From e7f009b920254249654ad0d020c64b8881606a86 Mon Sep 17 00:00:00 2001
From: Ivan Despot <66276597+g-despot@users.noreply.github.com>
Date: Tue, 21 Oct 2025 18:42:15 +0200
Subject: [PATCH 01/16] Update docs
---
.../quickstart.create_populate_collection.py | 59 ++
...eate_populate_collection_custom_vectors.py | 69 +++
.../code/quickstart/clients.install.new.mdx | 37 ++
.../quickstart.create_populate_collection.mdx | 88 +++
...ate_populate_collection_custom_vectors.mdx | 88 +++
.../code/quickstart/quickstart.query.rag.mdx | 107 ++--
docs/weaviate/quickstart/index.md | 551 +++---------------
src/css/custom.scss | 4 +
8 files changed, 474 insertions(+), 529 deletions(-)
create mode 100644 _includes/code/python/quickstart.create_populate_collection.py
create mode 100644 _includes/code/python/quickstart.create_populate_collection_custom_vectors.py
create mode 100644 _includes/code/quickstart/clients.install.new.mdx
create mode 100644 _includes/code/quickstart/quickstart.create_populate_collection.mdx
create mode 100644 _includes/code/quickstart/quickstart.create_populate_collection_custom_vectors.mdx
diff --git a/_includes/code/python/quickstart.create_populate_collection.py b/_includes/code/python/quickstart.create_populate_collection.py
new file mode 100644
index 00000000..b9fea1c3
--- /dev/null
+++ b/_includes/code/python/quickstart.create_populate_collection.py
@@ -0,0 +1,59 @@
+# START CreateCollection
+import weaviate
+from weaviate.classes.init import Auth
+from weaviate.classes.config import Configure, Property, DataType
+import os
+
+# Best practice: store your credentials in environment variables
+weaviate_url = os.environ["WEAVIATE_URL"]
+weaviate_api_key = os.environ["WEAVIATE_API_KEY"]
+
+# Step 1.1: Connect to your Weaviate Cloud instance
+client = weaviate.connect_to_weaviate_cloud(
+ cluster_url=weaviate_url,
+ auth_credentials=Auth.api_key(weaviate_api_key),
+)
+
+# END CreateCollection
+
+# NOT SHOWN TO THE USER - DELETE EXISTING COLLECTION
+client.collections.delete("Question")
+
+# START CreateCollection
+# Step 1.2: Create a collection
+# highlight-start
+questions = client.collections.create(
+ name="Question",
+ vector_config=Configure.Vectors.text2vec_weaviate(), # Configure the Weaviate Embeddings vectorizer
+ # You can also use auto-schema, here we define the schema manually
+ properties=[
+ Property(name="question", data_type=DataType.TEXT),
+ Property(name="answer", data_type=DataType.TEXT),
+ Property(name="category", data_type=DataType.TEXT),
+ ],
+)
+# highlight-end
+# START CreateCollection
+
+# END CreateCollection
+# fmt: off
+# START CreateCollection
+# Step 1.3: Import three objects
+data_objects = [
+ {"properties": {"question": "What is Python?", "answer": "Python is a high-level, interpreted programming language known for its simplicity and readability.", "category": "Programming"}},
+ {"properties": {"question": "What is machine learning?", "answer": "Machine learning is a subset of AI that enables systems to learn and improve from experience without being explicitly programmed.", "category": "AI"}},
+ {"properties": {"question": "What is a vector database?", "answer": "A vector database is a specialized database designed to store and query high-dimensional vectors efficiently.", "category": "Database"}},
+]
+# END CreateCollection
+# fmt: on
+# START CreateCollection
+
+questions = client.collections.use("Question")
+with questions.batch.dynamic() as batch:
+ for obj in data_objects:
+ batch.add_object(properties=obj)
+
+print(f"Imported {len(questions)} objects into the Question collection")
+
+client.close() # Free up resources
+# END CreateCollection
diff --git a/_includes/code/python/quickstart.create_populate_collection_custom_vectors.py b/_includes/code/python/quickstart.create_populate_collection_custom_vectors.py
new file mode 100644
index 00000000..a74059ec
--- /dev/null
+++ b/_includes/code/python/quickstart.create_populate_collection_custom_vectors.py
@@ -0,0 +1,69 @@
+# START CreateCollection
+import weaviate
+from weaviate.classes.init import Auth
+from weaviate.classes.config import Configure, Property, DataType
+import os
+
+# Best practice: store your credentials in environment variables
+weaviate_url = os.environ["WEAVIATE_URL"]
+weaviate_api_key = os.environ["WEAVIATE_API_KEY"]
+
+# Step 1.1: Connect to your Weaviate Cloud instance
+client = weaviate.connect_to_weaviate_cloud(
+ cluster_url=weaviate_url,
+ auth_credentials=Auth.api_key(weaviate_api_key),
+)
+
+# END CreateCollection
+
+# NOT SHOWN TO THE USER - DELETE EXISTING COLLECTION
+client.collections.delete("Question")
+
+# START CreateCollection
+# Step 1.2: Create a collection
+# highlight-start
+questions = client.collections.create(
+ name="Question",
+ vector_config=Configure.Vectors.self_provided(), # No automatic vectorization since we're providing vectors
+ properties=[
+ Property(name="question", data_type=DataType.TEXT),
+ Property(name="answer", data_type=DataType.TEXT),
+ Property(name="category", data_type=DataType.TEXT),
+ ],
+)
+# highlight-end
+# START CreateCollection
+
+# Import three hardcoded objects with their vectors
+# END CreateCollection
+# fmt: off
+# START CreateCollection
+# Step 1.3: Import three objects
+data_objects = [
+ {
+ "properties": {"question": "What is Python?", "answer": "Python is a high-level, interpreted programming language known for its simplicity and readability.", "category": "Programming"},
+ "vector": [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8]
+ },
+ {
+ "properties": {"question": "What is machine learning?", "answer": "Machine learning is a subset of AI that enables systems to learn and improve from experience without being explicitly programmed.", "category": "AI"},
+ "vector": [0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9]
+ },
+ {
+ "properties": {"question": "What is a vector database?", "answer": "A vector database is a specialized database designed to store and query high-dimensional vectors efficiently.", "category": "Database"},
+ "vector": [0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0]
+ }
+]
+# END CreateCollection
+# fmt: on
+# START CreateCollection
+
+# Insert the objects with vectors
+questions = client.collections.get("Question")
+with questions.batch.dynamic() as batch:
+ for obj in data_objects:
+ batch.add_object(properties=obj["properties"], vector=obj["vector"])
+
+print(f"Imported {len(data_objects)} objects with vectors into the Question collection")
+
+client.close() # Free up resources
+# END CreateCollection
diff --git a/_includes/code/quickstart/clients.install.new.mdx b/_includes/code/quickstart/clients.install.new.mdx
new file mode 100644
index 00000000..9ad1e129
--- /dev/null
+++ b/_includes/code/quickstart/clients.install.new.mdx
@@ -0,0 +1,37 @@
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+
+
+
+```bash
+pip install -U weaviate-client
+```
+
+
+
+
+```bash
+npm install weaviate-client
+```
+
+
+
+
+```bash
+go get github.com/weaviate/weaviate-go-client/v5
+```
+
+
+
+
+```xml
+
+ io.weaviate
+ client
+ 4.8.3
+
+```
+
+
+
diff --git a/_includes/code/quickstart/quickstart.create_populate_collection.mdx b/_includes/code/quickstart/quickstart.create_populate_collection.mdx
new file mode 100644
index 00000000..67c072e9
--- /dev/null
+++ b/_includes/code/quickstart/quickstart.create_populate_collection.mdx
@@ -0,0 +1,88 @@
+import Tabs from "@theme/Tabs";
+import TabItem from "@theme/TabItem";
+import FilteredTextBlock from "@site/src/components/Documentation/FilteredTextBlock";
+import PyCode from "!!raw-loader!/_includes/code/python/quickstart.create_populate_collection.py";
+import TSCode from "!!raw-loader!/_includes/code/typescript/quickstart.create_collection.ts";
+import GoCode from "!!raw-loader!/_includes/code/howto/go/docs/quickstart/2_1_create_collection/main.go";
+import JavaCode from "!!raw-loader!/_includes/code/howto/java/src/test/java/io/weaviate/docs/quickstart/CreateCollection.java";
+import VectorConfigSyntax from "/_includes/vector-config-syntax.mdx";
+import VectorsAutoSchemaError from "/_includes/error-note-vectors-autoschema.mdx";
+
+
+
+
+
+
+
+
+
+
+
+The collection also contains a configuration for the generative (RAG) integration:
+
+- OpenAI [generative AI integrations](/weaviate/model-providers/openai/generative) for retrieval augmented generation (RAG).
+
+
+
+
+
+
+The collection also contains a configuration for the generative (RAG) integration:
+
+- OpenAI [generative AI integrations](/weaviate/model-providers/openai/generative) for retrieval augmented generation (RAG).
+
+
+
+
+
+
+
+The collection also contains a configuration for the generative (RAG) integration:
+
+- OpenAI [generative AI integrations](/weaviate/model-providers/openai/generative) for retrieval augmented generation (RAG).
+
+```bash
+# Best practice: store your credentials in environment variables
+# export WEAVIATE_URL="YOUR_INSTANCE_URL" # Your Weaviate instance URL
+# export WEAVIATE_API_KEY="YOUR_API_KEY" # Your Weaviate instance API key
+
+curl -X POST \
+-H "Content-Type: application/json" \
+-H "Authorization: Bearer $WEAVIATE_API_KEY" \
+-d '{
+ "class": "Question",
+ "vectorizer": "text2vec-weaviate",
+ "moduleConfig": {
+ "text2vec-weaviate": {},
+ "generative-cohere": {}
+ }
+}' \
+"$WEAVIATE_URL/v1/schema"
+```
+
+
+
diff --git a/_includes/code/quickstart/quickstart.create_populate_collection_custom_vectors.mdx b/_includes/code/quickstart/quickstart.create_populate_collection_custom_vectors.mdx
new file mode 100644
index 00000000..6dedd6e8
--- /dev/null
+++ b/_includes/code/quickstart/quickstart.create_populate_collection_custom_vectors.mdx
@@ -0,0 +1,88 @@
+import Tabs from "@theme/Tabs";
+import TabItem from "@theme/TabItem";
+import FilteredTextBlock from "@site/src/components/Documentation/FilteredTextBlock";
+import PyCode from "!!raw-loader!/_includes/code/python/quickstart.create_populate_collection_custom_vectors.py";
+import TSCode from "!!raw-loader!/_includes/code/typescript/quickstart.create_collection.ts";
+import GoCode from "!!raw-loader!/_includes/code/howto/go/docs/quickstart/2_1_create_collection/main.go";
+import JavaCode from "!!raw-loader!/_includes/code/howto/java/src/test/java/io/weaviate/docs/quickstart/CreateCollection.java";
+import VectorConfigSyntax from "/_includes/vector-config-syntax.mdx";
+import VectorsAutoSchemaError from "/_includes/error-note-vectors-autoschema.mdx";
+
+
+
+
+
+
+
+
+
+
+
+The collection also contains a configuration for the generative (RAG) integration:
+
+- OpenAI [generative AI integrations](/weaviate/model-providers/openai/generative) for retrieval augmented generation (RAG).
+
+
+
+
+
+
+The collection also contains a configuration for the generative (RAG) integration:
+
+- OpenAI [generative AI integrations](/weaviate/model-providers/openai/generative) for retrieval augmented generation (RAG).
+
+
+
+
+
+
+
+The collection also contains a configuration for the generative (RAG) integration:
+
+- OpenAI [generative AI integrations](/weaviate/model-providers/openai/generative) for retrieval augmented generation (RAG).
+
+```bash
+# Best practice: store your credentials in environment variables
+# export WEAVIATE_URL="YOUR_INSTANCE_URL" # Your Weaviate instance URL
+# export WEAVIATE_API_KEY="YOUR_API_KEY" # Your Weaviate instance API key
+
+curl -X POST \
+-H "Content-Type: application/json" \
+-H "Authorization: Bearer $WEAVIATE_API_KEY" \
+-d '{
+ "class": "Question",
+ "vectorizer": "text2vec-weaviate",
+ "moduleConfig": {
+ "text2vec-weaviate": {},
+ "generative-cohere": {}
+ }
+}' \
+"$WEAVIATE_URL/v1/schema"
+```
+
+
+
diff --git a/_includes/code/quickstart/quickstart.query.rag.mdx b/_includes/code/quickstart/quickstart.query.rag.mdx
index d5885216..74560601 100644
--- a/_includes/code/quickstart/quickstart.query.rag.mdx
+++ b/_includes/code/quickstart/quickstart.query.rag.mdx
@@ -1,63 +1,50 @@
-import Tabs from '@theme/Tabs';
-import TabItem from '@theme/TabItem';
-import FilteredTextBlock from '@site/src/components/Documentation/FilteredTextBlock';
-import PyCode from '!!raw-loader!/_includes/code/python/quickstart.query.rag.py';
-import TSCode from '!!raw-loader!/_includes/code/typescript/quickstart.query.rag.ts';
-import GoCode from '!!raw-loader!/_includes/code/howto/go/docs/quickstart/3_2_rag/main.go';
-import JavaCode from '!!raw-loader!/_includes/code/howto/java/src/test/java/io/weaviate/docs/quickstart/RAG.java';
-
+import Tabs from "@theme/Tabs";
+import TabItem from "@theme/TabItem";
+import FilteredTextBlock from "@site/src/components/Documentation/FilteredTextBlock";
+import PyCode from "!!raw-loader!/_includes/code/python/quickstart.query.rag.py";
+import TSCode from "!!raw-loader!/_includes/code/typescript/quickstart.query.rag.ts";
+import GoCode from "!!raw-loader!/_includes/code/howto/go/docs/quickstart/3_2_rag/main.go";
+import JavaCode from "!!raw-loader!/_includes/code/howto/java/src/test/java/io/weaviate/docs/quickstart/RAG.java";
-
-
-We are using the OpenAI [generative AI integrations](/weaviate/model-providers/openai/generative) for retrieval augmented generation (RAG).
-
-
-
-
-
-
-
-We are using the OpenAI [generative AI integrations](/weaviate/model-providers/openai/generative) for retrieval augmented generation (RAG).
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
```bash
# Best practice: store your credentials in environment variables
# export WEAVIATE_URL="YOUR_INSTANCE_URL" # Your Weaviate instance URL
@@ -99,6 +86,6 @@ echo '{
-d @- \
$WEAVIATE_URL/v1/graphql
```
-
-
+
+
diff --git a/docs/weaviate/quickstart/index.md b/docs/weaviate/quickstart/index.md
index 17ff5664..d2388e22 100644
--- a/docs/weaviate/quickstart/index.md
+++ b/docs/weaviate/quickstart/index.md
@@ -1,91 +1,66 @@
---
title: Quickstart (with cloud resources)
-sidebar_position: 0
image: og/docs/quickstart-tutorial.jpg
# tags: ['getting started']
-hide_table_of_contents: true
---
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
import SkipLink from '/src/components/SkipValidationLink'
+import CardsSection from "/src/components/CardsSection";
-Expected time: 30 minutesPrerequisites: None
-
-
-:::info What you will learn
-
-This quickstart shows you how to combine Weaviate Cloud and Cohere to:
-
-1. Set up a Weaviate instance. (10 minutes)
-1. Add and vectorize your data. (10 minutes)
-1. Perform a semantic search and retrieval augmented generation (RAG). (10 minutes)
-
-```mermaid
-flowchart LR
- %% Define nodes with white backgrounds and darker borders
- A1["Create Weaviate Sandbox"] --> A2["Install client library"]
- A2 --> A3["Connect to Weaviate"]
- A3 --> B1["Define collection (with an inference API)"]
- B1 --> B2["Batch import objects"]
- B2 --> C1["Semantic search (nearText)"]
- C1 --> C2["RAG (Generate)"]
-
- %% Group nodes in subgraphs with brand colors
- subgraph sg1 ["1\. Setup"]
- A1
- A2
- A3
- end
-
- subgraph sg2 ["2\. Populate"]
- B1
- B2
- end
-
- subgraph sg3 ["3\. Query"]
- C1
- C2
- end
-
- %% Style nodes with white background and darker borders
- style A1 fill:#ffffff,stroke:#B9C8DF,color:#130C49
- style A2 fill:#ffffff,stroke:#B9C8DF,color:#130C49
- style A3 fill:#ffffff,stroke:#B9C8DF,color:#130C49
- style B1 fill:#ffffff,stroke:#B9C8DF,color:#130C49
- style B2 fill:#ffffff,stroke:#B9C8DF,color:#130C49
- style C1 fill:#ffffff,stroke:#B9C8DF,color:#130C49
- style C2 fill:#ffffff,stroke:#B9C8DF,color:#130C49
-
- %% Style subgraphs with brand colors
- style sg1 fill:#ffffff,stroke:#61BD73,stroke-width:2px,color:#130C49
- style sg2 fill:#ffffff,stroke:#130C49,stroke-width:2px,color:#130C49
- style sg3 fill:#ffffff,stroke:#7AD6EB,stroke-width:2px,color:#130C49
-```
-
-Notes:
-
-- The code examples here are self-contained. You can copy and paste them into your own environment to try them out.
-
-- If you prefer to use locally hosted resources, see [Quickstart: locally hosted](./local.md).
+export const quickstartOptions = [
+{
+title: "Vectorize objects on import",
+description:
+"Import objects and vectorize them with the Weaviate Embeddings service.",
+link: "?import=vectorization#create-a-collection",
+icon: "fas fa-compress-alt",
+},
+{
+title: "Import custom vectors",
+description:
+"Import pre-computed vector embeddings.",
+link: "?import=custom-embeddings#create-a-collection",
+icon: "fas fa-puzzle-piece",
+},
+];
+
+
+
+
-:::
+---
-
+
+
-### Requirements
+Weaviate is an open-source vector database built to power AI applications, from prototypes to production-scale systems. This quickstart guide will show you how to:
-In order to perform Retrieval Augmented Generation (RAG) in the last step, you will need a [Cohere](https://dashboard.cohere.com/) account. You can use a free Cohere trial API key.
+1. **Import data** - Create a collection and import data into it. The data will be vectorized with the Weaviate Embeddings service.
+2. **Search** - Perform a similarity (vector) search on your data.
+3. **RAG** - Perform Retrieval augmented generation (RAG) with a generative model.
-If you have another preferred [model provider](/weaviate/model-providers), you can use that instead of Cohere.
+
+
-
+Weaviate is an open-source vector database built to power AI applications, from prototypes to production-scale systems. This quickstart guide will show you how to:
-## Step 1: Set up Weaviate
+1. **Import data** - Create a collection and import data into it.
+2. **Search** - Perform a similarity (vector) search on your data.
+3. **RAG** - Perform Retrieval augmented generation (RAG) with a generative model.
-### 1.1 Create a Weaviate database
+
+
+
+## Prerequisites
+
+- A [Weaviate Cloud](https://console.weaviate.cloud/) Sandbox instance.
+
+
+How to set up a Weaviate Cloud Sandbox instance
-Go to the [Weaviate Cloud console](https://console.weaviate.cloud) and create a free Sandbox instance.
+Go to the [Weaviate Cloud console](https://console.weaviate.cloud) and create a free Sandbox instance as shown in the interactive example below.
-
-### 1.2 Install a client library
-
-We recommend using a [client library](../client-libraries/index.mdx) to work with Weaviate. Follow the instructions below to install one of the official client libraries, available in [Python](../client-libraries/python/index.mdx), [JavaScript/TypeScript](../client-libraries/typescript/index.mdx), [Go](../client-libraries/go.md), and [Java](../client-libraries/java.md).
-
-import CodeClientInstall from '/\_includes/code/quickstart/clients.install.mdx';
-
-
+
-### 1.3 Connect to Weaviate
+
+How to retrieve Weaviate Cloud credentials (`WEAVIATE_API_KEY` and `WEAVIATE_URL`)
-Now you can connect to your Weaviate instance. You will need the:
+After you create a Weaviate Cloud instance, you will need the:
- **REST Endpoint URL** and the
- **Administrator API Key**.
You can retrieve them both from the [WCD console](https://console.weaviate.cloud) as shown in the interactive example below.
-:::note
-
-New clusters with Weaviate version `v1.30` (or later) have [RBAC (Role-Based Access Control)](/weaviate/configuration/rbac/index.mdx) enabled by default. These clusters don't come with API keys, you will need to create an API key yourself and assign it a role (`admin`, `viewer` or a custom role).
-
-:::
-
-
-If you did not see any errors, you are ready to proceed. We will replace the simple cluster status check with more meaningful operations in the next steps.
+
-
+---
-## Step 2: Populate the database
+## Install a client library
-Now, we can populate our database by first defining a collection and then adding data.
+We recommend using a [client library](../client-libraries/index.mdx) to work with Weaviate. Follow the instructions below to install one of the official client libraries, available in [Python](../client-libraries/python/index.mdx), [JavaScript/TypeScript](../client-libraries/typescript/index.mdx), [Go](../client-libraries/go.md), and [Java](../client-libraries/java.md).
-### 2.1 Define a collection
+import CodeClientInstall from '/\_includes/code/quickstart/clients.install.new.mdx';
-:::info What is a collection?
+
-A collection is a set of objects that share the same data structure, like a table in relational databases or a collection in NoSQL databases. A collection also includes additional configurations that define how the data objects are stored and indexed.
+## Step 1: Create a collection {#create-a-collection}
-:::
+Now, we can populate our database by first defining a collection and then adding data. You can either **[vectorize each object during the import](?import=vectorization#create-a-collection)** (we will use the Weaviate Embeddings service to vectorize the data), or you can **[import pre-computed vector embeddings](?import=custom-embeddings#create-a-collection)**.
-The following example creates a _collection_ called `Question` with:
+
+
-- The [Weaviate Embeddings](/weaviate/model-providers/weaviate/embeddings.md) service for creating vectors during ingestion & queries.
+The following example creates a _collection_ called `Question` with the [Weaviate Embeddings](/weaviate/model-providers/weaviate/embeddings.md) service for creating vectors during ingestion and for querying.
-import CreateCollection from '/\_includes/code/quickstart/quickstart.create_collection.mdx'
+import CreateCollection from '/\_includes/code/quickstart/quickstart.create_populate_collection.mdx'
-Run this code to create the collection to which you can add data.
+
+
-import ModelProvider from '/\_includes/embedding-model-providers.mdx'
+The following example creates a _collection_ called `Questions` and imports precomputed vector embeddings created with the [Weaviate Embeddings](/weaviate/model-providers/weaviate/embeddings.md) service.
-
- Do you prefer a different setup?
-
-
+import CreateCollectionCustomVectors from '/\_includes/code/quickstart/quickstart.create_populate_collection_custom_vectors.mdx'
-### 2.2 Add objects
+
-We can now add data to our collection.
+
+
-The following example:
+## Step 2: Semantic (vector) search {#semantic-search}
-- Loads objects, and
-- Adds objects to the target collection (`Question`) using a batch process.
-
-:::tip Batch imports
-
-([Batch imports](../manage-objects/import.mdx)) are the most efficient way to add large amounts of data, as it sends multiple objects in a single request. See the [How-to: Batch import](../manage-objects/import.mdx) guide for more information.
-
-:::
-
-import ImportObjects from '/\_includes/code/quickstart/quickstart.import_objects.mdx'
-
-
-
-Run this code to add the demo data.
-
-
-
-## Step 3: Queries
-
-Weaviate provides a wide range of query tools to help you find the right data. We will try a few searches here.
-
-### 3.1 Semantic search {#semantic-search}
-
-Semantic search finds results based on meaning. This is called `nearText` in Weaviate.
-
-The following example searches for 2 objects whose meaning is most similar to that of `biology`.
+Semantic search finds results based on meaning. This is called `nearText` in Weaviate. The following example searches for 2 objects (_limit_) whose meaning is most similar to that of `biology`.
import QueryNearText from '/\_includes/code/quickstart/quickstart.query.neartext.mdx'
-Run this code to perform the query. Our query found entries for `DNA` and `species`.
-
-
- Example full response in JSON format
-
-```json
-{
- {
- "answer": "DNA",
- "question": "In 1953 Watson & Crick built a model of the molecular structure of this, the gene-carrying substance",
- "category": "SCIENCE"
- },
- {
- "answer": "species",
- "question": "2000 news: the Gunnison sage grouse isn't just another northern sage grouse, but a new one of this classification",
- "category": "SCIENCE"
- }
-}
-```
-
-
-
-If you inspect the full response, you will see that the word `biology` does not appear anywhere.
-
-Even so, Weaviate was able to return biology-related entries. This is made possible by _vector embeddings_ that capture meaning. Under the hood, semantic search is powered by vectors, or vector embeddings.
-
-Here is a diagram showing the workflow in Weaviate.
-
-```mermaid
-flowchart LR
- Query["ð Search: 'biology'"]
-
- subgraph sg1 ["Vector Search"]
- direction LR
- VS1["Convert query to vector"] --> VS2["Find similar vectors"]
- VS2 --> VS3["Return top matches"]
- end
-
- subgraph sg2 ["Results"]
- R1["Most similar documents"]
- end
-
- Query --> VS1
- VS3 --> R1
-
- %% Style nodes with white background and darker borders
- style Query fill:#ffffff,stroke:#B9C8DF,color:#130C49
- style VS1 fill:#ffffff,stroke:#B9C8DF,color:#130C49
- style VS2 fill:#ffffff,stroke:#B9C8DF,color:#130C49
- style VS3 fill:#ffffff,stroke:#B9C8DF,color:#130C49
- style R1 fill:#ffffff,stroke:#B9C8DF,color:#130C49
-
- %% Style subgraphs with brand colors
- style sg1 fill:#ffffff,stroke:#61BD73,stroke-width:2px,color:#130C49
- style sg2 fill:#ffffff,stroke:#130C49,stroke-width:2px,color:#130C49
-```
-
-:::info Where did the vectors come from?
-
-Weaviate used the **Weaviate Embeddings** service to generate a vector embedding for each object during import. During the query, Weaviate similarly converted the query (`biology`) into a vector.
-
-As we mentioned above, this is optional. See [Starter Guide: Bring Your Own Vectors](/weaviate/starter-guides/custom-vectors.mdx) if you would prefer to provide your own vectors.
+## Step 3: Retrieval augmented generation (RAG)
-:::
-
-:::tip More search types available
+
+
-Weaviate is capable of many types of searches. See, for example, our how-to guides on [similarity searches](../search/similarity.md), [keyword searches](../search/bm25.md), [hybrid searches](../search/hybrid.md), and [filtered searches](../search/filters.md).
-
-:::
+- For Retrieval Augmented Generation (RAG) in the last step, you will need a [Claude](https://console.anthropic.com/settings/keys) API key. You can also use another [model provider](/weaviate/model-providers) instead.
-### 3.2 Retrieval augmented generation
-
-Retrieval augmented generation (RAG), also called generative search, combines the power of generative AI models such as large language models (LLMs) with the up-to-date truthfulness of a database.
-
-RAG works by prompting a large language model (LLM) with a combination of a _user query_ and _data retrieved from a database_.
-
-This diagram shows the RAG workflow in Weaviate.
-
-```mermaid
-flowchart LR
- subgraph sg0 ["Weaviate Query"]
- direction TB
- Search["ð Search: 'biology'"]
- Prompt["âïļ Prompt: 'Write a tweet...'"]
- end
-
- subgraph sg1 ["Vector Search"]
- direction LR
- VS1["Convert query to vector"] --> VS2["Find similar vectors"]
- VS2 --> VS3["Return top matches"]
- end
-
- subgraph sg2 ["Generation"]
- direction LR
- G1["Send (results + prompt) to LLM"]
- G1 --> G2["Generate response"]
- end
-
- subgraph sg3 ["Results"]
- direction TB
- R1["Most similar documents"]
- R2["Generated content"]
- end
-
- Search --> VS1
- VS3 --> R1
- Prompt --> G1
- VS3 --> G1
- G2 --> R2
-
- %% Style nodes with white background and darker borders
- style Search fill:#ffffff,stroke:#B9C8DF,color:#130C49
- style Prompt fill:#ffffff,stroke:#B9C8DF,color:#130C49
- style VS1 fill:#ffffff,stroke:#B9C8DF,color:#130C49
- style VS2 fill:#ffffff,stroke:#B9C8DF,color:#130C49
- style VS3 fill:#ffffff,stroke:#B9C8DF,color:#130C49
- style G1 fill:#ffffff,stroke:#B9C8DF,color:#130C49
- style G2 fill:#ffffff,stroke:#B9C8DF,color:#130C49
- style R1 fill:#ffffff,stroke:#B9C8DF,color:#130C49
- style R2 fill:#ffffff,stroke:#B9C8DF,color:#130C49
-
- %% Style subgraphs with brand colors
- style sg0 fill:#ffffff,stroke:#130C49,stroke-width:2px,color:#130C49
- style sg1 fill:#ffffff,stroke:#61BD73,stroke-width:2px,color:#130C49
- style sg2 fill:#ffffff,stroke:#7AD6EB,stroke-width:2px,color:#130C49
- style sg3 fill:#ffffff,stroke:#130C49,stroke-width:2px,color:#130C49
-```
+Retrieval augmented generation (RAG), also called generative search, works by prompting a large language model (LLM) with a combination of a _user query_ and _data retrieved from a database_.
The following example combines the same search (for `biology`) with a prompt to generate a tweet.
@@ -379,215 +188,19 @@ import QueryRAG from '/\_includes/code/quickstart/quickstart.query.rag.mdx'
-:::info Cohere API key in the header
-
-Note that this code includes an additional header for the Cohere API key. Weaviate uses this key to access the Cohere generative AI model and perform retrieval augmented generation (RAG).
-
-:::
-
-Run this code to perform the query. Here is one possible response (your response will likely be different).
-
-```text
-𧎠In 1953 Watson & Crick built a model of the molecular structure of DNA, the gene-carrying substance! ð§ŽðŽ
-
-ðĶĒ 2000 news: the Gunnison sage grouse isn't just another northern sage grouse, but a new species! ðĶĒðŋ #ScienceFacts #DNA #SpeciesClassification
-```
-
-The response should be new, yet familiar. This is because you have seen the entries above for `DNA` and `species` in the [semantic search](#semantic-search) section.
-
-The power of RAG comes from the ability to transform your own data. Weaviate helps you in this journey by making it easy to perform a combined search & generation in just a few lines of code.
-
-
-
-## Recap
-
-In this quickstart guide, you:
-
-- Created a Serverless Weaviate sandbox instance on Weaviate Cloud.
-- Defined a collection and added data.
-- Performed queries, including:
- - Semantic search, and
- - Retrieval augmented generation.
-
-Where to go next is up to you. We include some suggested steps and resources below.
-
-
-
-## Next
-
-Try these additional resources to learn more about Weaviate:
-
-
-
-
-
-
-
More on search
-
-
-
- See how to perform searches, such as keyword, similarity, hybrid, image, filtered and reranked searches.
-
-
-
-
-
-
-
-
Manage data
-
-
-
- See how to manage data, such as manage collections, create objects, batch import data and use multi-tenancy.
-
-
-
-
-
-
-
-
RAG
-
-
-
- Check out the Starter guide: retrieval augmented generation.
-
-
-
-
-
-
-
-
Workshops and office hours
-
-
-
- We hold in-person and online workshops, office hours and events for different experience levels. Join us!
-
-
-
-
-
-
-
-
-
-## FAQs & Troubleshooting
-
-We provide answers to some common questions, or potential issues below.
-
-### Questions
-
-#### Can I use different integrations?
-
-
- See answer
-
-In this example, we use the `Weaviate Embeddings` and `Cohere` inference API. But you can use others.
-
-If you do want to change the embeddings, or the generative AI integrations, you can. You will need to:
-
-- Ensure that the Weaviate module is available in the Weaviate instance you are using,
-- Modify your collection definition to use your preferred integration, and
-- Make sure to use the right API key(s) (if necessary) for your integration.
-
-See the [model providers integration](../model-providers/index.md) section for more information.
-
-
-
-### Troubleshooting
-
-#### If you see Error: Name 'Question' already used as a name for an Object class
+
+
-
- See answer
-
-You may see this error if you try to create a collection that already exists in your instance of Weaviate. In this case, you can follow these instructions to delete the collection.
-
-import CautionSchemaDeleteClass from '/\_includes/schema-delete-class.mdx'
-
-
+- For Retrieval Augmented Generation (RAG) in the last step, you will need a [Claude](https://console.anthropic.com/settings/keys) API key. You can also use another [model provider](/weaviate/model-providers) instead.
-
-
-#### How to confirm collection creation
-
-
- See answer
+Retrieval augmented generation (RAG), also called generative search, works by prompting a large language model (LLM) with a combination of a _user query_ and _data retrieved from a database_.
-If you are not sure whether the collection has been created, check the `schema` endpoint.
-
-Replace WEAVIATE_INSTANCE_URL with your instance's REST Endpoint URL.:
-
-```
-https://WEAVIATE_INSTANCE_URL/v1/schema
-```
-
-You should see:
-
-```json
-{
- "classes": [
- {
- "class": "Question",
- ... // truncated additional information here
- "vectorizer": "text2vec-weaviate"
- }
- ]
-}
-```
-
-Where the schema should indicate that the `Question` collection has been added.
-
-:::note REST & GraphQL in Weaviate
-
-Weaviate uses a combination of RESTful and GraphQL APIs. In Weaviate, RESTful API endpoints can be used to add data or obtain information about the Weaviate instance, and the GraphQL interface to retrieve data.
-
-:::
-
-
-
-#### How to confirm data import
-
-
- See answer
-
-To confirm successful data import, check the `objects` endpoint to verify that all objects are imported.
-
-Replace WEAVIATE_INSTANCE_URL with your instance REST Endpoint URL:
-
-```
-https://WEAVIATE_INSTANCE_URL/v1/objects
-```
-
-You should see:
-
-```json
-{
- "deprecations": null,
- "objects": [
- ... // Details of each object
- ],
- "totalResults": 10 // You should see 10 results here
-}
-```
-
-Where you should be able to confirm that you have imported all `10` objects.
-
-
-
-#### If the `nearText` search is not working
-
-
- See answer
-
-To perform text-based (`nearText`) similarity searches, you need to have a vectorizer enabled, and configured in your collection.
-
-Make sure the vectorizer is configured [like this](#21-define-a-collection).
+The following example combines the same search (for `biology`) with a prompt to generate a tweet.
-If the search still doesn't work, [contact us](#questions-and-feedback)!
+
+
-
+## Next steps
## Questions and feedback
diff --git a/src/css/custom.scss b/src/css/custom.scss
index 5246c678..988de621 100644
--- a/src/css/custom.scss
+++ b/src/css/custom.scss
@@ -980,3 +980,7 @@ button.close {
.scalar-reference-intro-clients {
display: none !important;
}
+
+.hidden-tabs .tabs__item {
+ display: none;
+}
From 1fc2143033b4e274a88fe8775cae4522cf97c539 Mon Sep 17 00:00:00 2001
From: Ivan Despot <66276597+g-despot@users.noreply.github.com>
Date: Tue, 21 Oct 2025 22:00:51 +0200
Subject: [PATCH 02/16] Update docs
---
... => quickstart.short.create_collection.py} | 24 +-
...short.import_vectors.create_collection.py} | 6 +-
...t.short.import_vectors.query.nearvector.py | 30 ++
...ickstart.short.import_vectors.query.rag.py | 37 ++
.../python/quickstart.short.query.neartext.py | 28 ++
.../code/python/quickstart.short.query.rag.py | 37 ++
...=> quickstart.short.create_collection.mdx} | 2 +-
...ckstart.short.import-vectors.query.rag.mdx | 91 ++++
...hort.import_vectors.create_collection.mdx} | 2 +-
....short.import_vectors.query.nearvector.mdx | 86 ++++
.../quickstart.short.query.neartext.mdx | 86 ++++
.../quickstart/quickstart.short.query.rag.mdx | 91 ++++
docs/weaviate/quickstart/index.md | 231 ++++++---
docs/weaviate/tutorials/index.mdx | 11 +
.../tutorials/quick-tour-of-weaviate.mdx | 437 ++++++++++++++++++
sidebars.js | 1 +
src/components/CardsSection/index.jsx | 65 ++-
.../CardsSection/styles.module.scss | 16 +-
src/components/KapaAI/index.jsx | 19 +
src/components/KapaAI/styles.module.scss | 50 ++
20 files changed, 1233 insertions(+), 117 deletions(-)
rename _includes/code/python/{quickstart.create_populate_collection.py => quickstart.short.create_collection.py} (52%)
rename _includes/code/python/{quickstart.create_populate_collection_custom_vectors.py => quickstart.short.import_vectors.create_collection.py} (74%)
create mode 100644 _includes/code/python/quickstart.short.import_vectors.query.nearvector.py
create mode 100644 _includes/code/python/quickstart.short.import_vectors.query.rag.py
create mode 100644 _includes/code/python/quickstart.short.query.neartext.py
create mode 100644 _includes/code/python/quickstart.short.query.rag.py
rename _includes/code/quickstart/{quickstart.create_populate_collection.mdx => quickstart.short.create_collection.mdx} (98%)
create mode 100644 _includes/code/quickstart/quickstart.short.import-vectors.query.rag.mdx
rename _includes/code/quickstart/{quickstart.create_populate_collection_custom_vectors.mdx => quickstart.short.import_vectors.create_collection.mdx} (98%)
create mode 100644 _includes/code/quickstart/quickstart.short.import_vectors.query.nearvector.mdx
create mode 100644 _includes/code/quickstart/quickstart.short.query.neartext.mdx
create mode 100644 _includes/code/quickstart/quickstart.short.query.rag.mdx
create mode 100644 docs/weaviate/tutorials/quick-tour-of-weaviate.mdx
create mode 100644 src/components/KapaAI/index.jsx
create mode 100644 src/components/KapaAI/styles.module.scss
diff --git a/_includes/code/python/quickstart.create_populate_collection.py b/_includes/code/python/quickstart.short.create_collection.py
similarity index 52%
rename from _includes/code/python/quickstart.create_populate_collection.py
rename to _includes/code/python/quickstart.short.create_collection.py
index b9fea1c3..e033cdca 100644
--- a/_includes/code/python/quickstart.create_populate_collection.py
+++ b/_includes/code/python/quickstart.short.create_collection.py
@@ -17,19 +17,19 @@
# END CreateCollection
# NOT SHOWN TO THE USER - DELETE EXISTING COLLECTION
-client.collections.delete("Question")
+client.collections.delete("Movie")
# START CreateCollection
# Step 1.2: Create a collection
# highlight-start
-questions = client.collections.create(
- name="Question",
+movies = client.collections.create(
+ name="Movie",
vector_config=Configure.Vectors.text2vec_weaviate(), # Configure the Weaviate Embeddings vectorizer
# You can also use auto-schema, here we define the schema manually
properties=[
- Property(name="question", data_type=DataType.TEXT),
- Property(name="answer", data_type=DataType.TEXT),
- Property(name="category", data_type=DataType.TEXT),
+ Property(name="title", data_type=DataType.TEXT),
+ Property(name="description", data_type=DataType.TEXT),
+ Property(name="genre", data_type=DataType.TEXT),
],
)
# highlight-end
@@ -40,20 +40,20 @@
# START CreateCollection
# Step 1.3: Import three objects
data_objects = [
- {"properties": {"question": "What is Python?", "answer": "Python is a high-level, interpreted programming language known for its simplicity and readability.", "category": "Programming"}},
- {"properties": {"question": "What is machine learning?", "answer": "Machine learning is a subset of AI that enables systems to learn and improve from experience without being explicitly programmed.", "category": "AI"}},
- {"properties": {"question": "What is a vector database?", "answer": "A vector database is a specialized database designed to store and query high-dimensional vectors efficiently.", "category": "Database"}},
+ {"properties": {"title": "The Matrix", "description": "A computer hacker learns about the true nature of reality and his role in the war against its controllers.", "genre": "Science Fiction"}},
+ {"properties": {"title": "Spirited Away", "description": "A young girl becomes trapped in a mysterious world of spirits and must find a way to save her parents and return home.", "genre": "Animation"}},
+ {"properties": {"title": "The Lord of the Rings: The Fellowship of the Ring", "description": "A meek Hobbit and his companions set out on a perilous journey to destroy a powerful ring and save Middle-earth.", "genre": "Fantasy"}},
]
# END CreateCollection
# fmt: on
# START CreateCollection
-questions = client.collections.use("Question")
-with questions.batch.dynamic() as batch:
+movies = client.collections.use("Movie")
+with movies.batch.dynamic() as batch:
for obj in data_objects:
batch.add_object(properties=obj)
-print(f"Imported {len(questions)} objects into the Question collection")
+print(f"Imported {len(movies)} objects into the Movie collection")
client.close() # Free up resources
# END CreateCollection
diff --git a/_includes/code/python/quickstart.create_populate_collection_custom_vectors.py b/_includes/code/python/quickstart.short.import_vectors.create_collection.py
similarity index 74%
rename from _includes/code/python/quickstart.create_populate_collection_custom_vectors.py
rename to _includes/code/python/quickstart.short.import_vectors.create_collection.py
index a74059ec..4a4b030d 100644
--- a/_includes/code/python/quickstart.create_populate_collection_custom_vectors.py
+++ b/_includes/code/python/quickstart.short.import_vectors.create_collection.py
@@ -41,15 +41,15 @@
# Step 1.3: Import three objects
data_objects = [
{
- "properties": {"question": "What is Python?", "answer": "Python is a high-level, interpreted programming language known for its simplicity and readability.", "category": "Programming"},
+ "properties": {"title": "The Matrix", "description": "A computer hacker learns about the true nature of reality and his role in the war against its controllers.", "genre": "Science Fiction"},
"vector": [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8]
},
{
- "properties": {"question": "What is machine learning?", "answer": "Machine learning is a subset of AI that enables systems to learn and improve from experience without being explicitly programmed.", "category": "AI"},
+ "properties": {"title": "Spirited Away", "description": "A young girl becomes trapped in a mysterious world of spirits and must find a way to save her parents and return home.", "genre": "Animation"},
"vector": [0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9]
},
{
- "properties": {"question": "What is a vector database?", "answer": "A vector database is a specialized database designed to store and query high-dimensional vectors efficiently.", "category": "Database"},
+ "properties": {"title": "The Lord of the Rings: The Fellowship of the Ring", "description": "A meek Hobbit and his companions set out on a perilous journey to destroy a powerful ring and save Middle-earth.", "genre": "Fantasy"},
"vector": [0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0]
}
]
diff --git a/_includes/code/python/quickstart.short.import_vectors.query.nearvector.py b/_includes/code/python/quickstart.short.import_vectors.query.nearvector.py
new file mode 100644
index 00000000..d87db6ab
--- /dev/null
+++ b/_includes/code/python/quickstart.short.import_vectors.query.nearvector.py
@@ -0,0 +1,30 @@
+# NearText
+import weaviate
+from weaviate.classes.init import Auth
+import os, json
+
+# Best practice: store your credentials in environment variables
+weaviate_url = os.environ["WEAVIATE_URL"]
+weaviate_api_key = os.environ["WEAVIATE_API_KEY"]
+
+client = weaviate.connect_to_weaviate_cloud(
+ cluster_url=weaviate_url, # Replace with your Weaviate Cloud URL
+ auth_credentials=Auth.api_key(
+ weaviate_api_key
+ ), # Replace with your Weaviate Cloud key
+)
+
+movies = client.collections.use("Movie")
+
+# highlight-start
+response = movies.query.near_vector(
+ near_vector=[0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9],
+ limit=2
+)
+# highlight-end
+
+for obj in response.objects:
+ print(json.dumps(obj.properties, indent=2))
+
+client.close() # Free up resources
+# END NearText
diff --git a/_includes/code/python/quickstart.short.import_vectors.query.rag.py b/_includes/code/python/quickstart.short.import_vectors.query.rag.py
new file mode 100644
index 00000000..4728c269
--- /dev/null
+++ b/_includes/code/python/quickstart.short.import_vectors.query.rag.py
@@ -0,0 +1,37 @@
+# RAG
+import os
+import weaviate
+from weaviate.classes.init import Auth
+from weaviate.classes.generate import GenerativeConfig
+
+
+# Best practice: store your credentials in environment variables
+weaviate_url = os.environ["WEAVIATE_URL"]
+weaviate_api_key = os.environ["WEAVIATE_API_KEY"]
+openai_api_key = os.environ["OPENAI_APIKEY"]
+
+client = weaviate.connect_to_weaviate_cloud(
+ cluster_url=weaviate_url, # Replace with your Weaviate Cloud URL
+ auth_credentials=Auth.api_key(
+ weaviate_api_key
+ ), # Replace with your Weaviate Cloud key
+ # highlight-start
+ headers={"X-OpenAI-Api-Key": openai_api_key}, # Replace with your OpenAI API key
+ # highlight-end
+)
+
+questions = client.collections.use("Question")
+
+# highlight-start
+response = questions.generate.near_vector(
+ near_vector=[0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9],
+ limit=1,
+ grouped_task="Write a tweet with emojis about this movie.",
+ generative_provider=GenerativeConfig.openai(), # Configure the OpenAI generative integration for RAG
+)
+# highlight-end
+
+print(response.generative.text) # Inspect the generated text
+
+client.close() # Free up resources
+# END RAG
diff --git a/_includes/code/python/quickstart.short.query.neartext.py b/_includes/code/python/quickstart.short.query.neartext.py
new file mode 100644
index 00000000..24045840
--- /dev/null
+++ b/_includes/code/python/quickstart.short.query.neartext.py
@@ -0,0 +1,28 @@
+# NearText
+import weaviate
+from weaviate.classes.init import Auth
+import os, json
+
+# Best practice: store your credentials in environment variables
+weaviate_url = os.environ["WEAVIATE_URL"]
+weaviate_api_key = os.environ["WEAVIATE_API_KEY"]
+
+client = weaviate.connect_to_weaviate_cloud(
+ cluster_url=weaviate_url, # Replace with your Weaviate Cloud URL
+ auth_credentials=Auth.api_key(weaviate_api_key), # Replace with your Weaviate Cloud key
+)
+
+movies = client.collections.use("Movie")
+
+# highlight-start
+response = movies.query.near_text(
+ query="sci-fi",
+ limit=2
+)
+# highlight-end
+
+for obj in response.objects:
+ print(json.dumps(obj.properties, indent=2))
+
+client.close() # Free up resources
+# END NearText
diff --git a/_includes/code/python/quickstart.short.query.rag.py b/_includes/code/python/quickstart.short.query.rag.py
new file mode 100644
index 00000000..de931a7f
--- /dev/null
+++ b/_includes/code/python/quickstart.short.query.rag.py
@@ -0,0 +1,37 @@
+# RAG
+import os
+import weaviate
+from weaviate.classes.init import Auth
+from weaviate.classes.generate import GenerativeConfig
+
+
+# Best practice: store your credentials in environment variables
+weaviate_url = os.environ["WEAVIATE_URL"]
+weaviate_api_key = os.environ["WEAVIATE_API_KEY"]
+openai_api_key = os.environ["OPENAI_APIKEY"]
+
+client = weaviate.connect_to_weaviate_cloud(
+ cluster_url=weaviate_url, # Replace with your Weaviate Cloud URL
+ auth_credentials=Auth.api_key(
+ weaviate_api_key
+ ), # Replace with your Weaviate Cloud key
+ # highlight-start
+ headers={"X-OpenAI-Api-Key": openai_api_key}, # Replace with your OpenAI API key
+ # highlight-end
+)
+
+questions = client.collections.use("Question")
+
+# highlight-start
+response = questions.generate.near_text(
+ query="sci-fi",
+ limit=1,
+ grouped_task="Write a tweet with emojis about this movie.",
+ generative_provider=GenerativeConfig.openai(), # Configure the OpenAI generative integration for RAG
+)
+# highlight-end
+
+print(response.generative.text) # Inspect the generated text
+
+client.close() # Free up resources
+# END RAG
diff --git a/_includes/code/quickstart/quickstart.create_populate_collection.mdx b/_includes/code/quickstart/quickstart.short.create_collection.mdx
similarity index 98%
rename from _includes/code/quickstart/quickstart.create_populate_collection.mdx
rename to _includes/code/quickstart/quickstart.short.create_collection.mdx
index 67c072e9..696461fe 100644
--- a/_includes/code/quickstart/quickstart.create_populate_collection.mdx
+++ b/_includes/code/quickstart/quickstart.short.create_collection.mdx
@@ -1,7 +1,7 @@
import Tabs from "@theme/Tabs";
import TabItem from "@theme/TabItem";
import FilteredTextBlock from "@site/src/components/Documentation/FilteredTextBlock";
-import PyCode from "!!raw-loader!/_includes/code/python/quickstart.create_populate_collection.py";
+import PyCode from "!!raw-loader!/_includes/code/python/quickstart.short.create_collection.py";
import TSCode from "!!raw-loader!/_includes/code/typescript/quickstart.create_collection.ts";
import GoCode from "!!raw-loader!/_includes/code/howto/go/docs/quickstart/2_1_create_collection/main.go";
import JavaCode from "!!raw-loader!/_includes/code/howto/java/src/test/java/io/weaviate/docs/quickstart/CreateCollection.java";
diff --git a/_includes/code/quickstart/quickstart.short.import-vectors.query.rag.mdx b/_includes/code/quickstart/quickstart.short.import-vectors.query.rag.mdx
new file mode 100644
index 00000000..49d7cf03
--- /dev/null
+++ b/_includes/code/quickstart/quickstart.short.import-vectors.query.rag.mdx
@@ -0,0 +1,91 @@
+import Tabs from "@theme/Tabs";
+import TabItem from "@theme/TabItem";
+import FilteredTextBlock from "@site/src/components/Documentation/FilteredTextBlock";
+import PyCode from "!!raw-loader!/_includes/code/python/quickstart.short.import_vectors.query.rag.py";
+import TSCode from "!!raw-loader!/_includes/code/typescript/quickstart.query.rag.ts";
+import GoCode from "!!raw-loader!/_includes/code/howto/go/docs/quickstart/3_2_rag/main.go";
+import JavaCode from "!!raw-loader!/_includes/code/howto/java/src/test/java/io/weaviate/docs/quickstart/RAG.java";
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+```bash
+# Best practice: store your credentials in environment variables
+# export WEAVIATE_URL="YOUR_INSTANCE_URL" # Your Weaviate instance URL
+# export WEAVIATE_API_KEY="YOUR_API_KEY" # Your Weaviate instance API key
+# export COHERE_APIKEY="YOUR_API_KEY" # Your Cohere API key
+
+echo '{
+ "query": "{
+ Get {
+ Question (
+ limit: 2
+ nearText: {
+ concepts: [\"biology\"],
+ }
+ ) {
+ question
+ answer
+ category
+ _additional {
+ generate(
+ groupedResult: {
+ task: \"\"\"
+ Write a tweet with emojis about this movie.
+ \"\"\"
+ }
+ ) {
+ groupedResult
+ error
+ }
+ }
+ }
+ }
+ }"
+}' | tr -d "\n" | curl \
+ -X POST \
+ -H 'Content-Type: application/json' \
+ -H "Authorization: Bearer $WEAVIATE_API_KEY" \
+ -H "X-Cohere-Api-Key: $COHERE_APIKEY" \
+ -d @- \
+ $WEAVIATE_URL/v1/graphql
+```
+
+
+
diff --git a/_includes/code/quickstart/quickstart.create_populate_collection_custom_vectors.mdx b/_includes/code/quickstart/quickstart.short.import_vectors.create_collection.mdx
similarity index 98%
rename from _includes/code/quickstart/quickstart.create_populate_collection_custom_vectors.mdx
rename to _includes/code/quickstart/quickstart.short.import_vectors.create_collection.mdx
index 6dedd6e8..25722c65 100644
--- a/_includes/code/quickstart/quickstart.create_populate_collection_custom_vectors.mdx
+++ b/_includes/code/quickstart/quickstart.short.import_vectors.create_collection.mdx
@@ -1,7 +1,7 @@
import Tabs from "@theme/Tabs";
import TabItem from "@theme/TabItem";
import FilteredTextBlock from "@site/src/components/Documentation/FilteredTextBlock";
-import PyCode from "!!raw-loader!/_includes/code/python/quickstart.create_populate_collection_custom_vectors.py";
+import PyCode from "!!raw-loader!/_includes/code/python/quickstart.short.import_vectors.create_collection.py";
import TSCode from "!!raw-loader!/_includes/code/typescript/quickstart.create_collection.ts";
import GoCode from "!!raw-loader!/_includes/code/howto/go/docs/quickstart/2_1_create_collection/main.go";
import JavaCode from "!!raw-loader!/_includes/code/howto/java/src/test/java/io/weaviate/docs/quickstart/CreateCollection.java";
diff --git a/_includes/code/quickstart/quickstart.short.import_vectors.query.nearvector.mdx b/_includes/code/quickstart/quickstart.short.import_vectors.query.nearvector.mdx
new file mode 100644
index 00000000..8fd27b68
--- /dev/null
+++ b/_includes/code/quickstart/quickstart.short.import_vectors.query.nearvector.mdx
@@ -0,0 +1,86 @@
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+import FilteredTextBlock from '@site/src/components/Documentation/FilteredTextBlock';
+import PyCode from '!!raw-loader!/_includes/code/python/quickstart.short.import_vectors.query.nearvector.py';
+import TSCode from '!!raw-loader!/_includes/code/typescript/quickstart.query.neartext.ts';
+import GoCode from '!!raw-loader!/_includes/code/howto/go/docs/quickstart/3_1_neartext/main.go';
+import JavaCode from '!!raw-loader!/_includes/code/howto/java/src/test/java/io/weaviate/docs/quickstart/NearText.java';
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+```bash
+# Best practice: store your credentials in environment variables
+# export WEAVIATE_URL="YOUR_INSTANCE_URL" # Your Weaviate instance URL
+# export WEAVIATE_API_KEY="YOUR_API_KEY" # Your Weaviate instance API key
+
+echo '{
+ "query": "{
+ Get {
+ Question (
+ limit: 2
+ nearText: {
+ concepts: [\"biology\"],
+ }
+ ) {
+ question
+ answer
+ category
+ }
+ }
+ }"
+}' | tr -d "\n" | curl \
+ -X POST \
+ -H 'Content-Type: application/json' \
+ -H "Authorization: Bearer $WEAVIATE_API_KEY" \
+ -d @- \
+ $WEAVIATE_URL/v1/graphql
+```
+
+
+
diff --git a/_includes/code/quickstart/quickstart.short.query.neartext.mdx b/_includes/code/quickstart/quickstart.short.query.neartext.mdx
new file mode 100644
index 00000000..1dc96e77
--- /dev/null
+++ b/_includes/code/quickstart/quickstart.short.query.neartext.mdx
@@ -0,0 +1,86 @@
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+import FilteredTextBlock from '@site/src/components/Documentation/FilteredTextBlock';
+import PyCode from '!!raw-loader!/_includes/code/python/quickstart.short.query.neartext.py';
+import TSCode from '!!raw-loader!/_includes/code/typescript/quickstart.query.neartext.ts';
+import GoCode from '!!raw-loader!/_includes/code/howto/go/docs/quickstart/3_1_neartext/main.go';
+import JavaCode from '!!raw-loader!/_includes/code/howto/java/src/test/java/io/weaviate/docs/quickstart/NearText.java';
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+```bash
+# Best practice: store your credentials in environment variables
+# export WEAVIATE_URL="YOUR_INSTANCE_URL" # Your Weaviate instance URL
+# export WEAVIATE_API_KEY="YOUR_API_KEY" # Your Weaviate instance API key
+
+echo '{
+ "query": "{
+ Get {
+ Question (
+ limit: 2
+ nearText: {
+ concepts: [\"biology\"],
+ }
+ ) {
+ question
+ answer
+ category
+ }
+ }
+ }"
+}' | tr -d "\n" | curl \
+ -X POST \
+ -H 'Content-Type: application/json' \
+ -H "Authorization: Bearer $WEAVIATE_API_KEY" \
+ -d @- \
+ $WEAVIATE_URL/v1/graphql
+```
+
+
+
diff --git a/_includes/code/quickstart/quickstart.short.query.rag.mdx b/_includes/code/quickstart/quickstart.short.query.rag.mdx
new file mode 100644
index 00000000..7f4783be
--- /dev/null
+++ b/_includes/code/quickstart/quickstart.short.query.rag.mdx
@@ -0,0 +1,91 @@
+import Tabs from "@theme/Tabs";
+import TabItem from "@theme/TabItem";
+import FilteredTextBlock from "@site/src/components/Documentation/FilteredTextBlock";
+import PyCode from "!!raw-loader!/_includes/code/python/quickstart.short.query.rag.py";
+import TSCode from "!!raw-loader!/_includes/code/typescript/quickstart.query.rag.ts";
+import GoCode from "!!raw-loader!/_includes/code/howto/go/docs/quickstart/3_2_rag/main.go";
+import JavaCode from "!!raw-loader!/_includes/code/howto/java/src/test/java/io/weaviate/docs/quickstart/RAG.java";
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+```bash
+# Best practice: store your credentials in environment variables
+# export WEAVIATE_URL="YOUR_INSTANCE_URL" # Your Weaviate instance URL
+# export WEAVIATE_API_KEY="YOUR_API_KEY" # Your Weaviate instance API key
+# export COHERE_APIKEY="YOUR_API_KEY" # Your Cohere API key
+
+echo '{
+ "query": "{
+ Get {
+ Question (
+ limit: 2
+ nearText: {
+ concepts: [\"biology\"],
+ }
+ ) {
+ question
+ answer
+ category
+ _additional {
+ generate(
+ groupedResult: {
+ task: \"\"\"
+ Write a tweet with emojis about this movie.
+ \"\"\"
+ }
+ ) {
+ groupedResult
+ error
+ }
+ }
+ }
+ }
+ }"
+}' | tr -d "\n" | curl \
+ -X POST \
+ -H 'Content-Type: application/json' \
+ -H "Authorization: Bearer $WEAVIATE_API_KEY" \
+ -H "X-Cohere-Api-Key: $COHERE_APIKEY" \
+ -d @- \
+ $WEAVIATE_URL/v1/graphql
+```
+
+
+
diff --git a/docs/weaviate/quickstart/index.md b/docs/weaviate/quickstart/index.md
index d2388e22..967a9280 100644
--- a/docs/weaviate/quickstart/index.md
+++ b/docs/weaviate/quickstart/index.md
@@ -4,82 +4,97 @@ image: og/docs/quickstart-tutorial.jpg
# tags: ['getting started']
---
-import Tabs from '@theme/Tabs';
-import TabItem from '@theme/TabItem';
-import SkipLink from '/src/components/SkipValidationLink'
+import Tabs from "@theme/Tabs";
+import TabItem from "@theme/TabItem";
+import SkipLink from "/src/components/SkipValidationLink";
import CardsSection from "/src/components/CardsSection";
+import Tooltip from "/src/components/Tooltip";
export const quickstartOptions = [
-{
-title: "Vectorize objects on import",
-description:
-"Import objects and vectorize them with the Weaviate Embeddings service.",
-link: "?import=vectorization#create-a-collection",
-icon: "fas fa-compress-alt",
-},
-{
-title: "Import custom vectors",
-description:
-"Import pre-computed vector embeddings.",
-link: "?import=custom-embeddings#create-a-collection",
-icon: "fas fa-puzzle-piece",
-},
+ {
+ title: "Vectorize objects during import",
+ description:
+ "Import objects and vectorize them with the Weaviate Embeddings service.",
+ link: "?import=vectorization",
+ icon: "fas fa-arrows-spin",
+ groupId: "import",
+ activeTab: "vectorization",
+ },
+ {
+ title: "Import vectors",
+ description: "Import pre-computed vector embeddings along with your data.",
+ link: "?import=custom-embeddings",
+ icon: "fas fa-circle-nodes",
+ groupId: "import",
+ activeTab: "custom-embeddings",
+ },
];
-
---
-
+
Weaviate is an open-source vector database built to power AI applications, from prototypes to production-scale systems. This quickstart guide will show you how to:
-1. **Import data** - Create a collection and import data into it. The data will be vectorized with the Weaviate Embeddings service.
-2. **Search** - Perform a similarity (vector) search on your data.
-3. **RAG** - Perform Retrieval augmented generation (RAG) with a generative model.
+1. **Create a collection & import data** - Create a collection and import data into it. The data will be vectorized with the Weaviate Embeddings service.
+2. **Search** - Perform a similarity (vector) search on your data using a text query.
+3. **RAG** - Perform Retrieval Augmented Generation (RAG) with a generative model.
-
+
Weaviate is an open-source vector database built to power AI applications, from prototypes to production-scale systems. This quickstart guide will show you how to:
-1. **Import data** - Create a collection and import data into it.
-2. **Search** - Perform a similarity (vector) search on your data.
-3. **RAG** - Perform Retrieval augmented generation (RAG) with a generative model.
+1. **Create a collection & import data**- Create a collection and import data into it. The data should already contain the vector embedding.
+2. **Search** - Perform a similarity (vector) search on your data using a vector query.
+3. **RAG** - Perform Retrieval Augmented Generation (RAG) with a generative model.
+import KapaAI from '/src/components/KapaAI';
+
+If you encounter any issues along the way or have additional questions, use the Ask AI feature.
## Prerequisites
-- A [Weaviate Cloud](https://console.weaviate.cloud/) Sandbox instance.
+A **[Weaviate Cloud](https://console.weaviate.cloud/)** Sandbox instance - you will need an admin **API key** and a **REST endpoint URL**. See the instructions below for more info.
How to set up a Weaviate Cloud Sandbox instance
Go to the [Weaviate Cloud console](https://console.weaviate.cloud) and create a free Sandbox instance as shown in the interactive example below.
-