Skipping the cache may result in slightly increased response times as each request will be processed fresh. Use this option judiciously to balance between data freshness and performance.
` elements. | | element+element | `div + p` | Selects the first `
` element that is placed immediately after `
The image generation API is depracated and no longer being maintained.
## Overview
The Image Translation API allows you to extract and translate text from images into any of 100+ supported languages. This powerful tool combines OCR (Optical Character Recognition) with translation capabilities, making it perfect for translating documents, signs, menus, or any image containing text.
* Extract and translate text from images in one API call
* Support for 100+ target languages
* High-quality OCR with accurate text extraction
* Preserves original image layout with translated text
* Multiple output formats (URL, base64, binary)
* Works with various image formats (PNG, JPEG, WebP, etc.)
## API Endpoint
```
POST /v1/ai/translate/image
```
## Quick Start
```javascript JavaScript theme={null}
import { JigsawStack } from "jigsawstack";
const jigsaw = JigsawStack({ apiKey: "your-api-key" });
const response = await jigsaw.translate.image({
"url": "https://images.unsplash.com/photo-1528716321680-815a8cdb8cbe?q=80&w=1376&auto=format&fit=crop&ixlib=rb-4.1.0&ixid=M3wxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8fA%3D%3D",
"target_language": "hi",
"return_type": "url"
})
```
## Response Example
```json theme={null}
{
"success": true,
"url": "https://jigsawstack-temp.b1e91a466694ad4af04df5d05ca12d93.r2.cloudflarestorage.com/temp/93653e58-b1fa-4672-a81d-00be1b7ec18e.jpg?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Credential=7b9a19349842b7b1a9e4c2e19f05b232%2F20250903%2Fauto%2Fs3%2Faws4_request&X-Amz-Date=20250903T192434Z&X-Amz-Expires=604800&X-Amz-Signature=aed9e0a569eaa75c082410cda3bb643cc80e337cad0cb6dbb358f2526f3cc348&X-Amz-SignedHeaders=host&x-amz-checksum-mode=ENABLED&x-id=GetObject",
"_usage": {
"input_tokens": 56,
"output_tokens": 186,
"inference_time_tokens": 24458,
"total_tokens": 24700
}
}
```
## Supported Languages
The Translation API supports over 100 languages. Here are some of the most commonly used:
| Code | Language | Code | Language | Code | Language |
| ---- | -------- | ---- | -------- | ---- | ---------- |
| ar | Arabic | fr | French | pt | Portuguese |
| bn | Bengali | de | German | ru | Russian |
| zh | Chinese | hi | Hindi | es | Spanish |
| en | English | ja | Japanese | sw | Swahili |
| fi | Finnish | ko | Korean | tr | Turkish |
For a complete list of supported languages, please visit our [Language Codes Reference](https://jigsawstack.com/docs/additional-resources/languages).
## Overview
The Object Detection API is a powerful computer vision tool that can identify and locate objects, GUI elements, and interactive components in images. This advanced API is perfect for automation, testing, and building intelligent applications that need to understand visual content.
**Object Detection** excels at the following:
* GUI Automation: Identify buttons, forms, menus, and other interface elements for automated testing and interaction.
* Computer Vision Applications: Detect and classify objects in images for inventory management, security systems, and content analysis.
* Accessibility Tools: Locate and describe visual elements to assist users with visual impairments in navigating interfaces.
* Quality Assurance: Automatically verify that UI elements are properly positioned and displayed across different devices and browsers.
Let's see the Object Detection API in action by building an object detector.
## API Endpoint
```
POST /v1/object-detection
```
## Quick Start
```javascript JavaScript theme={null}
import { JigsawStack } from "jigsawstack";
const jigsaw = JigsawStack({ apiKey: "your-api-key" });
const response = await jigsaw.vision.object_detection({
"url": "https://jigsawstack.com/preview/object-detection-example-input.jpg",
"features": [
"object_detection"
],
"annotated_image": true,
"return_type": "url"
})
```
## Response Example
```json theme={null}
{
"success": true,
"annotated_image": "https://jigsawstack-temp.b1e91a466694ad4af04df5d05ca12d93.r2.cloudflarestorage.com/temp/c8a7c3ea-1a47-420f-8503-e3f391fd5e9f.jpg?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Credential=7b9a19349842b7b1a9e4c2e19f05b232%2F20250903%2Fauto%2Fs3%2Faws4_request&X-Amz-Date=20250903T192453Z&X-Amz-Expires=604800&X-Amz-Signature=04d2cc2f75cd561acc7333f2db3f999677c95da9c8507e223dec842233b72b50&X-Amz-SignedHeaders=host&x-amz-checksum-mode=ENABLED&x-id=GetObject",
"objects": [...],
"tags": [
"TV",
"Hands",
"Controller",
"Table",
"Wii",
"Playstation",
"Wires",
"Minecraft",
"Castle",
"Sky",
"Water",
"Trees",
"Grass",
"UI",
"Character"
],
"_usage": {
"input_tokens": 39,
"output_tokens": 3036,
"inference_time_tokens": 34278,
"total_tokens": 37353
}
}
```
## Use Cases & Applications
### GUI Automation
Automate UI testing and interaction with the detected objects.
* **Example**: Click on a button, fill out a form, or navigate through a menu.
* **Implementation**: Use the detected object coordinates to interact with the UI elements.
### Computer Vision Applications
Detect and classify objects in images for inventory management, security systems, and content analysis.
* **Example**: Identify objects in a warehouse, track inventory levels, or detect unauthorized items.
* **Implementation**: Use the detected object coordinates to track and manage inventory.
### Quality Assurance
Automatically verify that UI elements are properly positioned and displayed across different devices and browsers.
* **Example**: Verify that UI elements are properly positioned and displayed across different devices and browsers.
* **Implementation**: Use the detected object coordinates to verify that UI elements are properly positioned and displayed across different devices and browsers.
Hurray! You can now receive log events.
We're excited to announce our strategic partnership with [ARES](https://www.getares.ai/), bringing JigsawStack's powerful AI Search capabilities to their cutting-edge platform. With the ARES 3.20 update, users now have access to enhanced AI models powered by JigsawStack Search technology.
## Enhanced AI Models
### GPT-4o + JigsawStack Search
GPT-4o, OpenAI's most advanced model, now leverages JigsawStack Search to access the latest information from across the web, providing accurate, up-to-date responses for your research, content creation, and information needs.
* Latest data for informed decision-making
* Comprehensive research capabilities
* Factual grounding for better outputs
### Claude 3.5 Sonnet + JigsawStack Search
Anthropic's Claude 3.5 Sonnet, known for exceptional reasoning and creative output, now incorporates real-time data through JigsawStack Search, enhancing its problem-solving capabilities and creative potential.
* Current context for creative projects
* Enhanced coding assistance with latest documentation
* Improved analysis with real-world data
## Technical Integration Benefits
### Advanced Search Algorithm
JigsawStack's proprietary search algorithm delivers precisely relevant information by understanding context and intent, not just keywords.
### Seamless Experience
The integration provides a unified experience where AI models can access external information without disrupting your workflow.
### Performance Optimization
Our search capabilities are optimized for speed and efficiency, reducing latency and improving the overall user experience on the ARES platform.
## Real-World Applications
Access current market data, research papers, and industry trends to inform strategic decisions.
Generate factually accurate content with references to current events and verified information.
Get up-to-date coding examples, documentation, and best practices while building applications.
Analyze latest industry developments and competitive information for strategic planning.
Check out our [Google Sheets Demo](https://docs.google.com/spreadsheets/d/1wBrw7AtrU5Yd_8Be2CDgurEbSa40mRCsacxcpMDFtmY/edit?usp=sharing) to see how you can use JigsawStack in your Google Sheets.
4. Paste your API key in the input field and click `Save`
## How to use the add-on
You can call all of JigsawStack’s AI tools just like a regular spreadsheet formula.
Here are a few examples which are shown with autocompletion:
## Parameters and Return Types
Each JigsawStack function has a set of parameters and a return type. You can find more information on each parameter by clicking
on the dropdown menu in the custom function.
Warning: in the case where no description is shown, please click on the question mark icon next to the custom function.
Note: Loading will also show a similar error message. This is unavoidable and is due to the way Google Sheets handles custom functions.
Note: Refresh All Formulas, will clear all your existing cache.
## Access JigsawStack APIs on Hugging Face
[Hugging Face Spaces](https://huggingface.co/spaces) is a platform that allows developers to deploy and showcase machine learning applications using tools like Gradio and Streamlit. With JigsawStack's Spaces, you can:
* **Try APIs instantly** with interactive Gradio UIs
* **Share demos** with team members or users
* **Explore** how each API behaves with real inputs
* **Benchmark** different models quickly
***
## JigsawStack on Hugging Face
We've published a set of Hugging Face Spaces to let anyone explore our APIs with zero setup. Just visit the Space and start using it—no installation or authentication required.
Quickly condense long text into clear, concise summaries.
Extract structured data from URLs using AI-enhanced scraping.
Translate text instantly to over 160 languages.
Identify NSFW or inappropriate image content with high accuracy.
Detect and label objects in images using our optimized vision model.
Detect positive, negative, or neutral sentiment in any text input.
Perform semantic web searches powered by generative models.
Create high-quality images from text prompts quickly.
Extract and translate text directly from images.
Turn spoken audio into accurate, readable text.
Visually extract structured text data from documents and images.
Generate high-quality embeddings for vector search and clustering.
If you love what we're building, share our Spaces or give us a ❤️ on Hugging Face.
The JigsawStack Tool provides your agent with several capabilities:
* **JigsawStackAIScrape**: Scrape web content with AI-powered precision.
* **JigsawStackAISearch**: Perform AI-powered web searches for high-quality results.
* **JigsawStackSpeechToText**: Transcribe audio or video using the powerful large V3 Whisper model.
* **JigsawStackVOCR**: Recognize and extract data from images via AI prompts.
* **JigsawStackTextToSQL**: Generate SQL queries from natural language text.
## Setup
1. **Set up an [account](https://jigsawstack.com/)**: Get started for free
2. **Create and retrieve your API key**:
```bash theme={null}
export JIGSAWSTACK_API_KEY="your-api-key"
```
## Installation
Install the JigsawStack integration package for your project:
```bash theme={null}
# npm
npm install @langchain/jigsawstack
# Yarn
yarn add @langchain/jigsawstack
# pnpm
pnpm add @langchain/jigsawstack
```
## Usage: Standalone
### Example: Using Other JigsawStack Tools
```javascript theme={null}
import {
JigsawStackAIScrape,
JigsawStackAISearch,
JigsawStackSpeechToText,
JigsawStackVOCR,
JigsawStackTextToSQL,
} from "@langchain/jigsawstack";
// Example of AI Scrape Tool
const aiScrapeTool = new JigsawStackAIScrape({
params: {
element_prompts: ["Pro plan"],
},
});
const scrapeResult = await aiScrapeTool.invoke(
"https://jigsawstack.com/pricing",
);
console.log({ scrapeResult });
// Example of AI Search Tool
const aiSearchTool = new JigsawStackAISearch();
const searchResult = await aiSearchTool.invoke("The leaning tower of Pisa");
console.log({ searchResult });
// Example of VOCR Tool
const vocrTool = new JigsawStackVOCR({
params: {
prompt: "Describe the image in detail",
},
});
const vocrResult = await vocrTool.invoke("https://link-to-image.jpg");
console.log({ vocrResult });
// Example of Speech-to-Text Tool
const sttTool = new JigsawStackSpeechToText();
await sttTool.invoke("https://link-to-video.mp4");
// Example of Text-to-SQL Tool
const sqlTool = new JigsawStackTextToSQL({
params: {
sql_schema:
"CREATE TABLE Transactions (transaction_id INT PRIMARY KEY, user_id INT NOT NULL, ... )",
},
});
const sqlResult = await sqlTool.invoke(
"Generate a query to get transactions exceeding $10,000.",
);
console.log({ sqlResult });
```
## Usage: In an Agent
```javascript theme={null}
import { ChatOpenAI } from "@langchain/openai";
import { initializeAgentExecutorWithOptions } from "langchain/agents";
import {
JigsawStackAIScrape,
JigsawStackAISearch,
JigsawStackVOCR,
JigsawStackSpeechToText,
JigsawStackTextToSQL,
} from "@langchain/jigsawstack";
const model = new ChatOpenAI({ temperature: 0 });
// Add the necessary tools
const tools = [
new JigsawStackAIScrape(),
new JigsawStackAISearch(),
new JigsawStackVOCR(),
new JigsawStackSpeechToText(),
new JigsawStackTextToSQL(),
];
const executor = await initializeAgentExecutorWithOptions(tools, model, {
agentType: "zero-shot-react-description",
verbose: true,
});
const res = await executor.invoke({
input: "Kokkalo Restaurant Santorini",
});
console.log(res.output);
```
# JigsawStack AI for n8n Workflows
n8n is a visual, node based workflow automation tool. With JigsawStack’s official n8n node, you can bring intelligent actions into your flows using **API endpoints that run purpose built small models**, no infrastructure or ML ops needed.
JigsawStack delivers **custom small models trained for specialized use cases**, all served through fast and scalable API endpoints. These APIs plug directly into your tech stack, giving you reliable, production ready AI building blocks for your automation needs.
## How to add JigsawStack Node in your workflow ?
### n8n.cloud
If you're using [n8n.cloud](https://n8n.cloud), follow these simple steps to add JigsawStack to your workflow:
1. **Click on the + icon**
2. **Search JigsawStack**
Use the search input field to search for our node
3. **Install Node**
Hit the `install node` if not already installed
4. **Add credentials**
Get your API Key from your [JigsawStack dashboard](https://jigsawstack.com/dashboard).
5. **Hit execute**
Execute the node that you have selected.
### Self-hosted n8n
For self-hosted n8n installations, you'll need to install the JigsawStack node manually:
1. **Install the Node:**
```bash theme={null}
npm install n8n-nodes-jigsawstack
```
2. **Add Your API Key:**
In n8n, go to Settings > Credentials\
Click "New" and select "JigsawStack API"\
Enter your API key from your [JigsawStack dashboard](https://jigsawstack.com)
3. **Add the Node to Your Workflow:**
Drag the JigsawStack node into your workflow\
Select the operation you want (e.g., Sentiment Analysis, Image Generation)\
Configure the parameters as needed\
Connect with other nodes to automate your process
## Why Use JigsawStack in n8n?
**Optimized for speed and cost** – Lightweight models that work fast and scale well\
**Composable inside workflows** – Integrate easily with hundreds of other n8n nodes\
**Focused on use case fit** – Each model is designed to solve real world, narrow problems\
**No ML setup required** – Just call an endpoint, no fine tuning or infrastructure
Whether you're classifying content, processing images, analyzing sentiment, or extracting structured data from the web JigsawStack makes it drop dead simple to bring AI into your workflows.
**Example Use Cases:**
* Automatically summarize or translate incoming emails
* Detect spam, profanity, or sentiment in user generated content
* Generate images or speech from text for marketing automation
* Scrape and extract data from websites using AI
* Convert natural language to SQL for database queries
* Moderate images for NSFW content before publishing
* Build custom AI powered bots and automations
## Nodes available
* AI Scrape
* Analyze Sentiment
* Convert to SQL
* Generate Embedding
* HTML to Any
* Image Generation
* Make Prediction
* NSFW Detection
* Object Detection
* Process Image
* Profanity Detection
* Search Web
* Spam Detection
* Speech to Text
* Spell Check
* Summary
* Translate
* Translate Image
* Web Suggestion
## Resources & Support
* **Official n8n integration page:** [JigsawStack on n8n.io](https://n8n.io/integrations/jigsawstack/)
* **Official npm package:** [n8n-nodes-jigsawstack](https://www.npmjs.com/package/n8n-nodes-jigsawstack)
* **n8n Documentation:** [n8n.io](https://n8n.io/docs)
If you have questions, need help with setup, or want to suggest new features, reach out to us anytime!
# Postman
Source: https://jigsawstack.com/docs/integration/postman
Explore and test JigsawStack APIs directly in Postman with our official collection
## Access JigsawStack APIs in Postman
Postman is a popular API platform that makes working with APIs faster and easier. With our official JigsawStack Postman collection, you can:
* **Explore** our complete API suite in an interactive environment
* **Test** API calls with pre-configured requests
* **Integrate** JigsawStack into your projects with generated code snippets
* **Collaborate** with your team on API development
* **Build workflows** using Postman's powerful features
## Getting Started
The quickest way to get started with JigsawStack in Postman.
Support JigsawStack in the 2025 Postman Developers' Choice Awards.
| Category | Description | Example Endpoints |
|---|---|---|
| Core AI | Essential AI capabilities for text and data analysis | Sentiment Analysis, Translation, Summary |
| Web & Search | Web scraping and search capabilities | AI Web Scraper, Web Search, HTML to Any |
| Computer Vision | Image analysis and processing | vOCR, Object Detection |
| Audio | Speech processing and voice capabilities | Speech to Text |
| Geolocation | Location-based services and data | Geo Search, Geocode |
| Validation | Content validation and verification | NSFW Detection, Profanity Check, Spell Check |
| File Management | Cloud-based file storage and retrieval | File Storage |
## Community & Support
* **Join our [Discord community](https://jigsawstack.com/discord)** for questions and collaboration
* **Contribute to our collection** by suggesting improvements
* **Vote for JigsawStack** in the [2025 Postman Developers' Choice Awards](https://www.postman.com/jigsawstack)
If you have questions or need assistance with the JigsawStack Postman collection, please contact [support@jigsawstack.com](mailto:support@jigsawstack.com).
## Access JigsawStack APIs on Replicate
[Replicate](https://replicate.com/) is a cloud platform for running machine learning models in production with a simple API. It also provides a beautiful frontend for developers and non-developers alike to test and share model outputs.
With JigsawStack on Replicate, you can:
* **Run powerful AI models** without setting up infrastructure
* **Use the hosted playground** to quickly test inputs/outputs
* **Get production-ready REST endpoints** for inference
* **Integrate models via cURL, Python, JS, or serverless functions**
* **Build on open-source workflows using our public models**
***
## Getting Started with JigsawStack on Replicate
You can try our models on Replicate in two ways: through the interactive web interface or programmatically via their API.
### Interactive Playground
The easiest way to start is by using the playground on the Replicate website. No account is needed to test models this way — just open a model page in your browser and experiment with different inputs. You will, however, need to provide your JigsawStack API key.
Generate embeddings for semantic search, recommendation engines, and more.
Analyze user sentiment with high-accuracy emotion classification.
Translate across 160+ languages with lightning-fast response times.
Detect and localize objects in images with bounding boxes.
Screen images for explicit or inappropriate content in real time.
Extract structured content from any public webpage using AI agents.
Search the internet intelligently with AI-powered relevance scoring.
Generate stunning images from text prompts with fast inference.
Visual OCR model that reads complex layouts, documents, and forms.
You can embed any Replicate model widget using the iframe embed option on the model page — great for documentation, blogs, or onboarding flows.
## Overview
JigsawStack seamlessly integrates with Vercel AI SDK, enabling you to extend your AI applications with powerful tools for web scraping, computer vision, audio processing, sentiment analysis, and more. This integration allows you to leverage JigsawStack's comprehensive API suite within Vercel's AI framework.
Create a Zapier account and connect JigsawStack to start building automated workflows.
Connect JigsawStack to Zapier| Action | Description | Use Case |
|---|---|---|
| Sentiment Analysis | Analyze text sentiment (positive, negative, neutral) | Categorize customer feedback automatically |
| Speech to Text | Transcribe audio files using Whisper large V3 | Convert meeting recordings to searchable text |
| Text Summary | Generate concise summaries of longer text | Create article summaries for newsletters |
| Translation | Translate text between languages | Automatically translate customer communications |
| vOCR | Extract text from images with high accuracy | Process receipts and invoices automatically |
| Object Detection | Recognize objects within images | Catalog product images by detected items |
| NSFW Detection | Detect inappropriate content in images | Filter user-uploaded content automatically |
| Profanity Check | Check text for inappropriate language | Moderate comments before publishing |
| Spam Check | Analyze text for spam indicators | Filter form submissions for quality |
| Spell Check | Detect and correct spelling errors | Automatically proofread content |
| Email Verification | Verify email deliverability and status | Clean contact lists before campaigns |
Some JigsawStack APIs may not be available in the Zapier actions. If there's a specific capability you need, please contact [support@jigsawstack.com](mailto:support@jigsawstack.com) for assistance.
JigsawStack is provides a suite of custom small models plugged into the right infrastructure to power your AI applications
## Prerequisites
To get the most out of this guide, you’ll need to:
* **Set up an** [account](https://jigsawstack.com/dashboard)
* **Create and retrieve your** [API key](https://jigsawstack.com/dashboard)
## Get started
Get started using the JigsawStack SDK in your project.
### Installation