Skip to content

Commit 9167606

Browse files
committed
add references
1 parent 21944eb commit 9167606

File tree

5 files changed

+173
-123
lines changed

5 files changed

+173
-123
lines changed

src/content/docs/reference-architecture/diagrams/ai/ai-rag.mdx

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -4,6 +4,7 @@ pcx_content_type: reference-architecture-diagram
44
tags:
55
- AI
66
products:
7+
- AutoRAG
78
- Workers AI
89
- Workers
910
- Queues
@@ -25,6 +26,10 @@ Examples for application of these technique includes for instance customer servi
2526

2627
In the context of Retrieval-Augmented Generation (RAG), knowledge seeding involves incorporating external information from pre-existing sources into the generative process, while querying refers to the mechanism of retrieving relevant knowledge from these sources to inform the generation of coherent and contextually accurate text. Both are shown below.
2728

29+
:::note[Looking for a managed option?]
30+
[AutoRAG](/autorag) offers a fully managed way to build RAG pipelines on Cloudflare, handling ingestion, indexing, and querying out of the box. [Get started](/autorag/get-started/).
31+
:::
32+
2833
## Knowledge Seeding
2934

3035
![Figure 1: Knowledge seeding](~/assets/images/reference-architecture/rag-ref-architecture-diagrams/rag-architecture-seeding.svg "Figure 1: Knowledge seeding")
@@ -49,6 +54,7 @@ In the context of Retrieval-Augmented Generation (RAG), knowledge seeding involv
4954

5055
## Related resources
5156

57+
- [Get started with AutoRAG](/autorag/get-started/)
5258
- [Tutorial: Build a RAG AI](/workers-ai/tutorials/build-a-retrieval-augmented-generation-ai/)
5359
- [Workers AI: Text embedding models](/workers-ai/models/)
5460
- [Workers AI: Text generation models](/workers-ai/models/)

src/content/docs/vectorize/index.mdx

Lines changed: 47 additions & 18 deletions
Original file line numberDiff line numberDiff line change
@@ -10,84 +10,113 @@ head:
1010
content: Overview
1111
---
1212

13-
import { CardGrid, Description, Feature, LinkTitleCard, Plan, RelatedProduct, Render } from "~/components"
13+
import {
14+
CardGrid,
15+
Description,
16+
Feature,
17+
LinkTitleCard,
18+
Plan,
19+
RelatedProduct,
20+
Render,
21+
} from "~/components";
1422

1523
<Description>
1624

1725
Build full-stack AI applications with Vectorize, Cloudflare's powerful vector database.
1826

19-
2027
</Description>
2128

2229
Vectorize is a globally distributed vector database that enables you to build full-stack, AI-powered applications with [Cloudflare Workers](/workers/). Vectorize makes querying embeddings — representations of values or objects like text, images, audio that are designed to be consumed by machine learning models and semantic search algorithms — faster, easier and more affordable.
2330

2431
<Render file="vectorize-ga" />
2532

26-
2733
For example, by storing the embeddings (vectors) generated by a machine learning model, including those built-in to [Workers AI](/workers-ai/) or by bringing your own from platforms like [OpenAI](#), you can build applications with powerful search, similarity, recommendation, classification and/or anomaly detection capabilities based on your own data.
2834

2935
The vectors returned can reference images stored in Cloudflare R2, documents in KV, and/or user profiles stored in D1 — enabling you to go from vector search result to concrete object all within the Workers platform, and without standing up additional infrastructure.
3036

31-
***
37+
---
3238

3339
## Features
3440

3541
<Feature header="Vector database" href="/vectorize/get-started/intro/" cta="Create your Vector database">
3642

3743
Learn how to create your first Vectorize database, upload vector embeddings, and query those embeddings from [Cloudflare Workers](/workers/).
3844

39-
4045
</Feature>
4146

4247
<Feature header="Vector embeddings using Workers AI" href="/vectorize/get-started/embeddings/" cta="Create vector embeddings using Workers AI">
4348

4449
Learn how to use Vectorize to generate vector embeddings using Workers AI.
4550

51+
</Feature>
52+
53+
<Feature header="Search using Vectorize and AutoRAG" href="/autorag" cta="Build a RAG with Vectorize">
54+
55+
Learn how to automatically index your data and store it in Vectorize, then query it to generate context-aware responses using AutoRAG.
4656

4757
</Feature>
4858

49-
***
59+
---
5060

5161
## Related products
5262

5363
<RelatedProduct header="Workers AI" href="/workers-ai/" product="workers-ai">
5464

5565
Run machine learning models, powered by serverless GPUs, on Cloudflare’s global network.
5666

57-
5867
</RelatedProduct>
5968

6069
<RelatedProduct header="R2 Storage" href="/r2/" product="r2">
6170

6271
Store large amounts of unstructured data without the costly egress bandwidth fees associated with typical cloud storage services.
6372

64-
6573
</RelatedProduct>
6674

67-
***
75+
---
6876

6977
## More resources
7078

7179
<CardGrid>
7280

73-
<LinkTitleCard title="Limits" href="/vectorize/platform/limits/" icon="document">
74-
Learn about Vectorize limits and how to work within them.
81+
<LinkTitleCard
82+
title="Limits"
83+
href="/vectorize/platform/limits/"
84+
icon="document"
85+
>
86+
Learn about Vectorize limits and how to work within them.
7587
</LinkTitleCard>
7688

7789
<LinkTitleCard title="Use cases" href="/use-cases/ai/" icon="document">
78-
Learn how you can build and deploy ambitious AI applications to Cloudflare's global network.
90+
Learn how you can build and deploy ambitious AI applications to Cloudflare's
91+
global network.
7992
</LinkTitleCard>
8093

81-
<LinkTitleCard title="Storage options" href="/workers/platform/storage-options/" icon="document">
82-
Learn more about the storage and database options you can build on with Workers.
94+
<LinkTitleCard
95+
title="Storage options"
96+
href="/workers/platform/storage-options/"
97+
icon="document"
98+
>
99+
Learn more about the storage and database options you can build on with
100+
Workers.
83101
</LinkTitleCard>
84102

85-
<LinkTitleCard title="Developer Discord" href="https://discord.cloudflare.com" icon="discord">
86-
Connect with the Workers community on Discord to ask questions, join the `#vectorize` channel to show what you are building, and discuss the platform with other developers.
103+
<LinkTitleCard
104+
title="Developer Discord"
105+
href="https://discord.cloudflare.com"
106+
icon="discord"
107+
>
108+
Connect with the Workers community on Discord to ask questions, join the
109+
`#vectorize` channel to show what you are building, and discuss the platform
110+
with other developers.
87111
</LinkTitleCard>
88112

89-
<LinkTitleCard title="@CloudflareDev" href="https://x.com/cloudflaredev" icon="x.com">
90-
Follow @CloudflareDev on Twitter to learn about product announcements, and what is new in Cloudflare Developer Platform.
113+
<LinkTitleCard
114+
title="@CloudflareDev"
115+
href="https://x.com/cloudflaredev"
116+
icon="x.com"
117+
>
118+
Follow @CloudflareDev on Twitter to learn about product announcements, and
119+
what is new in Cloudflare Developer Platform.
91120
</LinkTitleCard>
92121

93122
</CardGrid>

src/content/docs/vectorize/reference/what-is-a-vector-database.mdx

Lines changed: 12 additions & 12 deletions
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,6 @@ title: Vector databases
33
pcx_content_type: concept
44
sidebar:
55
order: 2
6-
76
---
87

98
Vector databases are a key part of building scalable AI-powered applications. Vector databases provide long term memory, on top of an existing machine learning model.
@@ -14,10 +13,10 @@ Without a vector database, you would need to train your model (or models) or re-
1413

1514
A vector database determines what other data (represented as vectors) is near your input query. This allows you to build different use-cases on top of a vector database, including:
1615

17-
* Semantic search, used to return results similar to the input of the query.
18-
* Classification, used to return the grouping (or groupings) closest to the input query.
19-
* Recommendation engines, used to return content similar to the input based on different criteria (for example previous product sales, or user history).
20-
* Anomaly detection, used to identify whether specific data points are similar to existing data, or different.
16+
- Semantic search, used to return results similar to the input of the query.
17+
- Classification, used to return the grouping (or groupings) closest to the input query.
18+
- Recommendation engines, used to return content similar to the input based on different criteria (for example previous product sales, or user history).
19+
- Anomaly detection, used to identify whether specific data points are similar to existing data, or different.
2120

2221
Vector databases can also power [Retrieval Augmented Generation](https://arxiv.org/abs/2005.11401) (RAG) tasks, which allow you to bring additional context to LLMs (Large Language Models) by using the context from a vector search to augment the user prompt.
2322

@@ -44,16 +43,17 @@ Instead of passing the prompt directly to the LLM, in the RAG approach you:
4443
1. Generate vector embeddings from an existing dataset or corpus (for example, the dataset you want to use to add additional context to the LLMs response). An existing dataset or corpus could be a product documentation, research data, technical specifications, or your product catalog and descriptions.
4544
2. Store the output embeddings in a Vectorize database index.
4645

47-
When a user initiates a prompt, instead of passing it (without additional context) to the LLM, you *augment* it with additional context:
46+
When a user initiates a prompt, instead of passing it (without additional context) to the LLM, you _augment_ it with additional context:
4847

4948
1. The user prompt is passed into the same ML model used for your dataset, returning a vector embedding representation of the query.
5049
2. This embedding is used as the query (semantic search) against the vector database, which returns similar vectors.
5150
3. These vectors are used to look up the content they relate to (if not embedded directly alongside the vectors as metadata).
5251
4. This content is provided as context alongside the original user prompt, providing additional context to the LLM and allowing it to return an answer that is likely to be far more contextual than the standalone prompt.
5352

54-
Refer to the [RAG using Workers AI tutorial](/workers-ai/tutorials/build-a-retrieval-augmented-generation-ai/) to learn how to combine Workers AI and Vectorize for generative AI use-cases.
53+
Create a RAG today with [AutoRAG](/autorag) to deploy a fully managed RAG pipeline in just a few clicks. It automatically sets up Vectorize, handles continuous indexing, and serves responses through a single API.
5554

56-
<sup>1</sup> You can learn more about the theory behind RAG by reading the [RAG paper](https://arxiv.org/abs/2005.11401).
55+
<sup>1</sup> You can learn more about the theory behind RAG by reading the [RAG
56+
paper](https://arxiv.org/abs/2005.11401).
5757

5858
## Terminology
5959

@@ -85,9 +85,9 @@ Refer to the [dimensions](/vectorize/best-practices/create-indexes/#dimensions)
8585

8686
The distance metric is an index used for vector search. It defines how it determines how close your query vector is to other vectors within the index.
8787

88-
* Distance metrics determine how the vector search engine assesses similarity between vectors.
89-
* Cosine, Euclidean (L2), and Dot Product are the most commonly used distance metrics in vector search.
90-
* The machine learning model and type of embedding you use will determine which distance metric is best suited for your use-case.
91-
* Different metrics determine different scoring characteristics. For example, the `cosine` distance metric is well suited to text, sentence similarity and/or document search use-cases. `euclidean` can be better suited for image or speech recognition use-cases.
88+
- Distance metrics determine how the vector search engine assesses similarity between vectors.
89+
- Cosine, Euclidean (L2), and Dot Product are the most commonly used distance metrics in vector search.
90+
- The machine learning model and type of embedding you use will determine which distance metric is best suited for your use-case.
91+
- Different metrics determine different scoring characteristics. For example, the `cosine` distance metric is well suited to text, sentence similarity and/or document search use-cases. `euclidean` can be better suited for image or speech recognition use-cases.
9292

9393
Refer to the [distance metrics](/vectorize/best-practices/create-indexes/#distance-metrics) documentation to learn how to configure a distance metric when creating a Vectorize index.

0 commit comments

Comments
 (0)