vectorize is now generally available (#17118)

pdwittig · elithrar · commit 914a223da152 · 2024-10-15T11:27:44.000+01:00
* vectorize is now generally available

* update for discord channel rename

* remove vectoroize pricing ref on tutorial as should be covewred by free

* add product tage to moved partial

* fix space
diff --git a/src/content/changelogs/vectorize.yaml b/src/content/changelogs/vectorize.yaml
@@ -5,6 +5,11 @@ productLink: "/vectorize/"
 productArea: Developer platform
 productAreaLink: /workers/platform/changelog/platform/
 entries:
+  - publish_date: "2024-09-26"
+    title: Vectorize GA
+    description: |-
+      Vectorize is now generally available
+
   - publish_date: "2024-09-16"
     title: Vectorize is available on Workers Free plan
     description: |-
diff --git a/src/content/docs/developer-spotlight/tutorials/creating-a-recommendation-api.mdx b/src/content/docs/developer-spotlight/tutorials/creating-a-recommendation-api.mdx
@@ -52,11 +52,6 @@ This tutorial involves the use of several Cloudflare products. Some of these pro
 
 <Render file="ai-local-usage-charges" product="workers" />
 
-:::note[Vectorize usage charges]
-
-You will also need access to [Vectorize](/vectorize/platform/pricing/). <Render file="vectorize-pricing" product="workers" />
-:::
-
 ## 1. Create a new Worker project
 
 First, let's create a Cloudflare Workers project.
diff --git a/src/content/docs/vectorize/get-started/embeddings.mdx b/src/content/docs/vectorize/get-started/embeddings.mdx
@@ -7,7 +7,7 @@ sidebar:
 
 import { Render, PackageManagers } from "~/components";
 
-<Render file="vectorize-beta" />
+<Render file="vectorize-ga" />
 
 Vectorize allows you to generate [vector embeddings](/vectorize/reference/what-is-a-vector-database/) using a machine-learning model, including the models available in [Workers AI](/workers-ai/).
 
diff --git a/src/content/docs/vectorize/get-started/intro.mdx b/src/content/docs/vectorize/get-started/intro.mdx
@@ -7,7 +7,7 @@ sidebar:
 
 import { Render, PackageManagers } from "~/components";
 
-<Render file="vectorize-beta" />
+<Render file="vectorize-ga" />
 
 Vectorize is Cloudflare's vector database. Vector databases allow you to use machine learning (ML) models to perform semantic search, recommendation, classification and anomaly detection tasks, as well as provide context to LLMs (Large Language Models).
 
diff --git a/src/content/docs/vectorize/index.mdx b/src/content/docs/vectorize/index.mdx
@@ -5,8 +5,6 @@ type: overview
 pcx_content_type: overview
 sidebar:
   order: 1
-  badge:
-    text: Beta
 head:
   - tag: title
     content: Cloudflare Vectorize
@@ -17,17 +15,15 @@ import { CardGrid, Description, Feature, LinkTitleCard, Plan, RelatedProduct, Re
 
 <Description>
 
-
 Build full-stack AI applications with Vectorize, Cloudflare's powerful vector database.
 
 
 </Description>
 
-<Plan type="workers-paid" />
-
 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.
 
-<Render file="vectorize-beta" />
+<Render file="vectorize-ga" />
+
 
 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.
 
diff --git a/src/content/docs/vectorize/platform/limits.mdx b/src/content/docs/vectorize/platform/limits.mdx
@@ -5,33 +5,25 @@ sidebar:
   order: 2
 ---
 
-:::note
-
-Many of these limits will increase during Vectorize's [public beta](/workers/platform/betas/). Refer to the [changelog](/vectorize/platform/changelog/) or join the [`#vectorize-beta`](https://discord.cloudflare.com/) channel in the Cloudflare Developer Discord to keep up to date with changes.
-
-:::
-
 The following limits apply to accounts, indexes and vectors (as specified):
 
 | Feature                                                       | Current Limit                                                    |
 | ------------------------------------------------------------- | ---------------------------------------------------------------- |
-| Indexes per account                                           | 100 indexes <sup>beta</sup>                                      |
-| Maximum dimensions per vector                                 | 1536 dimensions <sup>beta</sup>                                  |
+| Indexes per account                                           | 100 indexes                                                      |
+| Maximum dimensions per vector                                 | 1536 dimensions                                                  |
 | Maximum vector ID length                                      | 64 bytes                                                         |
-| Metadata per vector                                           | 10KiB <sup>beta</sup>                                            |
-| Maximum returned results (`topK`) with values or metadata     | 20 <sup>beta</sup>                                               |
-| Maximum returned results (`topK`) without values and metadata | 100 <sup>beta</sup>                                              |
-| Maximum upsert batch size (per batch)                         | 1000 <sup>beta</sup> (Workers) / 5000 <sup>beta</sup> (HTTP API) |
+| Metadata per vector                                           | 10KiB                                                            |
+| Maximum returned results (`topK`) with values or metadata     | 20                                                               |
+| Maximum returned results (`topK`) without values and metadata | 100                                                              |
+| Maximum upsert batch size (per batch)                         | 1000 (Workers) / 5000 (HTTP API)                                 |
 | Maximum index name length                                     | 64 bytes                                                         |
-| Maximum vectors per index                                     | 5,000,000 <sup>beta</sup>                                        |
-| Maximum namespaces per index                                  | 1000 namespaces <sup>beta</sup>                                  |
+| Maximum vectors per index                                     | 5,000,000                                                        |
+| Maximum namespaces per index                                  | 1000 namespaces                                                  |
 | Maximum namespace name length                                 | 64 bytes                                                         |
 | Maximum vectors upload size                                   | 100 MB                                                           |
 | Maximum metadata indexes per Vectorize index                  | 10                                                               |
 | Maximum indexed data per metadata index per vector            | 64 bytes                                                         |
 
-<sup>beta</sup> This limit is beta only and is expected to increase over time.
-
 ## Limits V1 (deprecated)
 
 The following limits apply to accounts, indexes and vectors (as specified):
diff --git a/src/content/docs/vectorize/platform/pricing.mdx b/src/content/docs/vectorize/platform/pricing.mdx
@@ -7,11 +7,7 @@ sidebar:
 
 import { Render } from "~/components";
 
-:::note
-
-Vectorize is currently in public beta and is free to use on [Workers Free or Paid plans](/workers/platform/pricing/#workers).
-
-:::
+<Render file="vectorize-ga" />
 
 Vectorize bills based on:
 
@@ -22,19 +18,19 @@ You are not billed for CPU, memory, "active index hours", or the number of index
 
 ## Billing metrics
 
-<Render file="vectorize-pricing" product="workers" />
+<Render file="vectorize-pricing" />
 
 ### Usage examples
 
 The following table defines a number of example use-cases and the estimated monthly cost for querying a Vectorize index. These estimates do not include the Vectorize usage that is part of the Workers Free and Paid plans.
 
-| Workload   | Dimensions per vector | Stored dimensions | Queries per month | Calculation                             | Estimated total                |
-| ---------- | --------------------- | ----------------- | ----------------- | --------------------------------------- | ------------------------------ |
-| Experiment | 384                   | 5,000 vectors     | 10,000            | `(5000+10000)*384*(0.040/1000000)`      | $0.24 / mo <sup>included</sup> |
-| Scaling    | 768                   | 25,000 vectors    | 50,000            | `(25000+50000)*768*(0.040/1000000)`     | $2.31 / mo <sup>partial</sup>  |
-| Production | 768                   | 50,000 vectors    | 200,000           | `(50000+200000)*768*(0.040/1000000)`    | $7.68 / mo                     |
-| Large      | 768                   | 250,000 vectors   | 500,000           | `(250000+500000)*768*(0.040/1000000)`   | $23.04 / mo                    |
-| XL         | 1536                  | 500,000 vectors   | 1,000,000         | `(500000+1000000)*1536*(0.040/1000000)` | $92.16 / mo                    |
+| Workload   | Dimensions per vector | Stored dimensions | Queries per month | Calculation                                                      | Estimated total                |
+| ---------- | --------------------- | ----------------- | ----------------- | ---------------------------------------------------------------- | ------------------------------ |
+| Experiment | 384                   | 5,000 vectors     | 10,000            | `(10000*384*(0.01/1000000))    + (5000*384*(0.05/100000000))`    | $0.04 / mo <sup>included</sup> |
+| Scaling    | 768                   | 25,000 vectors    | 50,000            | `(50000*768*(0.01/1000000))    + (25000*768*(0.05/100000000))`   | $0.39 / mo <sup>partial</sup>  |
+| Production | 768                   | 50,000 vectors    | 200,000           | `(200000*768*(0.01/1000000))   + (50000*768*(0.05/100000000))`   | $1.56 / mo                     |
+| Large      | 768                   | 250,000 vectors   | 500,000           | `(500000*768*(0.01/1000000))   + (250000*768*(0.05/100000000))`  | $3.94 / mo                     |
+| XL         | 1536                  | 500,000 vectors   | 1,000,000         | `(1000000*1536*(0.01/1000000)) + (500000*1536*(0.05/100000000))` | $15.74 / mo                    |
 
 <sup>included</sup> All of this usage would fall into the Vectorize usage
 included in the Workers Free or Paid plan.
@@ -46,10 +42,6 @@ within the Workers Paid plan.
 
 Frequently asked questions related to Vectorize pricing:
 
-- When will Vectorize start charging me?
-
-We intend to enable billing for Vectorize usage in January 2024.
-
 - Will Vectorize always have a free tier?
 
 Yes, the [Workers free tier](/workers/platform/pricing/#workers) will always include the ability to prototype and experiment with Vectorize for free.
diff --git a/src/content/docs/workers/platform/pricing.mdx b/src/content/docs/workers/platform/pricing.mdx
@@ -170,7 +170,7 @@ For more information and [examples of Durable Objects billing](/durable-objects/
 
 Vectorize is currently only available on the Workers paid plan.
 
-<Render file="vectorize-pricing" />
+<Render file="vectorize-pricing" product="vectorize" />
 
 ## Service bindings
 
diff --git a/src/content/partials/vectorize/vectorize-beta.mdx b/src/content/partials/vectorize/vectorize-beta.mdx
diff --git a/src/content/partials/vectorize/vectorize-ga.mdx b/src/content/partials/vectorize/vectorize-ga.mdx
@@ -0,0 +1,12 @@
+---
+{}
+
+---
+
+:::note[Vectorize is now Generally Available]
+
+
+To report bugs or give feedback, go to the [#vectorize Discord channel](https://discord.cloudflare.com). If you are having issues with Wrangler, report issues in the [Wrangler GitHub repository](https://github.com/cloudflare/workers-sdk/issues/new/choose).
+
+
+:::
diff --git a/src/content/partials/vectorize/vectorize-pricing.mdx b/src/content/partials/vectorize/vectorize-pricing.mdx
@@ -4,12 +4,12 @@
 
 |                                     | [Workers Paid](/workers/platform/pricing/#workers)                               | [Workers Free](/workers/platform/pricing/#workers) |
 | ----------------------------------- | -------------------------------------------------------------------------------- | -------------------------------------------------- |
-| **Total queried vector dimensions** | First 50 million queried vector dimensions / month included + $0.040 per million | 30 million queried vector dimensions / month       |
-| **Total stored vector dimensions**  | First 10 million stored vector dimensions + $0.040 per million                   | 5 million stored vector dimensions                 |
+| **Total queried vector dimensions** | First 50 million queried vector dimensions / month included + $0.01 per million  | 30 million queried vector dimensions / month       |
+| **Total stored vector dimensions**  | First 10 million stored vector dimensions + $0.05 per 100 million                | 5 million stored vector dimensions                 |
 
 ### Calculating vector dimensions
 
-To calculate your potential usage, calculate the sum of your stored + queried vectors, multiply by the dimension size, and multiply by the unit price (divided by 1 million). The formula is defined as `(stored vectors + queried vectors) * dimensions * ($0.040 / 1000000)`
+To calculate your potential usage, calculate the sum of your stored + queried vectors, multiply by the dimension size, and multiply by the unit price. The formula is defined as `(queried vectors * dimensions * ($0.01 / 1000000) + (stored vectors + dimensions * ($0.05 / 100000000)`
 
 - For example, inserting 10,000 vectors of 768 dimensions each, and querying those 1,000 times per day (30,000 times per month) would be calculated as `(30000 * 768) = 23,040,000` queried dimensions and `(10000 * 768) = 7,680,000` stored dimensions (within the included monthly allocation)
-- Separately, and excluding the included monthly allocation, this would be calculated as `(30,000+10,000) * 768 * ($0.040 / 1,000,000)` and sum to $1.23 per month.
+- Separately, and excluding the included monthly allocation, this would be calculated as `(30,000 * 768 * ($0.01 / 1,000,000) + (10,000 * 768 * ($0.05 / 100,000,000)` and sum to $0.23 per month.

-Original file line number
+Diff line change
@@ @@ -0,0 +1,12 @@ @@
 +---
 +{}
++
 +---
++
 +:::note[Vectorize is now Generally Available]
++
++
 +To report bugs or give feedback, go to the [#vectorize Discord channel](https://discord.cloudflare.com). If you are having issues with Wrangler, report issues in the [Wrangler GitHub repository](https://github.com/cloudflare/workers-sdk/issues/new/choose).
++
++
 +:::