mirror of
https://github.com/lordmathis/llamactl.git
synced 2025-12-23 01:24:24 +00:00
Deployed 514b1b0 to dev with MkDocs 1.6.1 and mike 2.1.3
This commit is contained in:
190
dev/swagger.yaml
190
dev/swagger.yaml
@@ -1,5 +1,173 @@
|
||||
basePath: /api/v1
|
||||
definitions:
|
||||
config.AppConfig:
|
||||
properties:
|
||||
auth:
|
||||
$ref: '#/definitions/config.AuthConfig'
|
||||
backends:
|
||||
$ref: '#/definitions/config.BackendConfig'
|
||||
build_time:
|
||||
type: string
|
||||
commit_hash:
|
||||
type: string
|
||||
instances:
|
||||
$ref: '#/definitions/config.InstancesConfig'
|
||||
local_node:
|
||||
type: string
|
||||
nodes:
|
||||
additionalProperties:
|
||||
$ref: '#/definitions/config.NodeConfig'
|
||||
type: object
|
||||
server:
|
||||
$ref: '#/definitions/config.ServerConfig'
|
||||
version:
|
||||
type: string
|
||||
type: object
|
||||
config.AuthConfig:
|
||||
properties:
|
||||
inference_keys:
|
||||
description: List of keys for OpenAI compatible inference endpoints
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
management_keys:
|
||||
description: List of keys for management endpoints
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
require_inference_auth:
|
||||
description: Require authentication for OpenAI compatible inference endpoints
|
||||
type: boolean
|
||||
require_management_auth:
|
||||
description: Require authentication for management endpoints
|
||||
type: boolean
|
||||
type: object
|
||||
config.BackendConfig:
|
||||
properties:
|
||||
llama-cpp:
|
||||
$ref: '#/definitions/config.BackendSettings'
|
||||
mlx:
|
||||
$ref: '#/definitions/config.BackendSettings'
|
||||
vllm:
|
||||
$ref: '#/definitions/config.BackendSettings'
|
||||
type: object
|
||||
config.BackendSettings:
|
||||
properties:
|
||||
args:
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
command:
|
||||
type: string
|
||||
docker:
|
||||
$ref: '#/definitions/config.DockerSettings'
|
||||
environment:
|
||||
additionalProperties:
|
||||
type: string
|
||||
type: object
|
||||
response_headers:
|
||||
additionalProperties:
|
||||
type: string
|
||||
type: object
|
||||
type: object
|
||||
config.DockerSettings:
|
||||
properties:
|
||||
args:
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
enabled:
|
||||
type: boolean
|
||||
environment:
|
||||
additionalProperties:
|
||||
type: string
|
||||
type: object
|
||||
image:
|
||||
type: string
|
||||
type: object
|
||||
config.InstancesConfig:
|
||||
properties:
|
||||
auto_create_dirs:
|
||||
description: Automatically create the data directory if it doesn't exist
|
||||
type: boolean
|
||||
configs_dir:
|
||||
description: Instance config directory override
|
||||
type: string
|
||||
data_dir:
|
||||
description: Directory where all llamactl data will be stored (instances.json,
|
||||
logs, etc.)
|
||||
type: string
|
||||
default_auto_restart:
|
||||
description: Default auto-restart setting for new instances
|
||||
type: boolean
|
||||
default_max_restarts:
|
||||
description: Default max restarts for new instances
|
||||
type: integer
|
||||
default_on_demand_start:
|
||||
description: Default on-demand start setting for new instances
|
||||
type: boolean
|
||||
default_restart_delay:
|
||||
description: Default restart delay for new instances (in seconds)
|
||||
type: integer
|
||||
enable_lru_eviction:
|
||||
description: Enable LRU eviction for instance logs
|
||||
type: boolean
|
||||
logs_dir:
|
||||
description: Logs directory override
|
||||
type: string
|
||||
max_instances:
|
||||
description: Maximum number of instances that can be created
|
||||
type: integer
|
||||
max_running_instances:
|
||||
description: Maximum number of instances that can be running at the same time
|
||||
type: integer
|
||||
on_demand_start_timeout:
|
||||
description: How long to wait for an instance to start on demand (in seconds)
|
||||
type: integer
|
||||
port_range:
|
||||
description: Port range for instances (e.g., 8000,9000)
|
||||
items:
|
||||
type: integer
|
||||
type: array
|
||||
timeout_check_interval:
|
||||
description: Interval for checking instance timeouts (in minutes)
|
||||
type: integer
|
||||
type: object
|
||||
config.NodeConfig:
|
||||
properties:
|
||||
address:
|
||||
type: string
|
||||
api_key:
|
||||
type: string
|
||||
type: object
|
||||
config.ServerConfig:
|
||||
properties:
|
||||
allowed_headers:
|
||||
description: Allowed headers for CORS (e.g., "Accept", "Authorization", "Content-Type",
|
||||
"X-CSRF-Token")
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
allowed_origins:
|
||||
description: Allowed origins for CORS (e.g., "http://localhost:3000")
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
enable_swagger:
|
||||
description: Enable Swagger UI for API documentation
|
||||
type: boolean
|
||||
host:
|
||||
description: Server host to bind to
|
||||
type: string
|
||||
port:
|
||||
description: Server port to bind to
|
||||
type: integer
|
||||
response_headers:
|
||||
additionalProperties:
|
||||
type: string
|
||||
description: Response headers to send with responses
|
||||
type: object
|
||||
type: object
|
||||
instance.Instance:
|
||||
properties:
|
||||
created:
|
||||
@@ -13,6 +181,11 @@ definitions:
|
||||
auto_restart:
|
||||
description: Auto restart
|
||||
type: boolean
|
||||
command_override:
|
||||
type: string
|
||||
docker_enabled:
|
||||
description: Execution context overrides
|
||||
type: boolean
|
||||
environment:
|
||||
additionalProperties:
|
||||
type: string
|
||||
@@ -216,6 +389,23 @@ paths:
|
||||
summary: Parse vllm serve command
|
||||
tags:
|
||||
- Backends
|
||||
/api/v1/config:
|
||||
get:
|
||||
description: Returns the current server configuration (sanitized)
|
||||
responses:
|
||||
"200":
|
||||
description: Sanitized configuration
|
||||
schema:
|
||||
$ref: '#/definitions/config.AppConfig'
|
||||
"500":
|
||||
description: Internal Server Error
|
||||
schema:
|
||||
type: string
|
||||
security:
|
||||
- ApiKeyAuth: []
|
||||
summary: Get server configuration
|
||||
tags:
|
||||
- System
|
||||
/api/v1/instances:
|
||||
get:
|
||||
description: Returns a list of all instances managed by the server
|
||||
|
||||
Reference in New Issue
Block a user