from datetime import datetime, timezone

title: “Agent Recipes Server” description: “Deploy Agent Recipes as HTTP/API services” icon: “server”

Deploy Agent Recipes as a Server

Run Agent Recipes as HTTP services for integration with web applications, microservices, and automation pipelines.

Quick Start

Basic Server Setup

from flask import Flask, request, jsonify
from praisonai_tools.recipe_tools import LLMTool

app = Flask(__name__)
llm = LLMTool(provider="openai", model="gpt-4o-mini")

@app.route("/health", methods=["GET"])
def health():
    """Health check endpoint."""
    deps = llm.check_dependencies()
    return jsonify({
        "status": "healthy" if deps.get("api_key") else "unhealthy",
        "dependencies": deps
    })

@app.route("/recipes/blog", methods=["POST"])
def generate_blog():
    """Generate blog post."""
    data = request.json
    topic = data.get("topic", "")
    
    response = llm.complete(
        f"Write a blog post about: {topic}",
        system="You are an expert blog writer.",
        max_tokens=2000
    )
    
    return jsonify({
        "content": response.content,
        "model": response.model,
        "tokens": response.usage
    })

if __name__ == "__main__":
    app.run(host="0.0.0.0", port=8080)

Run the Server

# Set API key
export OPENAI_API_KEY=sk-...

# Install dependencies
pip install flask praisonai-tools

# Run server
python server.py

Test Endpoints

# Health check
curl http://localhost:8080/health

# Generate blog
curl -X POST http://localhost:8080/recipes/blog \
  -H "Content-Type: application/json" \
  -d '{"topic": "AI in Healthcare"}'

Production Server with FastAPI

from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
from praisonai_tools.recipe_tools import LLMTool, VisionTool, ChartTool
import os

app = FastAPI(title="Agent Recipes API", version="1.0.0")

# Initialize tools
llm = LLMTool(provider="openai", model="gpt-4o-mini")
vision = VisionTool(provider="openai")
chart = ChartTool()

class BlogRequest(BaseModel):
    topic: str
    style: str = "professional"
    max_tokens: int = 2000

class SentimentRequest(BaseModel):
    text: str

class ChartRequest(BaseModel):
    data: dict
    chart_type: str = "bar"
    title: str = "Chart"

@app.get("/health")
async def health():
    """Health check with dependency status."""
    return {
        "status": "healthy",
        "llm": llm.check_dependencies(),
        "vision": vision.check_dependencies(),
        "chart": chart.check_dependencies()
    }

@app.post("/recipes/blog")
async def generate_blog(req: BlogRequest):
    """Generate a blog post."""
    try:
        response = llm.complete(
            f"Write a {req.style} blog post about: {req.topic}",
            system="You are an expert blog writer.",
            max_tokens=req.max_tokens
        )
        return {
            "content": response.content,
            "model": response.model,
            "tokens": response.usage
        }
    except Exception as e:
        raise HTTPException(status_code=500, detail=str(e))

@app.post("/recipes/sentiment")
async def analyze_sentiment(req: SentimentRequest):
    """Analyze text sentiment."""
    try:
        response = llm.complete(
            f"Analyze the sentiment of this text and respond with JSON: {req.text}",
            max_tokens=100
        )
        return {"analysis": response.content}
    except Exception as e:
        raise HTTPException(status_code=500, detail=str(e))

@app.post("/recipes/chart")
async def generate_chart(req: ChartRequest):
    """Generate a chart from data."""
    try:
        if req.chart_type == "bar":
            result = chart.bar(req.data, title=req.title)
        elif req.chart_type == "line":
            result = chart.line(req.data, title=req.title)
        elif req.chart_type == "pie":
            result = chart.pie(req.data, title=req.title)
        else:
            raise HTTPException(status_code=400, detail="Invalid chart type")
        
        return {"path": result.path, "type": req.chart_type}
    except Exception as e:
        raise HTTPException(status_code=500, detail=str(e))

if __name__ == "__main__":
    import uvicorn
    uvicorn.run(app, host="0.0.0.0", port=8080)

Run FastAPI Server

# Install dependencies
pip install fastapi uvicorn praisonai-tools

# Run with auto-reload for development
uvicorn server:app --reload --host 0.0.0.0 --port 8080

# Production with multiple workers
uvicorn server:app --workers 4 --host 0.0.0.0 --port 8080

Docker Deployment

Dockerfile

FROM python:3.11-slim

WORKDIR /app

# Install system dependencies
RUN apt-get update && apt-get install -y \
    ffmpeg \
    tesseract-ocr \
    && rm -rf /var/lib/apt/lists/*

# Install Python dependencies
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy application
COPY . .

# Expose port
EXPOSE 8080

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
    CMD curl -f http://localhost:8080/health || exit 1

# Run server
CMD ["uvicorn", "server:app", "--host", "0.0.0.0", "--port", "8080"]

requirements.txt

fastapi>=0.100.0
uvicorn>=0.23.0
praisonai-tools>=0.0.1
python-multipart>=0.0.6

docker-compose.yml

version: '3.8'

services:
  recipes-api:
    build: .
    ports:
      - "8080:8080"
    environment:
      - OPENAI_API_KEY=${OPENAI_API_KEY}
      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
    volumes:
      - ./output:/app/output
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8080/health"]
      interval: 30s
      timeout: 10s
      retries: 3

Build and Run

# Build image
docker build -t recipes-api .

# Run container
docker run -d \
  -p 8080:8080 \
  -e OPENAI_API_KEY=$OPENAI_API_KEY \
  --name recipes-api \
  recipes-api

# Or with docker-compose
docker-compose up -d

Configuration

Environment Variables

Variable	Description	Required
`OPENAI_API_KEY`	OpenAI API key	Yes (for OpenAI)
`ANTHROPIC_API_KEY`	Anthropic API key	No
`GOOGLE_API_KEY`	Google API key	No
`RECIPES_LOG_LEVEL`	Logging level (DEBUG, INFO, WARNING)	No
`RECIPES_MAX_TOKENS`	Default max tokens	No
`RECIPES_TIMEOUT`	Request timeout in seconds	No

Logging Configuration

import logging

logging.basicConfig(
    level=logging.INFO,
    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
)

# Mask API keys in logs
class SecretFilter(logging.Filter):
    def filter(self, record):
        if hasattr(record, 'msg'):
            record.msg = record.msg.replace(
                os.environ.get('OPENAI_API_KEY', ''),
                '****'
            )
        return True

logging.getLogger().addFilter(SecretFilter())

Monitoring

Prometheus Metrics

from prometheus_client import Counter, Histogram, generate_latest
from fastapi import Response

REQUEST_COUNT = Counter(
    'recipes_requests_total',
    'Total recipe requests',
    ['recipe', 'status']
)

REQUEST_LATENCY = Histogram(
    'recipes_request_latency_seconds',
    'Request latency',
    ['recipe']
)

@app.get("/metrics")
async def metrics():
    return Response(
        generate_latest(),
        media_type="text/plain"
    )

Health Check Endpoint

@app.get("/health")
async def health():
    checks = {
        "llm": llm.check_dependencies(),
        "disk_space": check_disk_space(),
        "memory": check_memory()
    }
    
    all_healthy = all(
        v.get("api_key", True) for v in checks.values() 
        if isinstance(v, dict)
    )
    
    return {
        "status": "healthy" if all_healthy else "degraded",
        "checks": checks,
        "timestamp": datetime.now(timezone.utc).isoformat()
    }

Security

API Key Authentication

from fastapi import Security, HTTPException
from fastapi.security import APIKeyHeader

API_KEY_HEADER = APIKeyHeader(name="X-API-Key")

async def verify_api_key(api_key: str = Security(API_KEY_HEADER)):
    if api_key != os.environ.get("RECIPES_API_KEY"):
        raise HTTPException(status_code=403, detail="Invalid API key")
    return api_key

@app.post("/recipes/blog")
async def generate_blog(req: BlogRequest, api_key: str = Security(verify_api_key)):
    # ... implementation

Rate Limiting

from slowapi import Limiter
from slowapi.util import get_remote_address

limiter = Limiter(key_func=get_remote_address)
app.state.limiter = limiter

@app.post("/recipes/blog")
@limiter.limit("10/minute")
async def generate_blog(request: Request, req: BlogRequest):
    # ... implementation

Next Steps

CLI Reference - Command line usage
Python Integration - Use in applications
Troubleshooting - Common issues

​title: “Agent Recipes Server” description: “Deploy Agent Recipes as HTTP/API services” icon: “server”

​Deploy Agent Recipes as a Server

​Quick Start

​Basic Server Setup

​Run the Server

​Test Endpoints

​Production Server with FastAPI

​Run FastAPI Server

​Docker Deployment

​Dockerfile

​requirements.txt

​docker-compose.yml

​Build and Run

​Configuration

​Environment Variables

​Logging Configuration

​Monitoring

​Prometheus Metrics

​Health Check Endpoint

​Security

​API Key Authentication

​Rate Limiting

​Next Steps

title: “Agent Recipes Server” description: “Deploy Agent Recipes as HTTP/API services” icon: “server”

Deploy Agent Recipes as a Server

Quick Start

Basic Server Setup

Run the Server

Test Endpoints

Production Server with FastAPI

Run FastAPI Server

Docker Deployment

Dockerfile

requirements.txt

docker-compose.yml

Build and Run

Configuration

Environment Variables

Logging Configuration

Monitoring

Prometheus Metrics

Health Check Endpoint

Security

API Key Authentication

Rate Limiting

Next Steps