Overview
LoopOS AI provides a comprehensive REST API for accessing all AI services. All endpoints follow RESTful conventions and return JSON responses.Base URL
Authentication
Currently, LoopOS AI services don’t require authentication for public endpoints. All requests must use HTTPS.Authentication may be added in the future. Check documentation for updates.
Request Format
All requests use:- Method: POST (except health check)
- Content-Type:
application/json - Body: JSON object
Response Format
All responses return JSON:- 200 OK: Successful request
- 422 Validation Error: Invalid input parameters
- 413 Payload Too Large: Request exceeds size limits
- 429 Too Many Requests: Rate limit exceeded
- 500 Internal Server Error: Server-side error
Common Request Fields
Most endpoints accept these common fields:| Field | Type | Description | Default |
|---|---|---|---|
language | string | Language code (e.g., “PT-PT”, “en-US”) | “PT-PT” |
conversation | boolean | Whether this is conversational | false |
callback_url | string | Async callback URL | null |
loopos_core_context | string | Business context | null |
messages | array | Conversation messages | [] |
images | array | Image URLs or base64 | [] |
agent_specific | object | Service-specific params | null |
session_extra_data | object | Session metadata |
Endpoints
Core Services
- Chat - Conversational interface for submission
- Decision - Decision making service
- C2C Descriptor - Marketplace listing generation
- C2C Validation - Content validation
- Brands - Brand discovery
- Value Estimation - Price estimation
- ID Validator - Document validation
- Translator - Catalog translation
- Protocol Generator - Protocol generation
Utility Endpoints
GET /health- Health check endpointGET /- Root endpoint (serves index page)
Rate Limiting
Rate limits are applied per endpoint. If you exceed the limit, you’ll receive a429 Too Many Requests response.
Timeouts
- Default timeout: 120 seconds
- Long-running operations: Up to 300 seconds
Error Responses
Validation Error (422)
Server Error (500)
OpenAPI Specification
The complete OpenAPI specification is available at:- Generate client libraries
- Explore endpoints in tools like Postman
- Validate requests and responses
Code Examples
Related Documentation
- Quickstart - Getting started guide
- Integration Guide - Integration patterns
- Services Overview - Service details