mirror of
https://github.com/simstudioai/sim.git
synced 2026-04-28 03:00:29 -04:00
f99518b837
* feat(tools): added calcom * added more triggers, tested * updated regex in script for release to be more lenient * fix(tag-dropdown): performance improvements and scroll bug fixes - Add flatTagIndexMap for O(1) tag lookups (replaces O(n²) findIndex calls) - Memoize caret position calculation to avoid DOM manipulation on every render - Use refs for inputValue/cursorPosition to keep handleTagSelect callback stable - Change itemRefs from index-based to tag-based keys to prevent stale refs - Fix scroll jump in nested folders by removing scroll reset from registerFolder - Add onFolderEnter callback for scroll reset when entering folder via keyboard - Disable keyboard navigation wrap-around at boundaries - Simplify selection reset to single effect on flatTagList.length change Also: - Add safeCompare utility for timing-safe string comparison - Refactor webhook signature validation to use safeCompare Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * updated types * fix(calcom): simplify required field constraints for booking attendee The condition field already restricts these to calcom_create_booking, so simplified to required: true. Per Cal.com API docs, email is optional while name and timeZone are required. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * added tests * updated folder multi select, updated calcom and github tools and docs generator script * updated drag, updated outputs for tools, regen docs with nested docs script * updated setup instructions links, destructure trigger outputs, fix text subblock styling * updated docs gen script * updated docs script * updated docs script * updated script * remove destructuring of stripe webhook * expanded wand textarea, updated calcom tools --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
64 lines
3.2 KiB
Plaintext
64 lines
3.2 KiB
Plaintext
---
|
|
title: Embeddings
|
|
description: Generate Open AI embeddings
|
|
---
|
|
|
|
import { BlockInfoCard } from "@/components/ui/block-info-card"
|
|
|
|
<BlockInfoCard
|
|
type="openai"
|
|
color="#10a37f"
|
|
/>
|
|
|
|
{/* MANUAL-CONTENT-START:intro */}
|
|
[OpenAI](https://www.openai.com) is a leading AI research and deployment company that offers a suite of powerful AI models and APIs. OpenAI provides cutting-edge technologies including large language models (like GPT-4), image generation (DALL-E), and embeddings that enable developers to build sophisticated AI-powered applications.
|
|
|
|
With OpenAI, you can:
|
|
|
|
- **Generate text**: Create human-like text for various applications using GPT models
|
|
- **Create images**: Transform text descriptions into visual content with DALL-E
|
|
- **Produce embeddings**: Convert text into numerical vectors for semantic search and analysis
|
|
- **Build AI assistants**: Develop conversational agents with specialized knowledge
|
|
- **Process and analyze data**: Extract insights and patterns from unstructured text
|
|
- **Translate languages**: Convert content between different languages with high accuracy
|
|
- **Summarize content**: Condense long-form text while preserving key information
|
|
|
|
In Sim, the OpenAI integration enables your agents to leverage these powerful AI capabilities programmatically as part of their workflows. This allows for sophisticated automation scenarios that combine natural language understanding, content generation, and semantic analysis. Your agents can generate vector embeddings from text, which are numerical representations that capture semantic meaning, enabling advanced search, classification, and recommendation systems. Additionally, through the DALL-E integration, agents can create images from text descriptions, opening up possibilities for visual content generation. This integration bridges the gap between your workflow automation and state-of-the-art AI capabilities, enabling your agents to understand context, generate relevant content, and make intelligent decisions based on semantic understanding. By connecting Sim with OpenAI, you can create agents that process information more intelligently, generate creative content, and deliver more personalized experiences to users.
|
|
{/* MANUAL-CONTENT-END */}
|
|
|
|
|
|
## Usage Instructions
|
|
|
|
Integrate Embeddings into the workflow. Can generate embeddings from text.
|
|
|
|
|
|
|
|
## Tools
|
|
|
|
### `openai_embeddings`
|
|
|
|
Generate embeddings from text using OpenAI
|
|
|
|
#### Input
|
|
|
|
| Parameter | Type | Required | Description |
|
|
| --------- | ---- | -------- | ----------- |
|
|
| `input` | string | Yes | Text to generate embeddings for |
|
|
| `model` | string | No | Model to use for embeddings |
|
|
| `encodingFormat` | string | No | The format to return the embeddings in |
|
|
| `apiKey` | string | Yes | OpenAI API key |
|
|
|
|
#### Output
|
|
|
|
| Parameter | Type | Description |
|
|
| --------- | ---- | ----------- |
|
|
| `success` | boolean | Operation success status |
|
|
| `output` | object | Embeddings generation results |
|
|
| ↳ `embeddings` | array | Array of embedding vectors |
|
|
| ↳ `model` | string | Model used for generating embeddings |
|
|
| ↳ `usage` | object | Token usage information |
|
|
| ↳ `prompt_tokens` | number | Number of tokens in the prompt |
|
|
| ↳ `total_tokens` | number | Total number of tokens used |
|
|
|
|
|