feat(embeddings): multi-provider Embeddings block on a shared core

apps/docs/components/icons.tsx

@@ -2412,6 +2412,36 @@ export function ImageIcon(props: SVGProps<SVGSVGElement>) {
   )
 }
 
+export function EmbeddingsIcon(props: SVGProps<SVGSVGElement>) {
+  return (
+    <svg
+      {...props}
+      width='26'
+      height='26'
+      viewBox='0 0 26 26'
+      fill='none'
+      xmlns='http://www.w3.org/2000/svg'
+      stroke='currentColor'
+      strokeWidth='2'
+      strokeLinecap='round'
+      strokeLinejoin='round'
+    >
+      {/* Rays sit below the nodes in weight, but not so far below that they
+          wash out to loose dots at the 14px search-row size. */}
+      <path
+        d='M13 13L5.5 6.5M13 13L21 7M13 13L6.5 20M13 13L21 19'
+        strokeWidth='1.6'
+        opacity='0.9'
+      />
+      <circle cx='13' cy='13' r='3.1' fill='currentColor' stroke='none' />
+      <circle cx='5.5' cy='6.5' r='1.9' fill='currentColor' stroke='none' />
+      <circle cx='21' cy='7' r='1.9' fill='currentColor' stroke='none' />
+      <circle cx='6.5' cy='20' r='1.9' fill='currentColor' stroke='none' />
+      <circle cx='21' cy='19' r='1.9' fill='currentColor' stroke='none' />
+    </svg>
+  )
+}
+
 export function TypeformIcon(props: SVGProps<SVGSVGElement>) {
   return (
     <svg

apps/docs/components/ui/icon-mapping.ts

@@ -66,6 +66,7 @@ import {
   ElasticsearchIcon,
   ElevenLabsIcon,
   EmailBisonIcon,
+  EmbeddingsIcon,
   EnrichmentIcon,
   EnrichSoIcon,
   EnrowIcon,
@@ -317,6 +318,7 @@ export const blockTypeToIconMap: Record<string, IconComponent> = {
   elasticsearch: ElasticsearchIcon,
   elevenlabs: ElevenLabsIcon,
   emailbison: EmailBisonIcon,
+  embeddings: EmbeddingsIcon,
   enrich: EnrichSoIcon,
   enrichment: EnrichmentIcon,
   enrow: EnrowIcon,

apps/docs/content/docs/en/integrations/embeddings.mdx

@@ -0,0 +1,130 @@
+---
+title: Embeddings
+description: Generate embeddings
+---
+
+import { BlockInfoCard } from "@/components/ui/block-info-card"
+
+<BlockInfoCard 
+  type="embeddings"
+  color="#7B4DFF"
+/>
+
+{/* MANUAL-CONTENT-START:intro */}
+An embedding turns a piece of text into a list of numbers that captures its meaning. Two texts that mean similar things get similar numbers, so you can compare meaning directly instead of matching keywords. That is what powers semantic search, grouping related items, and spotting near-duplicates that are worded differently.
+
+The Embeddings block generates those numbers using OpenAI, Google Gemini, Cohere, or Mistral. Pick a provider, pick one of its models, pass in text, and get a vector back — one vector per input, in the order you supplied them. You can embed a single string or a list of strings in one call.
+
+Models differ in what they are good at and what they cost. `text-embedding-3-small` is the cost-efficient general choice, `gemini-embedding-001` gives the highest retrieval quality, `embed-v4.0` handles multilingual content, and `codestral-embed` is tuned for source code. Some models also let you trade vector size against quality, and some accept a task type so the vector is conditioned for how it will be used — the block only offers those controls for the models that actually support them.
+
+Two things worth knowing before you build on it. Vectors are only comparable when they come from the same model at the same size, so changing either means re-embedding everything you intend to compare. And input longer than the model's limit is shortened to fit rather than rejected, with a warning in the run, so chunk long documents yourself when the tail matters.
+
+Sim's knowledge bases embed separately, at a fixed vector width and from a smaller set of models. This block is for embedding text yourself inside a workflow.
+{/* MANUAL-CONTENT-END */}
+
+
+## Usage Instructions
+
+Turn text into embedding vectors for semantic search, clustering, and similarity. Supports OpenAI, Google Gemini, Cohere, and Mistral embedding models.
+
+
+
+## Actions
+
+### `embeddings_openai`
+
+Generate embeddings from text using OpenAI's embedding models
+
+#### Input
+
+| Parameter | Type | Required | Description |
+| --------- | ---- | -------- | ----------- |
+| `input` | string | Yes | Text to embed, or an array of texts to embed in one call |
+| `model` | string | No | Embedding model to use |
+| `taskType` | string | No | What the embedding is for, when the model supports task conditioning: document, query, similarity, classification, or clustering |
+| `dimensions` | number | No | Output dimensions, when the model supports truncation. Defaults to native. |
+| `apiKey` | string | Yes | API key for the selected embedding provider |
+
+#### Output
+
+| Parameter | Type | Description |
+| --------- | ---- | ----------- |
+| `embeddings` | json | Generated embeddings |
+| `model` | string | Model used |
+| `provider` | string | Provider used |
+| `dimensions` | number | Dimensionality of each vector |
+| `usage` | json | Token usage |
+
+### `embeddings_gemini`
+
+Generate embeddings from text using Google's Gemini embedding models
+
+#### Input
+
+| Parameter | Type | Required | Description |
+| --------- | ---- | -------- | ----------- |
+| `input` | string | Yes | Text to embed, or an array of texts to embed in one call |
+| `model` | string | No | Embedding model to use |
+| `taskType` | string | No | What the embedding is for, when the model supports task conditioning: document, query, similarity, classification, or clustering |
+| `dimensions` | number | No | Output dimensions, when the model supports truncation. Defaults to native. |
+| `apiKey` | string | Yes | API key for the selected embedding provider |
+
+#### Output
+
+| Parameter | Type | Description |
+| --------- | ---- | ----------- |
+| `embeddings` | json | Generated embeddings |
+| `model` | string | Model used |
+| `provider` | string | Provider used |
+| `dimensions` | number | Dimensionality of each vector |
+| `usage` | json | Token usage |
+
+### `embeddings_cohere`
+
+Generate embeddings from text using Cohere's embedding models
+
+#### Input
+
+| Parameter | Type | Required | Description |
+| --------- | ---- | -------- | ----------- |
+| `input` | string | Yes | Text to embed, or an array of texts to embed in one call |
+| `model` | string | No | Embedding model to use |
+| `taskType` | string | No | What the embedding is for, when the model supports task conditioning: document, query, similarity, classification, or clustering |
+| `dimensions` | number | No | Output dimensions, when the model supports truncation. Defaults to native. |
+| `apiKey` | string | Yes | API key for the selected embedding provider |
+
+#### Output
+
+| Parameter | Type | Description |
+| --------- | ---- | ----------- |
+| `embeddings` | json | Generated embeddings |
+| `model` | string | Model used |
+| `provider` | string | Provider used |
+| `dimensions` | number | Dimensionality of each vector |
+| `usage` | json | Token usage |
+
+### `embeddings_mistral`
+
+Generate embeddings from text using Mistral's embedding models
+
+#### Input
+
+| Parameter | Type | Required | Description |
+| --------- | ---- | -------- | ----------- |
+| `input` | string | Yes | Text to embed, or an array of texts to embed in one call |
+| `model` | string | No | Embedding model to use |
+| `taskType` | string | No | What the embedding is for, when the model supports task conditioning: document, query, similarity, classification, or clustering |
+| `dimensions` | number | No | Output dimensions, when the model supports truncation. Defaults to native. |
+| `apiKey` | string | Yes | API key for the selected embedding provider |
+
+#### Output
+
+| Parameter | Type | Description |
+| --------- | ---- | ----------- |
+| `embeddings` | json | Generated embeddings |
+| `model` | string | Model used |
+| `provider` | string | Provider used |
+| `dimensions` | number | Dimensionality of each vector |
+| `usage` | json | Token usage |
+
+

apps/docs/content/docs/en/integrations/exa.mdx

@@ -71,8 +71,6 @@ Search the web using Exa AI. Returns relevant search results with titles, URLs,
 | `startCrawlDate` | string | No | Deprecated: use startPublishedDate. Only include results crawled on or after this ISO 8601 date |
 | `endCrawlDate` | string | No | Deprecated: use endPublishedDate. Only include results crawled on or before this ISO 8601 date |
 | `apiKey` | string | Yes | Exa AI API Key |
-| `pricing` | custom | No | No description |
-| `rateLimit` | string | No | No description |
 
 #### Output
 
@@ -120,8 +118,6 @@ Retrieve the contents of webpages using Exa AI. Returns the title, text content,
 | `livecrawlTimeout` | number | No | Live crawl timeout in milliseconds \(max 90000\). Default: 10000 |
 | `livecrawl` | string | No | Deprecated: use maxAgeHours instead. Live crawling mode: never, fallback, always, or preferred |
 | `apiKey` | string | Yes | Exa AI API Key |
-| `pricing` | custom | No | No description |
-| `rateLimit` | string | No | No description |
 
 #### Output
 
@@ -162,8 +158,6 @@ Find webpages similar to a given URL using Exa AI. Deprecated by Exa in favor of
 | `livecrawlTimeout` | number | No | Live crawl timeout in milliseconds \(max 90000\). Default: 10000 |
 | `livecrawl` | string | No | Deprecated: use maxAgeHours instead. Live crawling mode: never, fallback, always, or preferred |
 | `apiKey` | string | Yes | Exa AI API Key |
-| `pricing` | custom | No | No description |
-| `rateLimit` | string | No | No description |
 
 #### Output
 
@@ -191,8 +185,6 @@ Get an AI-generated answer to a question with citations from the web using Exa A
 | `text` | boolean | No | Include the full page text of each cited source \(default: false\). This does not affect the answer itself. |
 | `outputSchema` | json | No | JSON Schema describing the answer shape. When supplied, the answer is returned as a structured object instead of a string. |
 | `apiKey` | string | Yes | Exa AI API Key |
-| `pricing` | custom | No | No description |
-| `rateLimit` | string | No | No description |
 
 #### Output
 
@@ -222,8 +214,6 @@ Run a deep research task with Exa Agent. Handles multi-step list building, enric
 | `systemPrompt` | string | No | Additional guidance for how the agent should behave or format its answer |
 | `previousRunId` | string | No | ID of a completed agent run to continue from, for follow-up questions |
 | `apiKey` | string | Yes | Exa AI API Key |
-| `pricing` | custom | No | No description |
-| `rateLimit` | string | No | No description |
 
 #### Output
 

apps/docs/content/docs/en/integrations/google_books.mdx

@@ -46,8 +46,6 @@ Search for books using the Google Books API
 | `startIndex` | number | No | Index of the first result to return \(for pagination\) |
 | `maxResults` | number | No | Maximum number of results to return \(1-40\) |
 | `langRestrict` | string | No | Restrict results to a specific language \(ISO 639-1 code\) |
-| `pricing` | per_request | No | No description |
-| `rateLimit` | string | No | No description |
 
 #### Output
 
@@ -84,8 +82,6 @@ Get detailed information about a specific book volume
 | `apiKey` | string | Yes | Google Books API key |
 | `volumeId` | string | Yes | The ID of the volume to retrieve |
 | `projection` | string | No | Projection level \(full, lite\) |
-| `pricing` | per_request | No | No description |
-| `rateLimit` | string | No | No description |
 
 #### Output
 

apps/docs/content/docs/en/integrations/google_maps.mdx

@@ -50,8 +50,6 @@ Get current air quality data for a location
 | `lat` | number | Yes | Latitude coordinate |
 | `lng` | number | Yes | Longitude coordinate |
 | `languageCode` | string | No | Language code for the response \(e.g., "en", "es"\) |
-| `pricing` | per_request | No | No description |
-| `rateLimit` | string | No | No description |
 
 #### Output
 
@@ -93,8 +91,6 @@ Get directions and route information between two locations
 | `waypoints` | json | No | Array of intermediate waypoints |
 | `units` | string | No | Unit system: metric or imperial |
 | `language` | string | No | Language code for results \(e.g., en, es, fr\) |
-| `pricing` | per_request | No | No description |
-| `rateLimit` | string | No | No description |
 
 #### Output
 
@@ -139,8 +135,6 @@ Calculate travel distance and time between multiple origins and destinations
 | `avoid` | string | No | Features to avoid: tolls, highways, or ferries |
 | `units` | string | No | Unit system: metric or imperial |
 | `language` | string | No | Language code for results \(e.g., en, es, fr\) |
-| `pricing` | custom | No | No description |
-| `rateLimit` | string | No | No description |
 
 #### Output
 
@@ -169,8 +163,6 @@ Get elevation data for a location
 | `apiKey` | string | Yes | Google Maps API key |
 | `lat` | number | Yes | Latitude coordinate |
 | `lng` | number | Yes | Longitude coordinate |
-| `pricing` | per_request | No | No description |
-| `rateLimit` | string | No | No description |
 
 #### Output
 
@@ -193,8 +185,6 @@ Convert an address into geographic coordinates (latitude and longitude)
 | `address` | string | Yes | The address to geocode |
 | `language` | string | No | Language code for results \(e.g., en, es, fr\) |
 | `region` | string | No | Region bias as a ccTLD code \(e.g., us, uk\) |
-| `pricing` | per_request | No | No description |
-| `rateLimit` | string | No | No description |
 
 #### Output
 
@@ -227,8 +217,6 @@ Geolocate a device using WiFi access points, cell towers, or IP address
 | `considerIp` | boolean | No | Whether to use IP address for geolocation \(default: true\) |
 | `cellTowers` | array | No | Array of cell tower objects with cellId, locationAreaCode, mobileCountryCode, mobileNetworkCode |
 | `wifiAccessPoints` | array | No | Array of WiFi access point objects with macAddress \(required\), signalStrength, etc. |
-| `pricing` | per_request | No | No description |
-| `rateLimit` | string | No | No description |
 
 #### Output
 
@@ -250,8 +238,6 @@ Get detailed information about a specific place
 | `placeId` | string | Yes | Google Place ID |
 | `fields` | string | No | Comma-separated list of fields to return |
 | `language` | string | No | Language code for results \(e.g., en, es, fr\) |
-| `pricing` | per_request | No | No description |
-| `rateLimit` | string | No | No description |
 
 #### Output
 
@@ -306,8 +292,6 @@ Search for places of a given type within a radius of a location
 | `rankPreference` | string | No | How to rank results: POPULARITY \(default\) or DISTANCE |
 | `languageCode` | string | No | Language code for the response \(e.g., en, es\) |
 | `regionCode` | string | No | Region bias as a ccTLD code \(e.g., us, uk\) |
-| `pricing` | per_request | No | No description |
-| `rateLimit` | string | No | No description |
 
 #### Output
 
@@ -342,8 +326,6 @@ Search for places using a text query
 | `language` | string | No | Language code for results \(e.g., en, es, fr\) |
 | `region` | string | No | Region bias as a ccTLD code \(e.g., us, uk\) |
 | `pageToken` | string | No | Token from a previous search response to fetch the next page of results. Wait a couple seconds after receiving the token before using it, or the API returns INVALID_REQUEST |
-| `pricing` | per_request | No | No description |
-| `rateLimit` | string | No | No description |
 
 #### Output
 
@@ -378,8 +360,6 @@ Get a daily pollen forecast (grass, tree, weed) for a location
 | `days` | number | No | Number of forecast days to return \(1-5, defaults to 1\) |
 | `languageCode` | string | No | Language code for the response \(e.g., "en", "es"\) |
 | `plantsDescription` | boolean | No | Include detailed plant descriptions \(defaults to true\) |
-| `pricing` | per_request | No | No description |
-| `rateLimit` | string | No | No description |
 
 #### Output
 
@@ -413,8 +393,6 @@ Convert geographic coordinates (latitude and longitude) into a human-readable ad
 | `lat` | number | Yes | Latitude coordinate |
 | `lng` | number | Yes | Longitude coordinate |
 | `language` | string | No | Language code for results \(e.g., en, es, fr\) |
-| `pricing` | per_request | No | No description |
-| `rateLimit` | string | No | No description |
 
 #### Output
 
@@ -439,8 +417,6 @@ Snap GPS coordinates to the nearest road segment
 | `apiKey` | string | Yes | Google Maps API key with Roads API enabled |
 | `path` | string | Yes | Pipe-separated list of lat,lng coordinates \(e.g., "60.170880,24.942795\|60.170879,24.942796"\) |
 | `interpolate` | boolean | No | Whether to interpolate additional points along the road |
-| `pricing` | per_request | No | No description |
-| `rateLimit` | string | No | No description |
 
 #### Output
 
@@ -466,8 +442,6 @@ Get solar potential and panel insights for the building nearest a location
 | `lat` | number | Yes | Latitude coordinate |
 | `lng` | number | Yes | Longitude coordinate |
 | `requiredQuality` | string | No | Minimum imagery quality to accept \(HIGH, MEDIUM, or BASE\) |
-| `pricing` | per_request | No | No description |
-| `rateLimit` | string | No | No description |
 
 #### Output
 
@@ -525,8 +499,6 @@ Get timezone information for a location
 | `lng` | number | Yes | Longitude coordinate |
 | `timestamp` | number | No | Unix timestamp to determine DST offset \(defaults to current time\) |
 | `language` | string | No | Language code for timezone name \(e.g., en, es, fr\) |
-| `pricing` | per_request | No | No description |
-| `rateLimit` | string | No | No description |
 
 #### Output
 
@@ -552,8 +524,6 @@ Validate and standardize a postal address
 | `regionCode` | string | No | ISO 3166-1 alpha-2 country code \(e.g., "US", "CA"\) |
 | `locality` | string | No | City or locality name |
 | `enableUspsCass` | boolean | No | Enable USPS CASS validation for US addresses |
-| `pricing` | per_request | No | No description |
-| `rateLimit` | string | No | No description |
 
 #### Output
 

apps/docs/content/docs/en/integrations/google_pagespeed.mdx

@@ -55,8 +55,6 @@ Analyze a webpage for performance, accessibility, SEO, and best practices using
 | `category` | string | No | Lighthouse categories to analyze \(comma-separated\): performance, accessibility, best-practices, seo |
 | `strategy` | string | No | Analysis strategy: desktop or mobile |
 | `locale` | string | No | Locale for results \(e.g., en, fr, de\) |
-| `pricing` | per_request | No | No description |
-| `rateLimit` | string | No | No description |
 
 #### Output