Skip to main content

​
Introduction

The Weaver REST API provides HTTP endpoints for interacting with the AI agent orchestration service. All endpoints return JSON responses and support standard HTTP methods.

​
Base URL

http://localhost:8080
The default server configuration uses port 8080, but this can be customized during deployment.

​
Available Endpoints

Chat

Send messages to AI agents and receive responses

Health

Check service health and readiness status

​
Authentication

Currently, the REST API does not require authentication for basic endpoints. Admin endpoints like /admin/status, /admin/service, and /admin/logs should be protected by network-level security or reverse proxy authentication.

​
Request Format

All POST requests should include: 
Content-Type: application/json

​
Response Format

All responses are returned in JSON format with appropriate HTTP status codes:
  • 200 OK - Successful request
  • 400 Bad Request - Invalid request body or parameters
  • 405 Method Not Allowed - Incorrect HTTP method
  • 503 Service Unavailable - Service not ready

​
Error Handling

Errors are returned with appropriate HTTP status codes and JSON bodies: 
{
  "error": "Error description"
}

​
Timeouts

The server is configured with 5-minute (300 second) read and write timeouts to accommodate long-running AI generation tasks.

​
Rate Limiting

Rate limiting is not currently implemented at the application level. Consider implementing rate limiting at the reverse proxy or infrastructure level for production deployments.

Build docs developers (and LLMs) love

Get started for freeTalk to us