Configuration Reference

The following is a complete reference of the arch_config.yml that controls the behavior of a single instance of the Arch gateway. This where you enable capabilities like routing to upstream LLm providers, defining prompt_targets where prompts get routed to, apply guardrails, and enable critical agent observability features.

 1version: v0.1
 2
 3listeners:
 4  ingress_traffic:
 5    address: 0.0.0.0
 6    port: 10000
 7    message_format: openai
 8    timeout: 5s
 9  egress_traffic:
10    address: 0.0.0.0
11    port: 12000
12    message_format: openai
13    timeout: 5s
14
15# Arch creates a round-robin load balancing between different endpoints, managed via the cluster subsystem.
16endpoints:
17  app_server:
18    # value could be ip address or a hostname with port
19    # this could also be a list of endpoints for load balancing
20    # for example endpoint: [ ip1:port, ip2:port ]
21    endpoint: 127.0.0.1:80
22    # max time to wait for a connection to be established
23    connect_timeout: 0.005s
24
25  mistral_local:
26    endpoint: 127.0.0.1:8001
27
28  error_target:
29    endpoint: error_target_1
30
31# Centralized way to manage LLMs, manage keys, retry logic, failover and limits in a central way
32llm_providers:
33  - name: openai/gpt-4o
34    access_key: $OPENAI_API_KEY
35    model: openai/gpt-4o
36    default: true
37
38  - access_key: $MISTRAL_API_KEY
39    model: mistral/mistral-8x7b
40
41  - model: mistral/mistral-7b-instruct
42    base_url: http://mistral_local
43
44# provides a way to override default settings for the arch system
45overrides:
46  # By default Arch uses an NLI + embedding approach to match an incoming prompt to a prompt target.
47  # The intent matching threshold is kept at 0.80, you can override this behavior if you would like
48  prompt_target_intent_matching_threshold: 0.60
49
50# default system prompt used by all prompt targets
51system_prompt: You are a network assistant that just offers facts; not advice on manufacturers or purchasing decisions.
52
53prompt_guards:
54  input_guards:
55    jailbreak:
56      on_exception:
57        message: Looks like you're curious about my abilities, but I can only provide assistance within my programmed parameters.
58
59prompt_targets:
60  - name: information_extraction
61    default: true
62    description: handel all scenarios that are question and answer in nature. Like summarization, information extraction, etc.
63    endpoint:
64      name: app_server
65      path: /agent/summary
66      http_method: POST
67    # Arch uses the default LLM and treats the response from the endpoint as the prompt to send to the LLM
68    auto_llm_dispatch_on_response: true
69    # override system prompt for this prompt target
70    system_prompt: You are a helpful information extraction assistant. Use the information that is provided to you.
71
72  - name: reboot_network_device
73    description: Reboot a specific network device
74    endpoint:
75      name: app_server
76      path: /agent/action
77    parameters:
78      - name: device_id
79        type: str
80        description: Identifier of the network device to reboot.
81        required: true
82      - name: confirmation
83        type: bool
84        description: Confirmation flag to proceed with reboot.
85        default: false
86        enum: [true, false]
87
88tracing:
89  # sampling rate. Note by default Arch works on OpenTelemetry compatible tracing.
90  sampling_rate: 0.1