local-llm-server/config/config.yml.sample

## Important stuff

# The base URL of your backend API
backend_url: http://x.x.x.x:5000

# Mode to run the proxy in
mode: oobabooga

# How many concurrent generation requests will be processed at the same time.
# Oobabooga only supports one. If you're using Oobabooga, you MUST set this to 1
# or else your estimated wait time will be incorrect.
concurrent_gens: 1

# The configured token limit of your backend.
# This number is shown to clients and on the home page. (may be important later)
token_limit: 7777

# How many requests a single IP is allowed to put in the queue.
# If an IP tries to put more than this their request will be rejected
# until the other(s) are completed.
ip_in_queue_max: 1

llm_middleware_name: Local LLM Proxy

## Optional

# Log request and response content.
log_prompts: false

# Python request has issues with self-signed certs.
verify_ssl: false

# Reject all requests if they aren't authenticated with a token.
auth_required: false

# JS tracking code to add to the home page.
#analytics_tracking_code: |
#  alert("hello");

# HTML to add under the "Estimated Wait Time" line.
#info_html: |
#  <a href="https://chub-archive.evulid.cc/#/proxy-stats.html?proxy=proxy_chub_archive_evulid">Historical Stats</a>

## STATS ##

# Display the total_proompts item on the stats screen.
show_num_prompts: true

# Display the uptime item on the stats screen.
show_uptime: true

# Load the number of prompts from the database to display on the stats page.
load_num_prompts: true

# Path that is shown to users for them to connect to
frontend_api_client: /api

# Relative paths are mapped to the directory of the server
database_path: ./proxy-server.db

average_generation_time_mode: database