mirror of
https://github.com/katanemo/plano.git
synced 2026-04-25 00:36:34 +02:00
Fix errors and improve Doc (#143)
* Fix link issues and add icons * Improve Doc * fix test * making minor modifications to shuguangs' doc changes --------- Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-261.local> Co-authored-by: Adil Hafeez <adil@katanemo.com>
This commit is contained in:
parent
3ed50e61d2
commit
b30ad791f7
27 changed files with 396 additions and 329 deletions
|
|
@ -1,4 +1,4 @@
|
|||
version: "0.1-beta"
|
||||
version: v0.1
|
||||
|
||||
listener:
|
||||
address: 0.0.0.0 # or 127.0.0.1
|
||||
|
|
@ -8,9 +8,9 @@ listener:
|
|||
common_tls_context: # If you configure port 443, you'll need to update the listener with your TLS certificates
|
||||
tls_certificates:
|
||||
- certificate_chain:
|
||||
filename: "/etc/certs/cert.pem"
|
||||
filename: /etc/certs/cert.pem
|
||||
private_key:
|
||||
filename: "/etc/certs/key.pem"
|
||||
filename: /etc/certs/key.pem
|
||||
|
||||
# Arch creates a round-robin load balancing between different endpoints, managed via the cluster subsystem.
|
||||
endpoints:
|
||||
|
|
@ -18,42 +18,42 @@ endpoints:
|
|||
# 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: "127.0.0.1:80"
|
||||
endpoint: 127.0.0.1:80
|
||||
# max time to wait for a connection to be established
|
||||
connect_timeout: 0.005s
|
||||
|
||||
mistral_local:
|
||||
endpoint: "127.0.0.1:8001"
|
||||
endpoint: 127.0.0.1:8001
|
||||
|
||||
error_target:
|
||||
endpoint: "error_target_1"
|
||||
endpoint: error_target_1
|
||||
|
||||
# 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
|
||||
- name: OpenAI
|
||||
provider: openai
|
||||
access_key: OPENAI_API_KEY
|
||||
model: gpt-4o
|
||||
default: true
|
||||
stream: true
|
||||
rate_limits:
|
||||
selector: #optional headers, to add rate limiting based on http headers like JWT tokens or API keys
|
||||
http_header:
|
||||
name: "Authorization"
|
||||
name: Authorization
|
||||
value: "" # Empty value means each separate value has a separate limit
|
||||
limit:
|
||||
tokens: 100000 # Tokens per unit
|
||||
unit: "minute"
|
||||
unit: minute
|
||||
|
||||
- name: "Mistral8x7b"
|
||||
provider: "mistral"
|
||||
access_key: $MISTRAL_API_KEY
|
||||
model: "mistral-8x7b"
|
||||
- name: Mistral8x7b
|
||||
provider: mistral
|
||||
access_key: MISTRAL_API_KEY
|
||||
model: mistral-8x7b
|
||||
|
||||
- name: "MistralLocal7b"
|
||||
provider: "local"
|
||||
model: "mistral-7b-instruct"
|
||||
endpoint: "mistral_local"
|
||||
- name: MistralLocal7b
|
||||
provider: local
|
||||
model: mistral-7b-instruct
|
||||
endpoint: mistral_local
|
||||
|
||||
# provides a way to override default settings for the arch system
|
||||
overrides:
|
||||
|
|
@ -62,44 +62,41 @@ overrides:
|
|||
prompt_target_intent_matching_threshold: 0.60
|
||||
|
||||
# default system prompt used by all prompt targets
|
||||
system_prompt: |
|
||||
You are a network assistant that just offers facts; not advice on manufacturers or purchasing decisions.
|
||||
system_prompt: You are a network assistant that just offers facts; not advice on manufacturers or purchasing decisions.
|
||||
|
||||
prompt_guards:
|
||||
input_guards:
|
||||
jailbreak:
|
||||
on_exception:
|
||||
message: "Looks like you're curious about my abilities, but I can only provide assistance within my programmed parameters."
|
||||
message: Looks like you're curious about my abilities, but I can only provide assistance within my programmed parameters.
|
||||
|
||||
prompt_targets:
|
||||
- name: "reboot_network_device"
|
||||
description: "Helps network operators perform device operations like rebooting a device."
|
||||
endpoint:
|
||||
name: app_server
|
||||
path: "/agent/action"
|
||||
parameters:
|
||||
- name: "device_id"
|
||||
# additional type options include: int | float | bool | string | list | dict
|
||||
type: "string"
|
||||
description: "Identifier of the network device to reboot."
|
||||
required: true
|
||||
- name: "confirmation"
|
||||
type: "string"
|
||||
description: "Confirmation flag to proceed with reboot."
|
||||
default: "no"
|
||||
enum: [yes, no]
|
||||
|
||||
- name: "information_extraction"
|
||||
- name: information_extraction
|
||||
default: true
|
||||
description: "This prompt handles all scenarios that are question and answer in nature. Like summarization, information extraction, etc."
|
||||
description: handel all scenarios that are question and answer in nature. Like summarization, information extraction, etc.
|
||||
endpoint:
|
||||
name: app_server
|
||||
path: "/agent/summary"
|
||||
path: /agent/summary
|
||||
# Arch uses the default LLM and treats the response from the endpoint as the prompt to send to the LLM
|
||||
auto_llm_dispatch_on_response: true
|
||||
# override system prompt for this prompt target
|
||||
system_prompt: |
|
||||
You are a helpful information extraction assistant. Use the information that is provided to you.
|
||||
system_prompt: You are a helpful information extraction assistant. Use the information that is provided to you.
|
||||
|
||||
- name: reboot_network_device
|
||||
description: Reboot a specific network device
|
||||
endpoint:
|
||||
name: app_server
|
||||
path: /agent/action
|
||||
parameters:
|
||||
- name: device_id
|
||||
type: str
|
||||
description: Identifier of the network device to reboot.
|
||||
required: true
|
||||
- name: confirmation
|
||||
type: bool
|
||||
description: Confirmation flag to proceed with reboot.
|
||||
default: false
|
||||
enum: [true, false]
|
||||
|
||||
error_target:
|
||||
endpoint:
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue