plano/demos/weather_forecast/arch_config.yaml
2024-11-07 22:11:00 -06:00

77 lines
1.9 KiB
YAML

version: "0.1-beta"
listener:
address: 0.0.0.0
port: 10000
message_format: huggingface
connect_timeout: 0.005s
endpoints:
weather_forecast_service:
endpoint: host.docker.internal:18083
connect_timeout: 0.005s
overrides:
# confidence threshold for prompt target intent matching
prompt_target_intent_matching_threshold: 0.6
llm_providers:
- name: gpt-4o-mini
access_key: $OPENAI_API_KEY
provider: openai
model: gpt-4o-mini
default: true
- name: gpt-3.5-turbo-0125
access_key: $OPENAI_API_KEY
provider: openai
model: gpt-3.5-turbo-0125
- name: gpt-4o
access_key: $OPENAI_API_KEY
provider: openai
model: gpt-4o
- name: ministral-3b
access_key: $MISTRAL_API_KEY
provider: mistral
model: ministral-3b-latest
system_prompt: |
You are a helpful assistant.
prompt_targets:
- name: weather_forecast
description: Check weather information for a given city.
parameters:
- name: city
description: the name of the city
required: true
type: str
- name: days
description: the number of days
type: int
required: true
- name: units
description: the temperature unit, e.g., Celsius and Fahrenheit
type: str
default: Fahrenheit
endpoint:
name: weather_forecast_service
path: /weather
- name: default_target
default: true
description: This is the default target for all unmatched prompts.
endpoint:
name: weather_forecast_service
path: /default_target
system_prompt: |
You are a helpful assistant! Summarize the user's request and provide a helpful response.
# if it is set to false arch will send response that it received from this prompt target to the user
# if true arch will forward the response to the default LLM
auto_llm_dispatch_on_response: false
tracing:
random_sampling: 100
trace_arch_internal: true