Production Deployment

# Heroku
heroku config:set OPENAI_API_KEY=sk-...

# Railway
railway variables set OPENAI_API_KEY=sk-...

# Docker / Kubernetes — pass via -e flags or secrets

# Single process (development)
uvicorn server:app --host 0.0.0.0 --port 8000 --reload

# Multi-process (production) — use number of CPU cores
uvicorn server:app --host 0.0.0.0 --port 8000 --workers 4

# With Gunicorn (more robust process management)
pip install gunicorn
gunicorn server:app \
  --worker-class uvicorn.workers.UvicornWorker \
  --workers 4 \
  --bind 0.0.0.0:8000 \
  --timeout 120 \
  --keep-alive 5

# Dockerfile
FROM python:3.11-slim

WORKDIR /app

# Install dependencies
COPY pyproject.toml .
RUN pip install langchat uvicorn gunicorn

# Copy application
COPY server.py .

# Build UI (if using the built-in frontend)
COPY src/langchat/core/ui /app/ui
RUN cd /app/ui && npm ci && npm run build

EXPOSE 8000

CMD ["gunicorn", "server:app", \
     "--worker-class", "uvicorn.workers.UvicornWorker", \
     "--workers", "4", \
     "--bind", "0.0.0.0:8000"]

docker build -t my-chatbot .

docker run -d \
  -p 8000:8000 \
  -e OPENAI_API_KEY=sk-... \
  -e PINECONE_API_KEY=pcsk-... \
  -e SUPABASE_URL=https://xxxx.supabase.co \
  -e SUPABASE_SERVICE_ROLE_KEY=eyJ... \
  --name my-chatbot \
  my-chatbot

curl http://your-server/health
# {"status":"healthy","timestamp":"...","version":"1.0.1"}

services:
  chatbot:
    image: my-chatbot
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3

from langchat.providers import OpenAI

llm = OpenAI(
    "gpt-4o-mini",
    api_keys=[
        os.environ["OPENAI_KEY_1"],
        os.environ["OPENAI_KEY_2"],
        os.environ["OPENAI_KEY_3"],
    ],
    max_retries_per_key=2,
)

-- Average response time (last 24 hours)
SELECT AVG(response_time) as avg_latency
FROM request_metrics
WHERE request_time > NOW() - INTERVAL '24 hours'
  AND success = true;

-- Error rate
SELECT
  COUNT(*) FILTER (WHERE success = false) as errors,
  COUNT(*) as total,
  ROUND(COUNT(*) FILTER (WHERE success = false)::numeric / COUNT(*) * 100, 2) as error_rate
FROM request_metrics
WHERE request_time > NOW() - INTERVAL '1 hour';

-- Slowest queries
SELECT user_id, response_time, request_time
FROM request_metrics
ORDER BY response_time DESC
LIMIT 20;

# Use the pooler URL instead of direct connection
SUPABASE_URL=https://xxxx.supabase.co  # standard — works for most cases

# Access the underlying FastAPI app after creation
from langchat.api import get_app
from fastapi.middleware.cors import CORSMiddleware

app = create_app(...)

# Remove the permissive CORS middleware and add a restrictive one
app.add_middleware(
    CORSMiddleware,
    allow_origins=["https://your-frontend.com"],
    allow_methods=["GET", "POST"],
    allow_headers=["*"],
)

pip install slowapi

from slowapi import Limiter, _rate_limit_exceeded_handler
from slowapi.util import get_remote_address
from slowapi.errors import RateLimitExceeded

limiter = Limiter(key_func=get_remote_address)
app.state.limiter = limiter
app.add_exception_handler(RateLimitExceeded, _rate_limit_exceeded_handler)