plano/demos/hr_agent/arch_config.yaml
2024-10-18 14:41:04 -07:00

49 lines
1.6 KiB
YAML

version: v0.1
listener:
address: 127.0.0.1
port: 8080 #If you configure port 443, you'll need to update the listener with tls_certificates
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
# 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.
prompt_targets:
- name: headcount
description: Get headcount data for a region by staffing type
endpoint:
name: app_server
path: /agent/headcount
parameters:
- name: staffing_type
type: str
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.
- name: hr_qa
endpoint:
name: app_server
path: /agent/hr_qa
description: Handle general Q/A related to HR.
default: true