From f47a6080e6fd2f6d731c6f077739a6635bc6db75 Mon Sep 17 00:00:00 2001
From: Michael Barlow <25936840+Michael-JB@users.noreply.github.com>
Date: Fri, 23 Aug 2024 09:20:48 +0200
Subject: [PATCH] docs: Use cosine similarity in quickstart example

- Previously, the quickstart example used dot product distance. This
  didn't make much sense as the vectors in the example were not
  normalised. It also led to some weird-looking query results. This
  commit changes the examples to use cosine similarity.
- While I was in the area, I prefixed '/' to the HTTP request paths so
  that they're all correct and consistent.
---
 .../MdxPages/FilteringClauses.mdx                  |  6 +++---
 .../InteractiveTutorial/MdxPages/Quickstart.mdx    | 14 +++++++-------
 2 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/src/components/InteractiveTutorial/MdxPages/FilteringClauses.mdx b/src/components/InteractiveTutorial/MdxPages/FilteringClauses.mdx
index a3e30fd0..0737b4be 100644
--- a/src/components/InteractiveTutorial/MdxPages/FilteringClauses.mdx
+++ b/src/components/InteractiveTutorial/MdxPages/FilteringClauses.mdx
@@ -21,11 +21,11 @@ Before we start to practice with filtering conditions, let's create some datapoi
 1. Create a collection:
 
 ``` json withRunButton="true"
-PUT collections/demo
+PUT /collections/demo
 {
   "vectors": {
-  "size": 4,
-  "distance": "Dot"
+    "size": 4,
+    "distance": "Cosine"
   }
 }
 ```
diff --git a/src/components/InteractiveTutorial/MdxPages/Quickstart.mdx b/src/components/InteractiveTutorial/MdxPages/Quickstart.mdx
index 2e4f3eb4..1f2d7496 100644
--- a/src/components/InteractiveTutorial/MdxPages/Quickstart.mdx
+++ b/src/components/InteractiveTutorial/MdxPages/Quickstart.mdx
@@ -8,14 +8,14 @@ In this tutorial, you will create a collection, load data into it and run a basi
 
 ## Create a collection
 
-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.
+First, create a collection to store vector data. Let’s name it `test_collection`. This collection will use cosine similarity to determine the distance between vectors. Added vectors will have 4 dimensions.
 
 ```json withRunButton=true
-PUT collections/test_collection
+PUT /collections/test_collection
 {
   "vectors": {
     "size": 4,
-    "distance": "Dot"
+    "distance": "Cosine"
   }
 }
 ```
@@ -25,7 +25,7 @@ PUT collections/test_collection
 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
+PUT /collections/test_collection/points
 {
   "points": [
     {
@@ -71,7 +71,7 @@ We need to ask a question in vector form:
 `[0.2, 0.1, 0.9, 0.7]`
 
 ```json withRunButton=true
-POST collections/test_collection/points/search
+POST /collections/test_collection/points/search
 {
   "vector": [0.2, 0.1, 0.9, 0.7],
   "limit": 3,
@@ -87,7 +87,7 @@ See [payload and vector in the result](https://qdrant.tech/documentation/concept
 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
+POST /collections/test_collection/points/search
 {
   "vector": [0.2, 0.1, 0.9, 0.7],
   "filter": {
@@ -107,4 +107,4 @@ That’s it! You have just performed a vector search. You loaded vectors into a
 
 ## Next steps
 
-In the next section, you will learn how to create complex filter conditions and how to use them in your queries.
\ No newline at end of file
+In the next section, you will learn how to create complex filter conditions and how to use them in your queries.