Add OpenAI-compatible endpoints and instance creation timestamp

This commit is contained in:
2025-07-27 12:07:33 +02:00
parent 1261232baa
commit e6652e52e1
7 changed files with 408 additions and 0 deletions

View File

@@ -295,6 +295,45 @@ const docTemplate = `{
}
}
}
},
"post": {
"description": "Forwards HTTP requests to the llama-server instance running on a specific port",
"tags": [
"instances"
],
"summary": "Proxy requests to a specific instance",
"parameters": [
{
"type": "string",
"description": "Instance Name",
"name": "name",
"in": "path",
"required": true
}
],
"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"
}
}
}
}
},
"/instances/{name}/restart": {
@@ -479,6 +518,58 @@ const docTemplate = `{
}
}
}
},
"/v1/": {
"post": {
"description": "Handles all POST requests to /v1/*, routing to the appropriate instance based on the request body",
"consumes": [
"application/json"
],
"tags": [
"openai"
],
"summary": "OpenAI-compatible proxy endpoint",
"responses": {
"200": {
"description": "OpenAI response"
},
"400": {
"description": "Invalid request body or model name",
"schema": {
"type": "string"
}
},
"500": {
"description": "Internal Server Error",
"schema": {
"type": "string"
}
}
}
}
},
"/v1/models": {
"get": {
"description": "Returns a list of instances in a format compatible with OpenAI API",
"tags": [
"openai"
],
"summary": "List instances in OpenAI-compatible format",
"responses": {
"200": {
"description": "List of OpenAI-compatible instances",
"schema": {
"$ref": "#/definitions/llamactl.OpenAIListInstancesResponse"
}
},
"500": {
"description": "Internal Server Error",
"schema": {
"type": "string"
}
}
}
}
}
},
"definitions": {
@@ -999,6 +1090,10 @@ const docTemplate = `{
"llamactl.Instance": {
"type": "object",
"properties": {
"created": {
"description": "Creation time",
"type": "integer"
},
"name": {
"type": "string"
},
@@ -1007,6 +1102,37 @@ const docTemplate = `{
"type": "boolean"
}
}
},
"llamactl.OpenAIInstance": {
"type": "object",
"properties": {
"created": {
"type": "integer"
},
"id": {
"type": "string"
},
"object": {
"type": "string"
},
"owned_by": {
"type": "string"
}
}
},
"llamactl.OpenAIListInstancesResponse": {
"type": "object",
"properties": {
"data": {
"type": "array",
"items": {
"$ref": "#/definitions/llamactl.OpenAIInstance"
}
},
"object": {
"type": "string"
}
}
}
}
}`

View File

@@ -288,6 +288,45 @@
}
}
}
},
"post": {
"description": "Forwards HTTP requests to the llama-server instance running on a specific port",
"tags": [
"instances"
],
"summary": "Proxy requests to a specific instance",
"parameters": [
{
"type": "string",
"description": "Instance Name",
"name": "name",
"in": "path",
"required": true
}
],
"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"
}
}
}
}
},
"/instances/{name}/restart": {
@@ -472,6 +511,58 @@
}
}
}
},
"/v1/": {
"post": {
"description": "Handles all POST requests to /v1/*, routing to the appropriate instance based on the request body",
"consumes": [
"application/json"
],
"tags": [
"openai"
],
"summary": "OpenAI-compatible proxy endpoint",
"responses": {
"200": {
"description": "OpenAI response"
},
"400": {
"description": "Invalid request body or model name",
"schema": {
"type": "string"
}
},
"500": {
"description": "Internal Server Error",
"schema": {
"type": "string"
}
}
}
}
},
"/v1/models": {
"get": {
"description": "Returns a list of instances in a format compatible with OpenAI API",
"tags": [
"openai"
],
"summary": "List instances in OpenAI-compatible format",
"responses": {
"200": {
"description": "List of OpenAI-compatible instances",
"schema": {
"$ref": "#/definitions/llamactl.OpenAIListInstancesResponse"
}
},
"500": {
"description": "Internal Server Error",
"schema": {
"type": "string"
}
}
}
}
}
},
"definitions": {
@@ -992,6 +1083,10 @@
"llamactl.Instance": {
"type": "object",
"properties": {
"created": {
"description": "Creation time",
"type": "integer"
},
"name": {
"type": "string"
},
@@ -1000,6 +1095,37 @@
"type": "boolean"
}
}
},
"llamactl.OpenAIInstance": {
"type": "object",
"properties": {
"created": {
"type": "integer"
},
"id": {
"type": "string"
},
"object": {
"type": "string"
},
"owned_by": {
"type": "string"
}
}
},
"llamactl.OpenAIListInstancesResponse": {
"type": "object",
"properties": {
"data": {
"type": "array",
"items": {
"$ref": "#/definitions/llamactl.OpenAIInstance"
}
},
"object": {
"type": "string"
}
}
}
}
}

View File

@@ -347,12 +347,35 @@ definitions:
type: object
llamactl.Instance:
properties:
created:
description: Creation time
type: integer
name:
type: string
running:
description: Status
type: boolean
type: object
llamactl.OpenAIInstance:
properties:
created:
type: integer
id:
type: string
object:
type: string
owned_by:
type: string
type: object
llamactl.OpenAIListInstancesResponse:
properties:
data:
items:
$ref: '#/definitions/llamactl.OpenAIInstance'
type: array
object:
type: string
type: object
info:
contact: {}
description: llamactl is a control server for managing Llama Server instances.
@@ -548,6 +571,33 @@ paths:
summary: Proxy requests to a specific instance
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
summary: Proxy requests to a specific instance
tags:
- instances
/instances/{name}/restart:
post:
description: Restarts a specific instance by name
@@ -668,4 +718,40 @@ paths:
summary: Get version of llama server
tags:
- server
/v1/:
post:
consumes:
- application/json
description: Handles all POST requests to /v1/*, routing to the appropriate
instance based on the request body
responses:
"200":
description: OpenAI response
"400":
description: Invalid request body or model name
schema:
type: string
"500":
description: Internal Server Error
schema:
type: string
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/llamactl.OpenAIListInstancesResponse'
"500":
description: Internal Server Error
schema:
type: string
summary: List instances in OpenAI-compatible format
tags:
- openai
swagger: "2.0"