minor #1187 [Docs] Fix incorrect class references in documentation (OskarStark)

This PR was merged into the main branch.

Discussion
----------

[Docs] Fix incorrect class references in documentation

| Q             | A
| ------------- | ---
| Bug fix?      | no
| New feature?  | no
| Docs?         | yes
| Issues        | --
| License       | MIT

Commits
-------

f688765 [Docs] Fix incorrect class references in documentation

Author: OskarStark

docs/bundles/ai-bundle.rst

@@ -868,7 +868,7 @@ To inject only specific tools, list them in the configuration:
         agent:
             my_agent:
                 tools:
-                    - 'Symfony\AI\Agent\Toolbox\Tool\SimilaritySearch'
+                    - 'Symfony\AI\Agent\Bridge\SimilaritySearch\SimilaritySearch'
 
 To restrict the access to a tool, you can use the :class:`Symfony\\AI\\Agent\\Attribute\\IsGrantedTool` attribute, which
 works similar to :class:`Symfony\\Component\\Security\\Http\\Attribute\\IsGranted` attribute in `symfony/security-http`. For this to work,

docs/components/chat.rst

@@ -66,8 +66,8 @@ for adding messages to the message store, and returning the messages from a stor
 
 This leads to a store implementing two methods::
 
+    use Symfony\AI\Chat\MessageStoreInterface;
     use Symfony\AI\Platform\Message\MessageBag;
-    use Symfony\AI\Store\MessageStoreInterface;
 
     class MyCustomStore implements MessageStoreInterface
     {
@@ -91,8 +91,8 @@ to setup and drop the store.
 
 This leads to a store implementing two methods::
 
-    use Symfony\AI\Store\ManagedStoreInterface;
-    use Symfony\AI\Store\MessageStoreInterface;
+    use Symfony\AI\Chat\ManagedStoreInterface;
+    use Symfony\AI\Chat\MessageStoreInterface;
 
     class MyCustomStore implements ManagedStoreInterface, MessageStoreInterface
     {

docs/components/store.rst

@@ -139,9 +139,9 @@ for adding vectorized documents to the store, and querying the store for documen
 
 This leads to a store implementing two methods::
 
+    use Symfony\AI\Platform\Vector\Vector;
+    use Symfony\AI\Store\Document\VectorDocument;
     use Symfony\AI\Store\StoreInterface;
-    use Symfony\AI\Store\Vector;
-    use Symfony\AI\Store\VectorDocument;
 
     class MyStore implements StoreInterface
     {
@@ -150,7 +150,7 @@ This leads to a store implementing two methods::
             // Implementation to add a document to the store
         }
 
-        public function query(Vector $vector, array $options = []): array
+        public function query(Vector $vector, array $options = []): iterable
         {
             // Implementation to query the store for documents
             return $documents;

docs/components/store/local.rst

@@ -13,9 +13,9 @@ InMemoryStore
 
 Stores vectors in a PHP array. Data is not persisted and is lost when the PHP process ends::
 
-    use Symfony\AI\Store\Bridge\Local\InMemoryStore;
+    use Symfony\AI\Store\InMemory\Store;
 
-    $store = new InMemoryStore();
+    $store = new Store();
     $store->add($document1, $document2);
     $results = $store->query($vector);
 
@@ -24,11 +24,11 @@ CacheStore
 
 Stores vectors using a PSR-6 cache implementation. Persistence depends on the cache adapter used::
 
-    use Symfony\AI\Store\Bridge\Local\CacheStore;
+    use Symfony\AI\Store\Bridge\Cache\Store;
     use Symfony\Component\Cache\Adapter\FilesystemAdapter;
 
     $cache = new FilesystemAdapter();
-    $store = new CacheStore($cache);
+    $store = new Store($cache);
     $store->add($document1, $document2);
     $results = $store->query($vector);
 
@@ -39,9 +39,10 @@ Both stores support different distance calculation strategies::
 
     use Symfony\AI\Store\Distance\DistanceCalculator;
     use Symfony\AI\Store\Distance\DistanceStrategy;
+    use Symfony\AI\Store\InMemory\Store;
 
     $calculator = new DistanceCalculator(DistanceStrategy::COSINE_DISTANCE);
-    $store = new InMemoryStore($calculator);
+    $store = new Store($calculator);
 
 Available strategies:
 

docs/cookbook/rag-implementation.rst

@@ -49,9 +49,9 @@ Step 1: Initialize the Vector Store
 
 First, create a store to hold your vector embeddings::
 
-    use Symfony\AI\Store\Bridge\Local\InMemoryStore;
+    use Symfony\AI\Store\InMemory\Store;
 
-    $store = new InMemoryStore();
+    $store = new Store();
 
 For production use, consider using persistent stores like ChromaDB, Pinecone, or MongoDB Atlas.
 
@@ -110,8 +110,8 @@ Step 4: Configure Similarity Search Tool
 
 Create a tool that performs semantic search on your vector store::
 
+    use Symfony\AI\Agent\Bridge\SimilaritySearch\SimilaritySearch;
     use Symfony\AI\Agent\Toolbox\AgentProcessor;
-    use Symfony\AI\Agent\Toolbox\Tool\SimilaritySearch;
     use Symfony\AI\Agent\Toolbox\Toolbox;
 
     $similaritySearch = new SimilaritySearch($vectorizer, $store);
@@ -169,9 +169,9 @@ Vector Store Selection
 
 For production environments, use persistent vector stores like ChromaDB::
 
-    use Symfony\AI\Store\Bridge\ChromaDB\ChromaStore;
+    use Symfony\AI\Store\Bridge\ChromaDb\Store;
 
-    $store = new ChromaStore(
+    $store = new Store(
         $httpClient,
         'http://localhost:8000',
         'my_collection'
@@ -305,7 +305,7 @@ When using the AI Bundle, configure RAG with YAML:
                 prompt:
                     text: 'Answer questions using only the SimilaritySearch tool. If you cannot find relevant information, say so.'
                 tools:
-                    - 'Symfony\AI\Agent\Toolbox\Tool\SimilaritySearch'
+                    - 'Symfony\AI\Agent\Bridge\SimilaritySearch\SimilaritySearch'
 
 Then use the indexer command to populate your store: