fix wording in Quickstart and Filtering tutorials (#194)

* update interactive tutorial for language and links

* fix two words

* fix filtering

src/components/InteractiveTutorial/MdxPages/FilteringClauses.mdx

@@ -2,18 +2,16 @@ export const title = "Filtering Clauses"
 
 # {title}
 
-<Alert severity="info">Click **RUN** button at code blocks to see a result of the query in the right part of the screen.<br/>Click inside a code block to edit it.</Alert>
-<br/>
+<Alert severity="info">Click **RUN** to send the API request. Your response will be on the right. <br/>You may edit any code block and rerun the request.</Alert>
 
-Qdrant support filtering of collections combining condition and clauses.
-In this tutorial you will learn how to filter collections using **filtering clauses**.
+Qdrant lets you to filter collections by combining **conditions** and **clauses**. In this tutorial, you will learn how to filter collections using filtering clauses.
 
 Clauses are different logical operations, such as OR, AND, and NOT.
-Clauses can be recursively nested into each other so that you can reproduce an arbitrary boolean expression.
+You can nest them inside each other to create any boolean expression.
 
-Let's start with creating a new collection and populating it with points.
+Start by creating a new collection and adding vectors.
 
-## Set up for this tutorial
+## Setup
 
 Before we start to practice with filtering conditions, let's create some datapoints to work with.
 
@@ -32,7 +30,7 @@ PUT collections/demo
 }
 ```
 
-2. And add points to it:
+2. Add vectors:
 
 ``` json withRunButton="true"
 PUT /collections/demo/points
@@ -68,7 +66,7 @@ PUT /collections/demo/points
 ```
 </details>
 
-Take a note of what data we put into points' `payload` field.
+**Note:** Take a good look at each point's `payload` field. You will need to add a filter using this payload.
 
 ## Must
 
@@ -142,9 +140,9 @@ POST /collections/demo/points/scroll
 }
 ```
 
-## Clauses combination
+## Combination
 
-It is also possible to use several clauses simultaneously:
+You can also use join different clauses:
 
 ``` json withRunButton="true"
 POST /collections/demo/points/scroll

src/components/InteractiveTutorial/MdxPages/Index.mdx

@@ -11,8 +11,9 @@ You will use the [Qdrant REST API](https://api.qdrant.tech) to interact with sam
 |[Quickstart](#/tutorial/quickstart)|Create a collection, upsert vectors & run a search.|
 |[Payload Filtering](#/tutorial/filtering-clauses)|Refine search results based on payload conditions.|
 
+
 ## Next steps:
 
 Once you are ready to leave this sandbox tutorial, you can try the complete [REST API](https://api.qdrant.tech) from the **Console**. All your resources will be persisted. 
 
-You can use one of our [language-specific Clients](https://qdrant.tech/documentation/interfaces/) to build your applications.
+To begin building a prototype application, you should [setup Qdrant on Docker](https://qdrant.tech/documentation/quick-start/) and start using one of our [language-specific Clients](https://qdrant.tech/documentation/interfaces/).

src/components/InteractiveTutorial/MdxPages/Quickstart.mdx

@@ -2,13 +2,13 @@ export const title = 'Quickstart';
 
 # {title}
 
-In this short example, you will create a Collection, load data into it and run a basic search query.
+In this tutorial, you will create a collection, load data into it and run a basic search query.
 
-<Alert severity="info">Click **RUN** button at code blocks to see a result of the query in the right part of the screen.<br/>Click inside a code block to edit it.</Alert>
+<Alert severity="info">Click **RUN** to send the API request. Your response will be on the right. <br/>You may edit any code block and rerun the request.</Alert>
 
 ## Create a collection
 
-You will be storing all of your vector data in a Qdrant collection. Let's call it `test_collection`. This collection will be using a dot product distance metric to compare vectors.
+First, create a collection to store vector data. Let’s name it `test_collection`. This collection will use the dot product distance metric to determine similarity between vectors. Added vectors will have 4 dimensions.
 
 ```json withRunButton=true
 PUT collections/test_collection
@@ -22,7 +22,7 @@ PUT collections/test_collection
 
 ## Add vectors
 
-Let's now add a few vectors with a payload. Payloads are other data you want to associate with the vector:
+Now, you need to add a few vectors. For each vector, you will specify a JSON payload. A payload is metadata that describes each vector, such as `city`.
 
 ```json withRunButton=true
 PUT collections/test_collection/points
@@ -64,7 +64,8 @@ PUT collections/test_collection/points
 
 ## Run a query
 
-Let's ask a basic question - Which of our stored vectors are most similar to the query vector `[0.2, 0.1, 0.9, 0.7]`?
+We need to ask a question in vector form: 
+</br>*Which of our stored vectors are most similar to the query vector ?* </br>`[0.2, 0.1, 0.9, 0.7]`
 
 ```json withRunButton=true
 POST collections/test_collection/points/search
@@ -75,12 +76,12 @@ POST collections/test_collection/points/search
 }
 ```
 
-The results are returned in decreasing similarity order. Note that payload and vector data is missing in these results by default.
+Qdrant will go through all available data and return results in order of decreasing similarity. Note that payload and vector data is missing in these results by default.
 See [payload and vector in the result](https://qdrant.tech/documentation/concepts/search#payload-and-vector-in-the-result) on how to enable it.
 
 ## Add a filter
 
-We can narrow down the results further by filtering by payload. Let's find the closest results that include "London".
+You can narrow down the results further by setting conditions on the payload. Let's filter the closest results that include the city of "London".
 
 ```json withRunButton=true
 POST collections/test_collection/points/search
@@ -99,7 +100,7 @@ POST collections/test_collection/points/search
 }
 ```
 
-You have just conducted vector search. You loaded vectors into a database and queried the database with a vector of your own. Qdrant found the closest results and presented you with a similarity score.
+That’s it! You have just performed a vector search. You loaded vectors into a database and queried the database with your own vector. Qdrant found the closest results and presented you with a similarity score.
 
 ## Next steps