apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-04-25 08:46:24 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Adil/fix salman docs (#75)

Browse source 
* added the first set of docs for our technical docs

* more docuemtnation changes

* added support for prompt processing and updated life of a request

* updated docs to including getting help sections and updated life of a request

* committing local changes for getting started guide, sample applications, and full reference spec for prompt-config

* updated configuration reference, added sample app skeleton, updated favico

* fixed the configuration refernce file, and made minor changes to the intent detection. commit v1 for now

* Updated docs with use cases and example code, updated what is arch, and made minor changes throughout

* fixed imaged and minor doc fixes

* add sphinx_book_theme

* updated README, and make some minor fixes to documetnation

* fixed README.md

* fixed image width

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-261.local>
Co-authored-by: Adil Hafeez <adil@katanemo.com>
This commit is contained in:
Salman Paracha 2024-09-24 13:54:17 -07:00 • committed by GitHub
parent 2d31aeaa36
commit 13dff3089d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
33 changed files with 931 additions and 287 deletions
Download patch file Download diff file Expand all files Collapse all files

16
docs/source/_config/prompt-config-full-reference.yml
View file

@ -2,7 +2,7 @@ version: "0.1-beta"
listener:
address: 0.0.0.0 # or 127.0.0.1
port_value: 8080
port_value: 8080
messages: "hugging-face-messages-json" # Defines how Arch should parse the content from application/json or text/pain Content-type in the http request
common_tls_context: # If you configure port 443, you'll need to update the listener with your TLS certificates
tls_certificates:
@ -16,18 +16,17 @@ system_prompts:
content: |
You are a network assistant that just offers facts; not advice on manufacturers or purchasing decisions.
#Centralized way to manage LLM providers that the application has access to. Manage keys retry logic, failover, and limits in a central way
llm_providers:
llm_providers: #Centralized way to manage LLMs, manage keys, retry logic, failover and limits in a central way
- name: "OpenAI"
access_key: $OPENAI_API_KEY
model: "gpt-40"
model: gpt-4o
default: true
stream: true
rate_limit:
selector: #optional headers, to add rate limiting based on http headers like JWT tokens or API keys
http-header:
name: "Authorization"
value: "" # Empty value means each separate value has a separate limit
value: "" # Empty value means each separate value has a separate limit
limit:
tokens: 100000 # Tokens per unit
unit: "minute"
@ -44,7 +43,6 @@ prompt_guards:
- name: "jailbreak"
on_exception:
forward_to_error_target: true
# Additional guard configurations can be added here
- name: "toxicity"
on_exception:
message: "Looks like you're curious about my abilities, but I can only provide assistance within my programmed parameters."
@ -74,5 +72,7 @@ error_target:
name: "error_handler"
path: "/errors"
intent-detection-threshold-override: 0.60 # By default Arch uses an NLI + embedding approach to match an incomming prompt to a prompt target.
# The intent matching threshold is kept at 0.80, you can overide this behavior if you would like
tracing: 100 #sampling rate. Note by default Arch works on OpenTelemetry compatible tracing.
intent-detection-threshold-override: 0.60 # By default Arch uses an NLI + embedding approach to match an incomming prompt to a prompt target.
# The intent matching threshold is kept at 0.80, you can overide this behavior if you would like