Skip to main content
from praisonaiagents import Agent

agent = Agent(name="recipe-server", instructions="Serve advanced recipes as HTTP endpoints.")
agent.start("Serve the data-analysis recipe on port 8000.")
The user calls a hardened recipe HTTP endpoint; rate limits, metrics, and auth guard production traffic. Harden a recipe HTTP server with rate limits, Prometheus metrics, admin reload, and distributed tracing. 
import os
from praisonai.recipe.serve import serve

serve(
    host="0.0.0.0",
    port=8765,
    workers=2,
    config={
        "auth": "api-key",
        "api_key": os.environ["PRAISONAI_API_KEY"],
        "rate_limit": 100,
        "enable_metrics": True,
    },
)

​
How It Works

​
Quick Start

1

Simple Usage

Enable rate limiting and metrics on an existing server:
from praisonai.recipe.serve import serve

serve(
    host="127.0.0.1",
    port=8765,
    config={
        "rate_limit": 100,
        "enable_metrics": True,
    },
)
Scrape metrics at GET /metrics (Prometheus format).
2

With Configuration

Production setup with auth, admin reload, workers, and tracing:
import os
from praisonai.recipe.serve import serve

serve(
    host="0.0.0.0",
    port=8765,
    workers=4,
    config={
        "auth": "api-key",
        "api_key": os.environ["PRAISONAI_API_KEY"],
        "rate_limit": 100,
        "max_request_size": 10 * 1024 * 1024,
        "enable_metrics": True,
        "enable_admin": True,
        "trace_exporter": "otlp",
        "otlp_endpoint": "http://localhost:4317",
        "service_name": "praisonai-recipe",
    },
)

​
How It Works

Advanced features layer onto the base recipe server from Recipe Serve. Rate limiting uses a sliding window per client; metrics expose request counts and latency; admin endpoints hot-reload recipes without restart.
FeatureEndpoint / APIPurpose
Rate limitingmiddlewareCap requests per minute per client
MetricsGET /metricsPrometheus exposition
Admin reloadPOST /admin/reloadRefresh recipe registry
TracingOpenTelemetryDistributed request spans
Workersserve(workers=N)Multi-process scaling

​
Configuration Options

KeyTypeDefaultDescription
rate_limitint0 (disabled)Requests per minute per client
rate_limit_exempt_pathslist["/health", "/metrics"]Paths exempt from rate limiting
max_request_sizeint10485760 (10MB)Maximum request body size
enable_metricsboolfalseEnable /metrics endpoint
enable_adminboolfalseEnable /admin/* endpoints
trace_exporterstr"none"Tracing exporter (none, otlp, jaeger, zipkin)
otlp_endpointstr"http://localhost:4317"OTLP collector endpoint
service_namestr"praisonai-recipe"Service name for tracing
workersint1Worker processes (serve() argument)

​
Common Patterns

​
Programmatic rate limiter

from praisonai.recipe.serve import create_rate_limiter

limiter = create_rate_limiter(requests_per_minute=100)
allowed, retry_after = limiter.check("client-ip-or-key")

if not allowed:
    print(f"Rate limited. Retry after {retry_after} seconds")

​
Admin reload

curl -X POST http://localhost:8765/admin/reload \
  -H "X-API-Key: $PRAISONAI_API_KEY"

​
Prometheus scrape config

scrape_configs:
  - job_name: praisonai-recipe
    static_configs:
      - targets: ["localhost:8765"]
    metrics_path: /metrics

​
OpenTelemetry dependencies

pip install opentelemetry-sdk opentelemetry-exporter-otlp
OpenTelemetry is lazily imported — if packages are missing, the server logs a warning and continues without tracing.

​
Best Practices

Set enable_admin=True only alongside auth: api-key and load the key from PRAISONAI_API_KEY. Admin reload can change live behaviour — protect it.
Set workers to roughly 2 × CPU cores + 1. Workers above 1 disable hot reload automatically.
Keep /health and /metrics in rate_limit_exempt_paths so orchestrators and Prometheus can poll without consuming quota.
The built-in limiter is in-memory per worker. For multi-node deployments, place a shared rate limiter in front of the service (API gateway or Redis-backed middleware).

Recipe Serve

Programmatic server configuration and deployment

Endpoints Code

Client-side code for calling recipe endpoints