Updates

developers/academy/starter_text_data/101_start_wcs/_snippets/30_connect.py

@@ -1,7 +1,7 @@
 import os
 
 your_wcs_url = os.getenv("WCS_DEMO_URL")
-your_wcs_key = os.getenv("WCS_DEMO_RO_KEY")
+your_wcs_key = os.getenv("WCS_DEMO_ADMIN_KEY")
 
 # WCSInstantiation
 import weaviate

developers/academy/starter_text_data/102_text_collections/20_create_collection.mdx

@@ -2,83 +2,77 @@
 title: Create a collection
 ---
 
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+import FilteredTextBlock from '@site/src/components/Documentation/FilteredTextBlock';
+import PyCode from '!!raw-loader!./_snippets/20_create_collection.py';
+
 ## <i class="fa-solid fa-square-chevron-right"></i> Background
 
 Weaviate stores data in "collections". A collection is a set of objects that share the same data structure. In our movie database, we might have a collection of movies, a collection of actors, and a collection of reviews.
 
 Here we will create a collection of movies.
 
-### <i class="fa-solid fa-code"></i> Collection creation
-
-
-### <i class="fa-solid fa-chalkboard"></i> Data structure
+## <i class="fa-solid fa-square-chevron-right"></i> Collection creation
 
-Each collection
+### <i class="fa-solid fa-code"></i> Code
 
+This example creates a collection for the movie data:
 
-Some text
+<FilteredTextBlock
+  text={PyCode}
+  startMarker="# CreateMovieCollection"
+  endMarker="# END CreateMovieCollection"
+  language="py"
+/>
 
-### <i class="fa-solid fa-chalkboard"></i> Theory subhead
-### <i class="fa-solid fa-code"></i> Practical subhead
+Each collection definition must have a name. Then, you can define additional parameters like we've done in this example. Let's break it down:
 
-Some text
+### <i class="fa-solid fa-chalkboard"></i> Properties
 
-## <i class="fa-solid fa-square-chevron-right"></i> TOP LEVEL HEADING
+Properties are the object attributes that you want to store in the collection. Each property has a name and a data type.
 
-Some text
+In our movie database, we have properties like `title`, `release_date` and `genre_ids`, with data types like `TEXT` (string), `DATE` (date), or `INT` (integer). It's also possible to have arrays of integers, like we have with `genre_ids`.
 
-### <i class="fa-solid fa-chalkboard"></i> Theory subhead
-### <i class="fa-solid fa-code"></i> Practical subhead
+### <i class="fa-solid fa-chalkboard"></i> Vectorizer configuration
 
-Some text
+If you do not specify the vector yourself, Weaviate will use a specified vectorizer to generate vector embeddings from your data.
 
-### <i class="fa-solid fa-chalkboard"></i> Theory subhead
-### <i class="fa-solid fa-code"></i> Practical subhead
+In this code example, we specify the `text2vec-openai` module with default options.
 
-Some text
+<FilteredTextBlock
+  text={PyCode}
+  startMarker="# Define the vectorizer module"
+  endMarker="# Define the generative module"
+  language="py"
+/>
 
+### <i class="fa-solid fa-chalkboard"></i> Generative configuration
 
+If you wish to use your collection with a generative model (e.g. a large language model), you must specify the generative module.
 
-## <i class="fa-solid fa-square-chevron-right"></i> Review
+In this code example, we specify the `openai` module (`generative-openai` is the full name) with default options.
 
-<Quiz questions={varName} />
+<FilteredTextBlock
+  text={PyCode}
+  startMarker="# Define the generative module"
+  endMarker="# END generativeDefinition"
+  language="py"
+/>
 
-Any quiz questions
+### <i class="fa-solid fa-code"></i> Python classes
 
-### <i class="fa-solid fa-pen-to-square"></i> Review exercise
+The code example makes use of classes such as `Property`, `DataType` and `Configure`. They are defined in the `weaviate.classes.config` submodule and are used to define the collection.
 
-:::note <i class="fa-solid fa-square-terminal"></i> Exercise
-Try out ...
-:::
+For convenience, we import the submodule as `wc` and use classes from it.
 
-### <i class="fa-solid fa-lightbulb-on"></i> Key takeaways
-
-:::info
-Add summary
-:::
+<FilteredTextBlock
+  text={PyCode}
+  startMarker="# SubmoduleImport"
+  endMarker="# END SubmoduleImport"
+  language="py"
+/>
 
 import { GiscusDocComment } from '/src/components/GiscusComment';
 
 <GiscusDocComment />
-
-import Quiz from '/src/components/Academy/quiz.js'
-const varName = [{
-  questionText: 'questionText',
-  answerOptions: [
-    {
-      answerText: 'answerOne',
-      isCorrect: false,
-      feedback: 'feedbackOne',
-    },
-    {
-      answerText: 'answerTwo',
-      isCorrect: false,
-      feedback: 'feedbackTwo',
-    },
-    {
-      answerText: 'answerThree',
-      isCorrect: false,
-      feedback: 'feedbackThree',
-    },
-  ]
-}];

developers/academy/starter_text_data/102_text_collections/30_import_data.mdx

@@ -2,13 +2,23 @@
 title: Import data
 ---
 
-import imageUrl from '../../tmp_images/academy_placeholder.jpg';
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+import FilteredTextBlock from '@site/src/components/Documentation/FilteredTextBlock';
+import PyCode from '!!raw-loader!./_snippets/30_import_data.py';
 
-<img src={imageUrl} alt="Image alt" width="75%"/>
+## <i class="fa-solid fa-square-chevron-right"></i> Collection creation
 
-## <i class="fa-solid fa-square-chevron-right"></i> TOP LEVEL HEADING
+### <i class="fa-solid fa-code"></i> Code
 
-Some text
+This example imports the movie data into our collection.
+
+<FilteredTextBlock
+  text={PyCode}
+  startMarker="# BatchImportData"
+  endMarker="# END BatchImportData"
+  language="py"
+/>
 
 ### <i class="fa-solid fa-chalkboard"></i> Theory subhead
 ### <i class="fa-solid fa-code"></i> Practical subhead

developers/academy/starter_text_data/102_text_collections/_snippets/20_create_collection.py

@@ -0,0 +1,48 @@
+import os
+
+your_wcs_url = os.getenv("WCS_DEMO_URL")
+your_wcs_key = os.getenv("WCS_DEMO_ADMIN_KEY")
+
+# CreateMovieCollection
+import weaviate
+# CreateMovieCollection  # SubmoduleImport
+import weaviate.classes.config as wc
+# CreateMovieCollection  # END SubmoduleImport
+
+client = weaviate.connect_to_wcs(
+    cluster_url=your_wcs_url,  # Replace with your WCS URL
+    auth_credentials=weaviate.auth.AuthApiKey(your_wcs_key)  # Replace with your WCS key
+)
+
+# END CreateMovieCollection
+
+client.close()
+
+# Actual instantiation
+client = weaviate.connect_to_local()
+
+client.collections.delete("Movie")
+
+# CreateMovieCollection
+try:
+    client.collections.create(
+        name="Movie",
+        properties=[
+            wc.Property(name="title", data_type=wc.DataType.TEXT),
+            wc.Property(name="overview", data_type=wc.DataType.TEXT),
+            wc.Property(name="vote_average", data_type=wc.DataType.NUMBER),
+            wc.Property(name="genre_ids", data_type=wc.DataType.INT_ARRAY),
+            wc.Property(name="release_date", data_type=wc.DataType.DATE),
+            wc.Property(name="tmdb_id", data_type=wc.DataType.INT),
+        ],
+        # Define the vectorizer module
+        vectorizer_config=wc.Configure.Vectorizer.text2vec_openai(),
+        # Define the generative module
+        generative_config=wc.Configure.Generative.openai()
+        # END generativeDefinition  # CreateMovieCollection
+    )
+
+finally:
+    client.close()  # Release resources
+# END CreateMovieCollection
+

developers/academy/starter_text_data/102_text_collections/_snippets/30_import_data.py

@@ -0,0 +1,51 @@
+import os
+
+your_wcs_url = os.getenv("WCS_DEMO_URL")
+your_wcs_key = os.getenv("WCS_DEMO_ADMIN_KEY")
+
+# BatchImportData
+import weaviate
+import pandas as pd
+import requests
+import datetime
+from weaviate.util import generate_uuid5
+
+client = weaviate.connect_to_wcs(
+    cluster_url=your_wcs_url,  # Replace with your WCS URL
+    auth_credentials=weaviate.auth.AuthApiKey(your_wcs_key)  # Replace with your WCS key
+)
+
+# END BatchImportData
+
+client.close()
+
+# Actual instantiation
+client = weaviate.connect_to_local()
+client.connect()
+
+# BatchImportData
+data_url = "https://raw.githubusercontent.com/weaviate-tutorials/edu-datasets/main/movies_data_1990_2024.json"
+resp = requests.get(data_url)
+df = pd.DataFrame(resp.json())
+
+try:
+    movies = client.collections.get("Movie")
+    with movies.batch.dynamic() as batch:
+        for i, movie in df[:10].iterrows():
+            release_date = datetime.datetime.strptime(movie["release_date"], "%Y-%m-%d")
+            movie_obj = {
+                "title": movie["title"],
+                "overview": movie["overview"],
+                "vote_average": movie["vote_average"],
+                "genre_ids": movie["genre_ids"],
+                "release_date": release_date,
+                "tmdb_id": movie["id"]
+            }
+            batch.add_object(
+                properties=movie_obj,
+                uuid=generate_uuid5(movie["id"])
+            )
+
+finally:
+    client.close()
+