apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-06-17 15:25:17 +02:00
Code Issues Projects Releases Packages Wiki Activity

updating the HR agent config

Browse source
This commit is contained in:
Salman Paracha 2024-10-18 14:41:04 -07:00
parent 93c88d60c5
commit dfaa93e2fa
1 changed files with 12 additions and 21 deletions
Download patch file Download diff file Expand all files Collapse all files

33
demos/hr_agent/arch_config.yaml
View file

@ -12,6 +12,16 @@ llm_providers:
model: gpt-4o
default: true
# 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: host.docker.internal:18083
# max time to wait for a connection to be established
connect_timeout: 0.005s
# default system prompt used by all prompt targets
system_prompt: |
You are a HR agent assistant that helps HR decision makers with reporting and workfoce planning. Nothing else. Please stay on topic of HR.
@ -25,34 +35,15 @@ prompt_targets:
parameters:
- name: staffing_type
type: str
description: The staffing type like contract, fte or agency
description: The staffing type like contract, fte or agency
required: true
- name: region
type: str
required: true
description: the geographical region for which you want headcount data.
description: the geographical region for which you want headcount data.
- name: hr_qa
endpoint:
name: app_server
path: /agent/hr_qa
description: Handle general Q/A related to HR.
default: true
# 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: host.docker.internal:18083
# max time to wait for a connection to be established
connect_timeout: 0.005s
ratelimits:
- model: gpt-4
selector:
key: selector-key
value: selector-value
limit:
tokens: 1
unit: minute