, [
        'maxItems' => 5,
-        'filter' => fn(VectorDocument $doc) => $doc->metadata['active'] === true,
+        'filter' => fn(VectorDocument $doc) => $doc->getMetadata()['active'] === true,
    ]);
--- a/docs/components/store/s3-vectors.rst
+++ b/docs/components/store/s3-vectors.rst
@@ -81,9 +81,10 @@ Query Similar Vectors
 ::

    use Symfony\AI\Platform\Vector\Vector;
+    use Symfony\AI\Store\Query\VectorQuery;

    $results = $store->query(
-        vector: new Vector([0.1, 0.2, 0.3, ...]),
+        query: new VectorQuery(new Vector([0.1, 0.2, 0.3, ...])),
        options: [
            'topK' => 5,
            'filter' => ['category' => 'documentation'],
@@ -91,7 +92,7 @@ Query Similar Vectors
    );

    foreach ($results as $result) {
-        echo $result->metadata['title'] . ' (score: ' . $result->score . ')' . PHP_EOL;
+        echo $result->getMetadata()['title'] . ' (score: ' . $result->getScore() . ')' . PHP_EOL;
    }

 Remove Documents
--- a/docs/components/store/sqlite.rst
+++ b/docs/components/store/sqlite.rst
@@ -94,7 +94,7 @@ The SQLite store supports filtering search results based on document metadata us
    use Symfony\AI\Store\Document\VectorDocument;

    $results = $store->query($vectorQuery, [
-        'filter' => fn(VectorDocument $doc) => $doc->metadata['category'] === 'products',
+        'filter' => fn(VectorDocument $doc) => $doc->getMetadata()['category'] === 'products',
    ]);

 Query Options
@@ -109,5 +109,5 @@ Example combining both options::

    $results = $store->query($vectorQuery, [
        'maxItems' => 5,
-        'filter' => fn(VectorDocument $doc) => $doc->metadata['active'] === true,
+        'filter' => fn(VectorDocument $doc) => $doc->getMetadata()['active'] === true,
    ]);
--- a/docs/components/store/supabase.rst
+++ b/docs/components/store/supabase.rst
@@ -152,15 +152,17 @@ Querying Documents

    $queryVector = new Vector([0.1, 0.2, 0.3, /* ... 768 dimensions */]);

-    $results = $store->query($queryVector, [
+    use Symfony\AI\Store\Query\VectorQuery;
+
+    $results = $store->query(new VectorQuery($queryVector), [
        'max_items' => 10,
        'min_score' => 0.7
    ]);

    foreach ($results as $document) {
-        echo "ID: " . $document->id . "\n";
-        echo "Score: " . $document->score . "\n";
-        echo "Metadata: " . json_encode($document->metadata->getArrayCopy()) . "\n";
+        echo "ID: " . $document->getId() . "\n";
+        echo "Score: " . $document->getScore() . "\n";
+        echo "Metadata: " . json_encode($document->getMetadata()->getArrayCopy()) . "\n";
    }

 Customization
--- a/docs/cookbook/rag-implementation.rst
+++ b/docs/cookbook/rag-implementation.rst
@@ -168,13 +168,11 @@ Vector Store Selection

 For production environments, use persistent vector stores like ChromaDB::

+    use Codewithkyrian\ChromaDB\ChromaDB;
    use Symfony\AI\Store\Bridge\ChromaDb\Store;

-    $store = new Store(
-        $httpClient,
-        'http://localhost:8000',
-        'my_collection'
-    );
+    $client = ChromaDB::factory()->connect();
+    $store = new Store($client, 'my_collection');

 ChromaDB is a great choice for production RAG systems as it provides: