How run-llama/llama_deploy works
LlamaDeploy is a deprecated workflow deployment platform: operators configure deployments through the CLI or API, then clients submit tasks and manage sessions against the API server. The server parses deployment configuration, manages workflow services and task execution, and exposes status, task/event, and optional UI-proxy endpoints. The graph also preserves source-management, metrics, and tracing responsibilities. Some modules were not excerpted; edges are limited to relationships visible in excerpts or the source index.
Main entry points: deployments.py Deployment routes · app.py FastAPI app · server.py Server lifecycle · apiserver.py API client models
Components 26
Operator tools
- CLI commands
llama_deploy/cli/__init__.py - Project init
llama_deploy/cli/init.py - CLI config
llama_deploy/cli/internal/config.py - Session commands
llama_deploy/cli/sessions.py
API server
- FastAPI app
llama_deploy/apiserver/app.py - Server lifecycle
llama_deploy/apiserver/server.py - Deployment routes
llama_deploy/apiserver/routers/deployments.py - Status routes
llama_deploy/apiserver/routers/status.py - Server settings
llama_deploy/apiserver/settings.py - Tracing
llama_deploy/apiserver/tracing.py - Metrics state
llama_deploy/apiserver/stats.py
Workflow runtime
- Config parser
llama_deploy/apiserver/deployment_config_parser.py - Deployment manager
llama_deploy/apiserver/deployment.py - Source manager interface
llama_deploy/apiserver/source_managers/base.py - Git source
llama_deploy/apiserver/source_managers/git.py - Local source
llama_deploy/apiserver/source_managers/local.py - Workflow services
llama_deploy/apiserver/deployment.py - Tasks and sessions
llama_deploy/apiserver/routers/deployments.py
Client and contracts
- Python client
llama_deploy/client/client.py - API client models
llama_deploy/client/models/apiserver.py - HTTP transport
llama_deploy/client/base.py - Task/session types
llama_deploy/types/core.py - API status types
llama_deploy/types/apiserver.py
Other components
- Operator
- Deployment UI
- Metrics exporter
Connections 29
- Operator → CLI commands: runs commands
- CLI commands → Project init: offers init
llama_deploy/cli/__init__.py - CLI commands → Session commands: offers sessions
llama_deploy/cli/__init__.py - Session commands → CLI config: loads profile
llama_deploy/cli/sessions.py - Session commands → Python client: creates client
llama_deploy/cli/sessions.py - Project init → Config parser: uses schema
llama_deploy/cli/init.py - Python client → API client models: exposes API
llama_deploy/client/client.py - API client models → HTTP transport: sends requests
llama_deploy/client/models/apiserver.py - API client models → Task/session types: uses payloads
llama_deploy/client/models/apiserver.py - API client models → API status types: uses status
llama_deploy/client/models/apiserver.py - API client models → FastAPI app: calls HTTP API
llama_deploy/client/models/apiserver.py - FastAPI app → Deployment routes: mounts routes
llama_deploy/apiserver/app.py - FastAPI app → Status routes: mounts routes
llama_deploy/apiserver/app.py - FastAPI app → Server lifecycle: sets lifespan
llama_deploy/apiserver/app.py - FastAPI app → Tracing: configures tracing
llama_deploy/apiserver/app.py - Server lifecycle → Deployment manager: starts and deploys
llama_deploy/apiserver/server.py - Server lifecycle → Config parser: parses startup config
llama_deploy/apiserver/server.py - Server lifecycle → Server settings: reads settings
llama_deploy/apiserver/server.py - Server lifecycle → Metrics state: updates state
llama_deploy/apiserver/server.py - Deployment routes → Deployment manager: deploys config
llama_deploy/apiserver/routers/deployments.py - Deployment routes → Config parser: parses uploads
llama_deploy/apiserver/routers/deployments.py - Deployment routes → Workflow services: runs workflows
llama_deploy/apiserver/routers/deployments.py - Deployment routes → Tasks and sessions: serves task operations
llama_deploy/apiserver/routers/deployments.py - Deployment routes → Deployment UI: proxies UI traffic
llama_deploy/apiserver/routers/deployments.py - Deployment manager → Source manager interface: uses source interface
llama_deploy/apiserver/deployment.py - Source manager interface → Config parser: uses source schema
llama_deploy/apiserver/source_managers/base.py - Git source → Source manager interface: implements interface
llama_deploy/apiserver/source_managers/git.py - Local source → Source manager interface: implements interface
llama_deploy/apiserver/source_managers/local.py - Server settings → Metrics exporter: enables exporter