plano/demos/advanced/multi_turn_rag/config.yaml
Adil Hafeez 5a4f8cb321
Standardize demo configs and CLI templates to v0.3.0
- Update all demo config files to version v0.3.0
- Rename llm_providers → model_providers across all configs
- Modernize listener format from object to array style
  (e.g. listeners: [{type: model, name:, port:}])
- Replace chatbot_ui with AnythingLLM in 6 docker-compose files
- Remove prometheus/grafana services from llm_gateway and
  preference_based_routing docker-compose files
- Add tracing: random_sampling: 100 to configs that lacked it
- Update 3 CLI init templates (coding_agent_routing,
  preference_aware_routing, conversational_state_v1_responses)
- Fix test_init.py assertion for model_providers key

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-15 01:43:59 -08:00

56 lines
1.7 KiB
YAML

version: v0.3.0
listeners:
- type: prompt
name: prompt_listener
port: 10000
endpoints:
rag_energy_source_agent:
endpoint: host.docker.internal:18083
connect_timeout: 0.005s
model_providers:
- access_key: $OPENAI_API_KEY
model: openai/gpt-4o-mini
default: true
system_prompt: |
You are a helpful assistant and can offer information about energy sources.
You will get a JSON object with energy_source and consideration fields. Focus on answering the querstion using those fields.
Keep your responses to just three main points to make it easy for the reader to digest the information
prompt_targets:
- name: get_info_for_energy_source
description: get information about an energy source
parameters:
- name: energy_source
type: str
description: a source of energy
required: true
enum: [renewable, fossil]
- name: consideration
type: str
description: a specific type of consideration for an energy source
enum: [cost, economic, technology]
endpoint:
name: rag_energy_source_agent
path: /agent/energy_source_info
http_method: POST
- name: default_target
default: true
description: This is the default target for all unmatched prompts.
endpoint:
name: rag_energy_source_agent
path: /default_target
http_method: POST
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