Documentation Index
Fetch the complete documentation index at: https://docs.praison.ai/llms.txt
Use this file to discover all available pages before exploring further.
Deploy agents to API servers, Docker containers, or cloud providers using praisonai deploy.
Quick Start
Set API Key
export OPENAI_API_KEY="your-key"
Initialize Deploy Config
praisonai deploy init --file agents.yaml --type api
Deploy
praisonai deploy run --file agents.yaml
Deploy Types
| Type | Command | Description |
|---|
| API | --type api | Local FastAPI server |
| Docker | --type docker | Docker container |
| AWS | --type cloud --provider aws | AWS ECS/Fargate |
| GCP | --type cloud --provider gcp | Google Cloud Run |
CLI Commands
praisonai deploy run
Execute deployment.
praisonai deploy run --file agents.yaml --type api
praisonai deploy run --file agents.yaml --type docker
praisonai deploy run --file agents.yaml --type cloud --provider aws
praisonai deploy run --file agents.yaml --type cloud --provider gcp
praisonai deploy init
Generate sample agents.yaml with deploy configuration.
praisonai deploy init --file agents.yaml --type api
praisonai deploy init --file agents.yaml --type docker
praisonai deploy init --file agents.yaml --type cloud --provider aws
praisonai deploy init --file agents.yaml --type cloud --provider gcp
praisonai deploy validate
Validate agents.yaml deploy configuration.
praisonai deploy validate --file agents.yaml
praisonai deploy plan
Show deployment plan without executing.
praisonai deploy plan --file agents.yaml
praisonai deploy status
Show deployment status.
praisonai deploy status --file agents.yaml
📊 Checking deployment status...
╭─────────────────────────────────────────────────────────────────────────────╮
│ Deployment Status │
├─────────────────┬───────────────────────────────────────────────────────────┤
│ Property │ Value │
├─────────────────┼───────────────────────────────────────────────────────────┤
│ State │ RUNNING │
│ Service Name │ praisonai-api │
│ Provider │ api │
│ URL │ http://127.0.0.1:8005 │
│ Healthy │ ✅ Yes │
│ Instances │ 1/1 │
╰─────────────────┴───────────────────────────────────────────────────────────╯
praisonai deploy doctor
Check deployment readiness.
praisonai deploy doctor
praisonai deploy doctor --provider aws
praisonai deploy doctor --provider gcp
praisonai deploy destroy
Destroy/delete deployment.
praisonai deploy destroy --file agents.yaml
praisonai deploy destroy --file agents.yaml --yes # Skip confirmation
CLI Flags
| Flag | Type | Default | Description |
|---|
--file, -f | string | agents.yaml | Path to agents.yaml |
--type | choice | - | api, docker, or cloud |
--provider | choice | - | aws, gcp, azure (for cloud type) |
--background | flag | false | Run in background |
--json | flag | false | Output as JSON |
--yes | flag | false | Skip confirmation prompts |
agents.yaml Deploy Section
Add a deploy section to your agents.yaml:
framework: praisonai
topic: helpful assistant
roles:
assistant:
role: Assistant
goal: Help users
backstory: You are helpful
tasks:
help_task:
description: Answer questions
expected_output: Helpful response
deploy:
type: api
api:
host: "127.0.0.1"
port: 8005
workers: 1
cors_enabled: true
auth_enabled: false
reload: false
Deploy Configuration Options
API Config
| Field | Type | Default | Description |
|---|
host | string | 127.0.0.1 | Server host |
port | int | 8005 | Server port |
workers | int | 1 | Worker processes |
cors_enabled | bool | true | Enable CORS |
auth_enabled | bool | false | Enable auth |
auth_token | string | null | Auth token |
reload | bool | false | Auto-reload (dev) |
Docker Config
| Field | Type | Default | Description |
|---|
image_name | string | praisonai-app | Image name |
tag | string | latest | Image tag |
base_image | string | python:3.11-slim | Base image |
expose | list[int] | [8005] | Ports to expose |
registry | string | null | Registry URL |
push | bool | false | Push to registry |
Cloud Config
| Field | Type | Default | Description |
|---|
provider | enum | - | aws, gcp, azure |
region | string | - | Deployment region |
service_name | string | - | Service name |
cpu | string | 256 | CPU allocation |
memory | string | 512 | Memory (MB) |
min_instances | int | 1 | Min instances |
max_instances | int | 10 | Max instances |
env_vars | dict | null | Environment vars |
SDK Deploy Class
Deploy programmatically using Python:
from praisonai.deploy import Deploy, DeployConfig, DeployType
from praisonai.deploy.models import APIConfig
config = DeployConfig(
type=DeployType.API,
api=APIConfig(host="127.0.0.1", port=8005, workers=1)
)
deploy = Deploy(config, "agents.yaml")
result = deploy.deploy()
print(f"URL: {result.url}")
Deploy Methods
| Method | Description |
|---|
deploy(background=False) | Execute deployment |
plan() | Generate deployment plan without executing |
status() | Get current deployment status |
doctor() | Run health checks |
destroy(force=False) | Destroy/delete deployment |
Troubleshooting
| Issue | Fix |
|---|
| No deploy section | Run praisonai deploy init |
| Invalid config | Run praisonai deploy validate |
| Missing deps | Run praisonai deploy doctor |
| Deploy failed | Check praisonai deploy status |
| Port in use | Change port in agents.yaml |
| Missing API key | export OPENAI_API_KEY="your-key" |
| Docker not running | Start Docker daemon |
| AWS credentials | export AWS_ACCESS_KEY_ID=... |
| GCP credentials | gcloud auth login |
