Added samples, benchmarks and docs for nox format. (#556)

* Added samples for nox format.

Signed-off-by: dblock <[email protected]>

* Added space after #!/usr/bin/env python.

Signed-off-by: dblock <[email protected]>

* Added benchmarks and docs.

Signed-off-by: dblock <[email protected]>

---------

Signed-off-by: dblock <[email protected]>

samples/knn/knn-boolean-filter.py

@@ -6,6 +6,10 @@
 # The OpenSearch Contributors require contributions made to
 # this file be licensed under the Apache-2.0 license or a
 # compatible open source license.
+#
+# Modifications Copyright OpenSearch Contributors. See
+# GitHub history for details.
+
 
 import os
 import random
@@ -14,19 +18,16 @@ from opensearchpy import OpenSearch, helpers
 
 # connect to an instance of OpenSearch
 
-host = os.getenv('HOST', default='localhost')
-port = int(os.getenv('PORT', 9200))
-auth = (
-    os.getenv('USERNAME', 'admin'), 
-    os.getenv('PASSWORD', 'admin')
-)
+host = os.getenv("HOST", default="localhost")
+port = int(os.getenv("PORT", 9200))
+auth = (os.getenv("USERNAME", "admin"), os.getenv("PASSWORD", "admin"))
 
 client = OpenSearch(
-    hosts = [{'host': host, 'port': port}],
-    http_auth = auth,
-    use_ssl = True,
-    verify_certs = False,
-    ssl_show_warn = False
+    hosts=[{"host": host, "port": port}],
+    http_auth=auth,
+    use_ssl=True,
+    verify_certs=False,
+    ssl_show_warn=False,
 )
 
 # check whether an index exists
@@ -34,38 +35,34 @@ index_name = "my-index"
 dimensions = 5
 
 if not client.indices.exists(index_name):
-    client.indices.create(index_name, 
+    client.indices.create(
+        index_name,
         body={
-            "settings":{
-                "index.knn": True
-            },
-            "mappings":{
+            "settings": {"index.knn": True},
+            "mappings": {
                 "properties": {
-                    "values": {
-                        "type": "knn_vector", 
-                        "dimension": dimensions
-                    },
+                    "values": {"type": "knn_vector", "dimension": dimensions},
                 }
-            }
-        }
+            },
+        },
     )
 
 # index data
 vectors = []
-genres = ['fiction', 'drama', 'romance']
+genres = ["fiction", "drama", "romance"]
 for i in range(3000):
     vec = []
-    for j in range(dimensions): 
-        vec.append(round(random.uniform(0, 1), 2)) 
-  
-    vectors.append({
-        "_index": index_name,
-        "_id": i,
-        "values": vec,
-        "metadata": {
-            "genre": random.choice(genres)
+    for j in range(dimensions):
+        vec.append(round(random.uniform(0, 1), 2))
+
+    vectors.append(
+        {
+            "_index": index_name,
+            "_id": i,
+            "values": vec,
+            "metadata": {"genre": random.choice(genres)},
         }
-    })
+    )
 
 # bulk index
 helpers.bulk(client, vectors)
@@ -75,30 +72,15 @@ client.indices.refresh(index=index_name)
 # search
 genre = random.choice(genres)
 vec = []
-for j in range(dimensions): 
-    vec.append(round(random.uniform(0, 1), 2)) 
+for j in range(dimensions):
+    vec.append(round(random.uniform(0, 1), 2))
 print(f"Searching for {vec} with the '{genre}' genre ...")
 
 search_query = {
     "query": {
         "bool": {
-            "filter": {
-                "bool": {
-                    "must": [{
-                        "term": {
-                            "metadata.genre": genre
-                        }
-                    }]
-                }
-            },
-            "must": {
-                "knn": {
-                    "values": {
-                        "vector": vec, 
-                        "k": 5
-                    }
-                }
-            }
+            "filter": {"bool": {"must": [{"term": {"metadata.genre": genre}}]}},
+            "must": {"knn": {"values": {"vector": vec, "k": 5}}},
         }
     }
 }