mirror of
https://github.com/katanemo/plano.git
synced 2026-04-25 08:46:24 +02:00
b30ad791f7
* Fix link issues and add icons * Improve Doc * fix test * making minor modifications to shuguangs' doc changes --------- Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-261.local> Co-authored-by: Adil Hafeez <adil@katanemo.com>
44 lines
1.4 KiB
YAML
44 lines
1.4 KiB
YAML
version: v0.1
|
|
|
|
listen:
|
|
address: 0.0.0.0 # or 127.0.0.1
|
|
port: 10000
|
|
# Defines how Arch should parse the content from application/json or text/pain Content-type in the http request
|
|
message_format: huggingface
|
|
|
|
# Centralized way to manage LLMs, manage keys, retry logic, failover and limits in a central way
|
|
llm_providers:
|
|
- name: OpenAI
|
|
provider: openai
|
|
access_key: OPENAI_API_KEY
|
|
model: gpt-4o
|
|
default: true
|
|
stream: true
|
|
|
|
# default system prompt used by all prompt targets
|
|
system_prompt: You are a network assistant that just offers facts; not advice on manufacturers or purchasing decisions.
|
|
|
|
prompt_targets:
|
|
- name: reboot_devices
|
|
description: Reboot specific devices or device groups
|
|
|
|
path: /agent/device_reboot
|
|
parameters:
|
|
- name: device_ids
|
|
type: list
|
|
description: A list of device identifiers (IDs) to reboot.
|
|
required: false
|
|
- name: device_group
|
|
type: str
|
|
description: The name of the device group to reboot
|
|
required: false
|
|
|
|
# Arch creates a round-robin load balancing between different endpoints, managed via the cluster subsystem.
|
|
endpoints:
|
|
app_server:
|
|
# value could be ip address or a hostname with port
|
|
# this could also be a list of endpoints for load balancing
|
|
# for example endpoint: [ ip1:port, ip2:port ]
|
|
endpoint: 127.0.0.1:80
|
|
# max time to wait for a connection to be established
|
|
connect_timeout: 0.005s
|