logo

AiManagement

Get the details of all available Llm models

SecurityApiKeyAuth
Request
query Parameters
limit
integer [ 1 .. 1000 ]
Default: 100

Maximum number of objects to return per query. The value must be between 1 and 1000. Default is 100.

Example: limit=50
cursor
string [ 1 .. 4096 ] characters

Cursor to fetch the next or previous page of results. The value of this property must be extracted from the 'prev_cursor' or 'next_cursor' property of a PaginatedResponseMetadata which is contained in the response of list and search API endpoints.

sort
string or null

The field to sort results by. A property name with a prepended '-' signifies a descending order.

Enum: "id" "-id" "name" "-name"
Example: sort=name
Responses
200

Success

default

Unexpected Error

get/ai/management/model
Response samples
application/json
{
  • "items": [
    ],
  • "response_metadata": {
    }
}

Get the details of an LLM model

SecurityApiKeyAuth
Request
path Parameters
modelId
required
string non-empty

The id of the LLM model

Responses
200

Model details retrieved successfully

default

Unexpected Error

get/ai/management/model/{modelId}
Response samples
application/json
{
  • "id": "a638d976-6b7e-43f4-9212-90f4dc6d405c",
  • "name": "Llama-3.2-3B.Q4_K_M.gguf:latest",
  • "file_checksum": "2f231ba8da66ca5c965bc9d6babcf936b0f3eb641a199adc69cc2c0f8839c771",
  • "architecture": "llama",
  • "base_name": "Llama-3.2",
  • "ai_parameters": "1.2B",
  • "context_length": 131072,
  • "embedding_length": 4096,
  • "quantization": "Q4_K_M",
  • "is_data_generate_default": true
}

Upload the model file and register it with Ollama service

SecurityApiKeyAuth
Request
query Parameters
orchestratorId
string non-empty
Default: "default"

The orchestrator where the model should be installed. This must be "default".

Request Body schema: multipart/form-data
required
file
string <binary>
Responses
201

LLM Model uploaded successfully

post/ai/management/model/upload
Response samples
application/json
{
  • "job": {
    }
}

Get the details of all available gateways

SecurityApiKeyAuth
Request
query Parameters
limit
integer [ 1 .. 1000 ]
Default: 100

Maximum number of objects to return per query. The value must be between 1 and 1000. Default is 100.

Example: limit=50
cursor
string [ 1 .. 4096 ] characters

Cursor to fetch the next or previous page of results. The value of this property must be extracted from the 'prev_cursor' or 'next_cursor' property of a PaginatedResponseMetadata which is contained in the response of list and search API endpoints.

sort
string or null

The field to sort results by. A property name with a prepended '-' signifies a descending order.

Enum: "id" "-id" "hostname" "-hostname"
Example: sort=hostname
Responses
200

Success

default

Unexpected Error

get/ai/management/gateway
Response samples
application/json
{
  • "items": [
    ],
  • "response_metadata": {
    }
}
➔ Next to AiGenerate