Lang switcher (#7)

* language switcher for documentation pages

* some cleanup and an example of usage

* fix highlight elements ordering

* fix for unexpected behavior

* styles fix

* changed tag

* copy button for code blocks in documentation

* warning and info styled elements for documentation

* docs auto-sync

* fixed 1px extra padding and prevented tabs generation when there is only one language

* docs auto-sync

* fix

* docs auto-sync

* moved css for information aside blocks to the article file

* fix

Co-authored-by: Andrey Vasnetsov <andrey@vasnetsov.com>
Co-authored-by: qdrant <qdrant@users.noreply.github.com>

qdrant-landing/content/documentation/collections.md

@@ -24,7 +24,7 @@ These settings can be changed at any time by a corresponding request.
 
 With REST API
 
-```
+``` http
 PUT /collections/example_collection
 
 {
@@ -34,6 +34,21 @@ PUT /collections/example_collection
 }
 ```
 
+``` python
+from qdrant_client import QdrantClient
+from qdrant_openapi_client.models.models import CreateCollection, Distance
+   
+client = QdrantClient(host="localhost", port=6333)
+
+client.http.collections_api.create_collection(
+   name="example_collection",
+   create_collection=CreateCollection(
+      distance=Distance.COSINE,
+      vector_size=300,
+   )
+)
+```
+
 In addition to the required options, you can also specify custom values for the following collection options:
 
 - `hnsw_config`
@@ -178,4 +193,4 @@ POST /collections/aliases
         }
     ]
 }
-```
+```

qdrant-landing/content/documentation/search.md

@@ -145,7 +145,7 @@ POST /collections/{collection_name}/points/search
 
 ## Recommendation API
 
-**DISCLAIMER**: Negative vectors is an experimental functionality that is not guaranteed to work with all king of embeddings.
+<aside role="alert">Negative vectors is an experimental functionality that is not guaranteed to work with all king of embeddings.</aside>
 
 In addition to the regular search, Qdrant also allows you to search based on multiple already stored data collection vectors.
 This API allows using vector search without using a neural network encoder for already encoded objects.