mirror of
https://github.com/lordmathis/llamactl.git
synced 2025-12-22 17:14:22 +00:00
1205 lines
31 KiB
YAML
1205 lines
31 KiB
YAML
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:
|
|
description: Unix timestamp when the instance was created
|
|
type: integer
|
|
name:
|
|
type: string
|
|
type: object
|
|
instance.Options:
|
|
properties:
|
|
auto_restart:
|
|
description: Auto restart
|
|
type: boolean
|
|
command_override:
|
|
type: string
|
|
docker_enabled:
|
|
description: Execution context overrides
|
|
type: boolean
|
|
environment:
|
|
additionalProperties:
|
|
type: string
|
|
description: Environment variables
|
|
type: object
|
|
idle_timeout:
|
|
description: Idle timeout
|
|
type: integer
|
|
max_restarts:
|
|
type: integer
|
|
on_demand_start:
|
|
description: On demand start
|
|
type: boolean
|
|
restart_delay:
|
|
description: seconds
|
|
type: integer
|
|
type: object
|
|
server.NodeResponse:
|
|
properties:
|
|
address:
|
|
type: string
|
|
type: object
|
|
server.OpenAIInstance:
|
|
properties:
|
|
created:
|
|
type: integer
|
|
id:
|
|
type: string
|
|
object:
|
|
type: string
|
|
owned_by:
|
|
type: string
|
|
type: object
|
|
server.OpenAIListInstancesResponse:
|
|
properties:
|
|
data:
|
|
items:
|
|
$ref: '#/definitions/server.OpenAIInstance'
|
|
type: array
|
|
object:
|
|
type: string
|
|
type: object
|
|
server.ParseCommandRequest:
|
|
properties:
|
|
command:
|
|
type: string
|
|
type: object
|
|
info:
|
|
contact: {}
|
|
description: llamactl is a control server for managing Llama Server instances.
|
|
license:
|
|
name: MIT License
|
|
url: https://opensource.org/license/mit/
|
|
title: llamactl API
|
|
version: "1.0"
|
|
paths:
|
|
/api/v1/backends/llama-cpp/devices:
|
|
get:
|
|
description: Returns a list of available devices for the llama server
|
|
responses:
|
|
"200":
|
|
description: List of devices
|
|
schema:
|
|
type: string
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: List available devices for llama server
|
|
tags:
|
|
- Backends
|
|
/api/v1/backends/llama-cpp/help:
|
|
get:
|
|
description: Returns the help text for the llama server command
|
|
responses:
|
|
"200":
|
|
description: Help text
|
|
schema:
|
|
type: string
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: Get help for llama server
|
|
tags:
|
|
- Backends
|
|
/api/v1/backends/llama-cpp/parse-command:
|
|
post:
|
|
consumes:
|
|
- application/json
|
|
description: Parses a llama-server command string into instance options
|
|
parameters:
|
|
- description: Command to parse
|
|
in: body
|
|
name: request
|
|
required: true
|
|
schema:
|
|
$ref: '#/definitions/server.ParseCommandRequest'
|
|
produces:
|
|
- application/json
|
|
responses:
|
|
"200":
|
|
description: Parsed options
|
|
schema:
|
|
$ref: '#/definitions/instance.Options'
|
|
"400":
|
|
description: Invalid request or command
|
|
schema:
|
|
additionalProperties:
|
|
type: string
|
|
type: object
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
additionalProperties:
|
|
type: string
|
|
type: object
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: Parse llama-server command
|
|
tags:
|
|
- Backends
|
|
/api/v1/backends/llama-cpp/version:
|
|
get:
|
|
description: Returns the version of the llama server command
|
|
responses:
|
|
"200":
|
|
description: Version information
|
|
schema:
|
|
type: string
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: Get version of llama server
|
|
tags:
|
|
- Backends
|
|
/api/v1/backends/mlx/parse-command:
|
|
post:
|
|
consumes:
|
|
- application/json
|
|
description: Parses MLX-LM server command string into instance options
|
|
parameters:
|
|
- description: Command to parse
|
|
in: body
|
|
name: request
|
|
required: true
|
|
schema:
|
|
$ref: '#/definitions/server.ParseCommandRequest'
|
|
produces:
|
|
- application/json
|
|
responses:
|
|
"200":
|
|
description: Parsed options
|
|
schema:
|
|
$ref: '#/definitions/instance.Options'
|
|
"400":
|
|
description: Invalid request or command
|
|
schema:
|
|
additionalProperties:
|
|
type: string
|
|
type: object
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: Parse mlx_lm.server command
|
|
tags:
|
|
- Backends
|
|
/api/v1/backends/vllm/parse-command:
|
|
post:
|
|
consumes:
|
|
- application/json
|
|
description: Parses a vLLM serve command string into instance options
|
|
parameters:
|
|
- description: Command to parse
|
|
in: body
|
|
name: request
|
|
required: true
|
|
schema:
|
|
$ref: '#/definitions/server.ParseCommandRequest'
|
|
produces:
|
|
- application/json
|
|
responses:
|
|
"200":
|
|
description: Parsed options
|
|
schema:
|
|
$ref: '#/definitions/instance.Options'
|
|
"400":
|
|
description: Invalid request or command
|
|
schema:
|
|
additionalProperties:
|
|
type: string
|
|
type: object
|
|
security:
|
|
- ApiKeyAuth: []
|
|
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
|
|
responses:
|
|
"200":
|
|
description: List of instances
|
|
schema:
|
|
items:
|
|
$ref: '#/definitions/instance.Instance'
|
|
type: array
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: List all instances
|
|
tags:
|
|
- Instances
|
|
/api/v1/instances/{name}:
|
|
delete:
|
|
description: Stops and removes a specific instance by name
|
|
parameters:
|
|
- description: Instance Name
|
|
in: path
|
|
name: name
|
|
required: true
|
|
type: string
|
|
responses:
|
|
"204":
|
|
description: No Content
|
|
"400":
|
|
description: Invalid name format
|
|
schema:
|
|
type: string
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: Delete an instance
|
|
tags:
|
|
- Instances
|
|
get:
|
|
description: Returns the details of a specific instance by name
|
|
parameters:
|
|
- description: Instance Name
|
|
in: path
|
|
name: name
|
|
required: true
|
|
type: string
|
|
responses:
|
|
"200":
|
|
description: Instance details
|
|
schema:
|
|
$ref: '#/definitions/instance.Instance'
|
|
"400":
|
|
description: Invalid name format
|
|
schema:
|
|
type: string
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: Get details of a specific instance
|
|
tags:
|
|
- Instances
|
|
post:
|
|
consumes:
|
|
- application/json
|
|
description: Creates a new instance with the provided configuration options
|
|
parameters:
|
|
- description: Instance Name
|
|
in: path
|
|
name: name
|
|
required: true
|
|
type: string
|
|
- description: Instance configuration options
|
|
in: body
|
|
name: options
|
|
required: true
|
|
schema:
|
|
$ref: '#/definitions/instance.Options'
|
|
responses:
|
|
"201":
|
|
description: Created instance details
|
|
schema:
|
|
$ref: '#/definitions/instance.Instance'
|
|
"400":
|
|
description: Invalid request body
|
|
schema:
|
|
type: string
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: Create and start a new instance
|
|
tags:
|
|
- Instances
|
|
put:
|
|
consumes:
|
|
- application/json
|
|
description: Updates the configuration of a specific instance by name
|
|
parameters:
|
|
- description: Instance Name
|
|
in: path
|
|
name: name
|
|
required: true
|
|
type: string
|
|
- description: Instance configuration options
|
|
in: body
|
|
name: options
|
|
required: true
|
|
schema:
|
|
$ref: '#/definitions/instance.Options'
|
|
responses:
|
|
"200":
|
|
description: Updated instance details
|
|
schema:
|
|
$ref: '#/definitions/instance.Instance'
|
|
"400":
|
|
description: Invalid name format
|
|
schema:
|
|
type: string
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: Update an instance's configuration
|
|
tags:
|
|
- Instances
|
|
/api/v1/instances/{name}/logs:
|
|
get:
|
|
description: Returns the logs from a specific instance by name with optional
|
|
line limit
|
|
parameters:
|
|
- description: Instance Name
|
|
in: path
|
|
name: name
|
|
required: true
|
|
type: string
|
|
- description: 'Number of lines to retrieve (default: all lines)'
|
|
in: query
|
|
name: lines
|
|
type: string
|
|
responses:
|
|
"200":
|
|
description: Instance logs
|
|
schema:
|
|
type: string
|
|
"400":
|
|
description: Invalid name format or lines parameter
|
|
schema:
|
|
type: string
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: Get logs from a specific instance
|
|
tags:
|
|
- Instances
|
|
/api/v1/instances/{name}/proxy:
|
|
get:
|
|
description: Forwards HTTP requests to the llama-server instance running on
|
|
a specific port
|
|
parameters:
|
|
- description: Instance Name
|
|
in: path
|
|
name: name
|
|
required: true
|
|
type: string
|
|
responses:
|
|
"200":
|
|
description: Request successfully proxied to instance
|
|
"400":
|
|
description: Invalid name format
|
|
schema:
|
|
type: string
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
"503":
|
|
description: Instance is not running
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: Proxy requests to a specific instance, does not autostart instance
|
|
if stopped
|
|
tags:
|
|
- Instances
|
|
post:
|
|
description: Forwards HTTP requests to the llama-server instance running on
|
|
a specific port
|
|
parameters:
|
|
- description: Instance Name
|
|
in: path
|
|
name: name
|
|
required: true
|
|
type: string
|
|
responses:
|
|
"200":
|
|
description: Request successfully proxied to instance
|
|
"400":
|
|
description: Invalid name format
|
|
schema:
|
|
type: string
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
"503":
|
|
description: Instance is not running
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: Proxy requests to a specific instance, does not autostart instance
|
|
if stopped
|
|
tags:
|
|
- Instances
|
|
/api/v1/instances/{name}/restart:
|
|
post:
|
|
description: Restarts a specific instance by name
|
|
parameters:
|
|
- description: Instance Name
|
|
in: path
|
|
name: name
|
|
required: true
|
|
type: string
|
|
responses:
|
|
"200":
|
|
description: Restarted instance details
|
|
schema:
|
|
$ref: '#/definitions/instance.Instance'
|
|
"400":
|
|
description: Invalid name format
|
|
schema:
|
|
type: string
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: Restart a running instance
|
|
tags:
|
|
- Instances
|
|
/api/v1/instances/{name}/start:
|
|
post:
|
|
description: Starts a specific instance by name
|
|
parameters:
|
|
- description: Instance Name
|
|
in: path
|
|
name: name
|
|
required: true
|
|
type: string
|
|
responses:
|
|
"200":
|
|
description: Started instance details
|
|
schema:
|
|
$ref: '#/definitions/instance.Instance'
|
|
"400":
|
|
description: Invalid name format
|
|
schema:
|
|
type: string
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: Start a stopped instance
|
|
tags:
|
|
- Instances
|
|
/api/v1/instances/{name}/stop:
|
|
post:
|
|
description: Stops a specific instance by name
|
|
parameters:
|
|
- description: Instance Name
|
|
in: path
|
|
name: name
|
|
required: true
|
|
type: string
|
|
responses:
|
|
"200":
|
|
description: Stopped instance details
|
|
schema:
|
|
$ref: '#/definitions/instance.Instance'
|
|
"400":
|
|
description: Invalid name format
|
|
schema:
|
|
type: string
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: Stop a running instance
|
|
tags:
|
|
- Instances
|
|
/api/v1/nodes:
|
|
get:
|
|
description: Returns a map of all nodes configured in the server (node name
|
|
-> node config)
|
|
responses:
|
|
"200":
|
|
description: Map of nodes
|
|
schema:
|
|
additionalProperties:
|
|
$ref: '#/definitions/server.NodeResponse'
|
|
type: object
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: List all configured nodes
|
|
tags:
|
|
- Nodes
|
|
/api/v1/nodes/{name}:
|
|
get:
|
|
description: Returns the details of a specific node by name
|
|
parameters:
|
|
- description: Node Name
|
|
in: path
|
|
name: name
|
|
required: true
|
|
type: string
|
|
responses:
|
|
"200":
|
|
description: Node details
|
|
schema:
|
|
$ref: '#/definitions/server.NodeResponse'
|
|
"400":
|
|
description: Invalid name format
|
|
schema:
|
|
type: string
|
|
"404":
|
|
description: Node not found
|
|
schema:
|
|
type: string
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: Get details of a specific node
|
|
tags:
|
|
- Nodes
|
|
/api/v1/version:
|
|
get:
|
|
description: Returns the version of the llamactl command
|
|
responses:
|
|
"200":
|
|
description: Version information
|
|
schema:
|
|
type: string
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: Get llamactl version
|
|
tags:
|
|
- System
|
|
/llama-cpp/{name}/:
|
|
get:
|
|
description: Proxies requests to the llama.cpp UI for the specified instance
|
|
parameters:
|
|
- description: Instance Name
|
|
in: query
|
|
name: name
|
|
required: true
|
|
type: string
|
|
produces:
|
|
- text/html
|
|
responses:
|
|
"200":
|
|
description: Proxied HTML response
|
|
schema:
|
|
type: string
|
|
"400":
|
|
description: Invalid instance
|
|
schema:
|
|
type: string
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: Proxy requests to llama.cpp UI for the instance
|
|
tags:
|
|
- Llama.cpp
|
|
/llama-cpp/{name}/apply-template:
|
|
post:
|
|
description: Proxies requests to the specified llama.cpp server instance, starting
|
|
it on-demand if configured
|
|
parameters:
|
|
- description: Instance Name
|
|
in: path
|
|
name: name
|
|
required: true
|
|
type: string
|
|
produces:
|
|
- application/json
|
|
responses:
|
|
"200":
|
|
description: Proxied response
|
|
schema:
|
|
additionalProperties: true
|
|
type: object
|
|
"400":
|
|
description: Invalid instance
|
|
schema:
|
|
type: string
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: Proxy requests to llama.cpp server instance
|
|
tags:
|
|
- Llama.cpp
|
|
/llama-cpp/{name}/completion:
|
|
post:
|
|
description: Proxies requests to the specified llama.cpp server instance, starting
|
|
it on-demand if configured
|
|
parameters:
|
|
- description: Instance Name
|
|
in: path
|
|
name: name
|
|
required: true
|
|
type: string
|
|
produces:
|
|
- application/json
|
|
responses:
|
|
"200":
|
|
description: Proxied response
|
|
schema:
|
|
additionalProperties: true
|
|
type: object
|
|
"400":
|
|
description: Invalid instance
|
|
schema:
|
|
type: string
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: Proxy requests to llama.cpp server instance
|
|
tags:
|
|
- Llama.cpp
|
|
/llama-cpp/{name}/detokenize:
|
|
post:
|
|
description: Proxies requests to the specified llama.cpp server instance, starting
|
|
it on-demand if configured
|
|
parameters:
|
|
- description: Instance Name
|
|
in: path
|
|
name: name
|
|
required: true
|
|
type: string
|
|
produces:
|
|
- application/json
|
|
responses:
|
|
"200":
|
|
description: Proxied response
|
|
schema:
|
|
additionalProperties: true
|
|
type: object
|
|
"400":
|
|
description: Invalid instance
|
|
schema:
|
|
type: string
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: Proxy requests to llama.cpp server instance
|
|
tags:
|
|
- Llama.cpp
|
|
/llama-cpp/{name}/embeddings:
|
|
post:
|
|
description: Proxies requests to the specified llama.cpp server instance, starting
|
|
it on-demand if configured
|
|
parameters:
|
|
- description: Instance Name
|
|
in: path
|
|
name: name
|
|
required: true
|
|
type: string
|
|
produces:
|
|
- application/json
|
|
responses:
|
|
"200":
|
|
description: Proxied response
|
|
schema:
|
|
additionalProperties: true
|
|
type: object
|
|
"400":
|
|
description: Invalid instance
|
|
schema:
|
|
type: string
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: Proxy requests to llama.cpp server instance
|
|
tags:
|
|
- Llama.cpp
|
|
/llama-cpp/{name}/infill:
|
|
post:
|
|
description: Proxies requests to the specified llama.cpp server instance, starting
|
|
it on-demand if configured
|
|
parameters:
|
|
- description: Instance Name
|
|
in: path
|
|
name: name
|
|
required: true
|
|
type: string
|
|
produces:
|
|
- application/json
|
|
responses:
|
|
"200":
|
|
description: Proxied response
|
|
schema:
|
|
additionalProperties: true
|
|
type: object
|
|
"400":
|
|
description: Invalid instance
|
|
schema:
|
|
type: string
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: Proxy requests to llama.cpp server instance
|
|
tags:
|
|
- Llama.cpp
|
|
/llama-cpp/{name}/metrics:
|
|
post:
|
|
description: Proxies requests to the specified llama.cpp server instance, starting
|
|
it on-demand if configured
|
|
parameters:
|
|
- description: Instance Name
|
|
in: path
|
|
name: name
|
|
required: true
|
|
type: string
|
|
produces:
|
|
- application/json
|
|
responses:
|
|
"200":
|
|
description: Proxied response
|
|
schema:
|
|
additionalProperties: true
|
|
type: object
|
|
"400":
|
|
description: Invalid instance
|
|
schema:
|
|
type: string
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: Proxy requests to llama.cpp server instance
|
|
tags:
|
|
- Llama.cpp
|
|
/llama-cpp/{name}/props:
|
|
get:
|
|
description: Proxies requests to the specified llama.cpp server instance, starting
|
|
it on-demand if configured
|
|
parameters:
|
|
- description: Instance Name
|
|
in: path
|
|
name: name
|
|
required: true
|
|
type: string
|
|
produces:
|
|
- application/json
|
|
responses:
|
|
"200":
|
|
description: Proxied response
|
|
schema:
|
|
additionalProperties: true
|
|
type: object
|
|
"400":
|
|
description: Invalid instance
|
|
schema:
|
|
type: string
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: Proxy requests to llama.cpp server instance
|
|
tags:
|
|
- Llama.cpp
|
|
post:
|
|
description: Proxies requests to the specified llama.cpp server instance, starting
|
|
it on-demand if configured
|
|
parameters:
|
|
- description: Instance Name
|
|
in: path
|
|
name: name
|
|
required: true
|
|
type: string
|
|
produces:
|
|
- application/json
|
|
responses:
|
|
"200":
|
|
description: Proxied response
|
|
schema:
|
|
additionalProperties: true
|
|
type: object
|
|
"400":
|
|
description: Invalid instance
|
|
schema:
|
|
type: string
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: Proxy requests to llama.cpp server instance
|
|
tags:
|
|
- Llama.cpp
|
|
/llama-cpp/{name}/reranking:
|
|
post:
|
|
description: Proxies requests to the specified llama.cpp server instance, starting
|
|
it on-demand if configured
|
|
parameters:
|
|
- description: Instance Name
|
|
in: path
|
|
name: name
|
|
required: true
|
|
type: string
|
|
produces:
|
|
- application/json
|
|
responses:
|
|
"200":
|
|
description: Proxied response
|
|
schema:
|
|
additionalProperties: true
|
|
type: object
|
|
"400":
|
|
description: Invalid instance
|
|
schema:
|
|
type: string
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: Proxy requests to llama.cpp server instance
|
|
tags:
|
|
- Llama.cpp
|
|
/llama-cpp/{name}/slots:
|
|
get:
|
|
description: Proxies requests to the specified llama.cpp server instance, starting
|
|
it on-demand if configured
|
|
parameters:
|
|
- description: Instance Name
|
|
in: path
|
|
name: name
|
|
required: true
|
|
type: string
|
|
produces:
|
|
- application/json
|
|
responses:
|
|
"200":
|
|
description: Proxied response
|
|
schema:
|
|
additionalProperties: true
|
|
type: object
|
|
"400":
|
|
description: Invalid instance
|
|
schema:
|
|
type: string
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: Proxy requests to llama.cpp server instance
|
|
tags:
|
|
- Llama.cpp
|
|
/llama-cpp/{name}/tokenize:
|
|
post:
|
|
description: Proxies requests to the specified llama.cpp server instance, starting
|
|
it on-demand if configured
|
|
parameters:
|
|
- description: Instance Name
|
|
in: path
|
|
name: name
|
|
required: true
|
|
type: string
|
|
produces:
|
|
- application/json
|
|
responses:
|
|
"200":
|
|
description: Proxied response
|
|
schema:
|
|
additionalProperties: true
|
|
type: object
|
|
"400":
|
|
description: Invalid instance
|
|
schema:
|
|
type: string
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: Proxy requests to llama.cpp server instance
|
|
tags:
|
|
- Llama.cpp
|
|
/v1/:
|
|
post:
|
|
consumes:
|
|
- application/json
|
|
description: Handles all POST requests to /v1/*, routing to the appropriate
|
|
instance based on the request body. Requires API key authentication via the
|
|
`Authorization` header.
|
|
responses:
|
|
"200":
|
|
description: OpenAI response
|
|
"400":
|
|
description: Invalid request body or instance name
|
|
schema:
|
|
type: string
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: OpenAI-compatible proxy endpoint
|
|
tags:
|
|
- OpenAI
|
|
/v1/models:
|
|
get:
|
|
description: Returns a list of instances in a format compatible with OpenAI
|
|
API
|
|
responses:
|
|
"200":
|
|
description: List of OpenAI-compatible instances
|
|
schema:
|
|
$ref: '#/definitions/server.OpenAIListInstancesResponse'
|
|
"500":
|
|
description: Internal Server Error
|
|
schema:
|
|
type: string
|
|
security:
|
|
- ApiKeyAuth: []
|
|
summary: List instances in OpenAI-compatible format
|
|
tags:
|
|
- OpenAI
|
|
securityDefinitions:
|
|
ApiKeyAuth:
|
|
in: header
|
|
name: X-API-Key
|
|
type: apiKey
|
|
swagger: "2.0"
|