-
Notifications
You must be signed in to change notification settings - Fork 5.6k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Vectorize] update docs for Vectorize V2 #15916
Conversation
Deploying cloudflare-docs with Cloudflare Pages
|
@@ -117,6 +117,11 @@ Refer to [Vectorize API](/vectorize/reference/client-api/) for additional exampl | |||
|
|||
### wrangler CLI | |||
|
|||
{{<Aside type="note" header="Cloudflare API rate limit">}} | |||
|
|||
Please use a maximum of 5000 vectors per embeddings.ndjson file to prevent the global [rate limit](/fundamentals/api/reference/limits/) for the Cloudflare API. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think wrangler can read a bigger file, but will batch lines up to 5K
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
That would be correct. Wrangler can split a large file into batches of 5000 for Vectorize V2 and process each batch as a separate insert request. Each batch however must be less than 5000 vectors and less than 128 MB for the insert request to succeed.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Two small changes
To continue: | ||
{{<Aside type="note" header="Workers Paid plan required">}} | ||
|
||
Hyperdrive is available to all users on the [Workers Paid plan](/workers/platform/pricing/#workers). |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Hyperdrive is available to all users on the [Workers Paid plan](/workers/platform/pricing/#workers). | |
Vectorize is available to all users on the [Workers Paid plan](/workers/platform/pricing/#workers). |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
resolved.
{{<Aside type="note" header="Enable metadata filtering">}} | ||
|
||
Vectorize V2 requires to define metadata properties that will support filtering. Please refer to [Vectorize API](/vectorize/reference/client-api/#create-metadata-index) for details. | ||
[Namespaces](/vectorize/best-practices/insert-vectors/#namespaces) support metadata filtering out of the box. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
[Namespaces](/vectorize/best-practices/insert-vectors/#namespaces) support metadata filtering out of the box. | |
[Namespaces](/vectorize/best-practices/insert-vectors/#namespaces) support metadata filtering by default. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
resolved.
@@ -86,6 +86,46 @@ const details = await env.YOUR_INDEX.describe(); | |||
|
|||
Retrieves the configuration of a given index directly, including its configured `dimensions` and distance `metric`. | |||
|
|||
### Create Metadata Index |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Should we include the index info command too?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Should we include the index info command too?
added.
Summary
Vectorize V2 changes: