Skip to content

[Workers AI] Adds Batch Pill and Feature #21604

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.

Sign up for GitHub

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

Merged
merged 4 commits into from
Apr 10, 2025
Merged

[Workers AI] Adds Batch Pill and Feature #21604

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
cd7f1a6
Adds Batch Pill and Feature
craigsdennis Apr 10, 2025
202c0f6
Added filters
kodster28 Apr 10, 2025
baf302b
Merge branch 'production' into add-async-queue-marks
kodster28 Apr 10, 2025
676d562
docs gen update
kodster28 Apr 10, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions src/components/ModelCatalog.tsx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -80,6 +80,10 @@ const ModelCatalog = ({ models }: { models: WorkersAIModelsSchema[] }) => {
return "Function calling";
}

if (property_id === "async_queue" && value === "true") {
return "Batch";
}

return [];
})
.filter((p) => Boolean(p)),
Expand All @@ -102,6 +106,10 @@ const ModelCatalog = ({ models }: { models: WorkersAIModelsSchema[] }) => {
return "Function calling";
}

if (property_id === "async_queue" && value === "true") {
return "Batch";
}

return [];
})
.filter((p) => Boolean(p)),
Expand Down
7 changes: 7 additions & 0 deletions src/components/models/ModelBadges.tsx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,13 @@ const ModelBadges = ({ model }: { model: WorkersAIModelsSchema }) => {
};
}

if (property_id === "async_queue" && value === "true") {
return {
variant: "note",
text: "Batch",
};
}

if (property_id === "planned_deprecation_date") {
const timestamp = Math.floor(new Date(value as string).getTime() / 1000);

Expand Down
6 changes: 6 additions & 0 deletions src/components/models/ModelFeatures.tsx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -110,6 +110,12 @@ const ModelFeatures = ({ model }: { model: WorkersAIModelsSchema }) => {
<td>Yes</td>
</tr>
)}
{properties.async_queue && (
<tr>
<td>Batch</td>
<td>Yes</td>
</tr>
)}
{properties.price && properties.price.length > 0 && (
<tr>
<td>Unit Pricing</td>
Expand Down
10 changes: 10 additions & 0 deletions src/content/workers-ai-models/bart-large-cnn.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,16 @@
{
"property_id": "beta",
"value": "true"
},
{
"property_id": "price",
"value": [
{
"unit": "per M input tokens",
"price": 0,
"currency": "USD"
}
]
}
],
"schema": {
Expand Down
152 changes: 119 additions & 33 deletions src/content/workers-ai-models/bge-base-en-v1.5.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,10 @@
"created_at": "2023-09-25 19:21:11.898",
"tags": [],
"properties": [
{
"property_id": "async_queue",
"value": "true"
},
{
"property_id": "price",
"value": [
Expand All @@ -37,53 +41,135 @@
"schema": {
"input": {
"type": "object",
"properties": {
"text": {
"oneOf": [
{
"type": "string",
"description": "The text to embed",
"minLength": 1
"oneOf": [
{
"properties": {
"text": {
"oneOf": [
{
"type": "string",
"description": "The text to embed",
"minLength": 1
},
{
"type": "array",
"description": "Batch of text values to embed",
"items": {
"type": "string",
"description": "The text to embed",
"minLength": 1
},
"maxItems": 100
}
]
},
{
"pooling": {
"type": "string",
"enum": [
"mean",
"cls"
],
"default": "mean",
"description": "The pooling method used in the embedding process. `cls` pooling will generate more accurate embeddings on larger inputs - however, embeddings created with cls pooling are not compatible with embeddings generated with mean pooling. The default pooling method is `mean` in order for this to not be a breaking change, but we highly suggest using the new `cls` pooling for better accuracy."
}
},
"required": [
"text"
]
},
{
"properties": {
"requests": {
"type": "array",
"description": "Batch of text values to embed",
"description": "Batch of the embeddings requests to run using async-queue",
"items": {
"type": "string",
"description": "The text to embed",
"minLength": 1
},
"maxItems": 100
"properties": {
"text": {
"oneOf": [
{
"type": "string",
"description": "The text to embed",
"minLength": 1
},
{
"type": "array",
"description": "Batch of text values to embed",
"items": {
"type": "string",
"description": "The text to embed",
"minLength": 1
},
"maxItems": 100
}
]
},
"pooling": {
"type": "string",
"enum": [
"mean",
"cls"
],
"default": "mean",
"description": "The pooling method used in the embedding process. `cls` pooling will generate more accurate embeddings on larger inputs - however, embeddings created with cls pooling are not compatible with embeddings generated with mean pooling. The default pooling method is `mean` in order for this to not be a breaking change, but we highly suggest using the new `cls` pooling for better accuracy."
}
},
"required": [
"text"
]
}
}
},
"required": [
"requests"
]
}
},
"required": [
"text"
]
},
"output": {
"type": "object",
"contentType": "application/json",
"properties": {
"shape": {
"type": "array",
"items": {
"type": "number"
"oneOf": [
{
"type": "object",
"contentType": "application/json",
"properties": {
"shape": {
"type": "array",
"items": {
"type": "number"
}
},
"data": {
"type": "array",
"description": "Embeddings of the requested text values",
"items": {
"type": "array",
"description": "Floating point embedding representation shaped by the embedding model",
"items": {
"type": "number"
}
}
},
"pooling": {
"type": "string",
"enum": [
"mean",
"cls"
],
"description": "The pooling method used in the embedding process."
}
}
},
"data": {
"type": "array",
"description": "Embeddings of the requested text values",
"items": {
"type": "array",
"description": "Floating point embedding representation shaped by the embedding model",
"items": {
"type": "number"
{
"type": "object",
"contentType": "application/json",
"title": "Async response",
"properties": {
"request_id": {
"type": "string",
"description": "The async request id that can be used to obtain the results."
}
}
}
}
]
}
}
}
Loading
Loading