通过 claw 免费额度来部署酒馆，下面教程开始。
首先获取 5$ 条件 ：
- 首次注册赠送
5$：有效期一个月 - 每个月赠送
5$：注册账号后一个月内绑定 GitHub 账户，同时要求绑定的 GitHub 账户注册时间超过 180 天
SillyTavern部署：
点击 App Launchpad ，点击 Create App
容器参数如下：
Application Nmae：sillytavern
Image Name：ghcr.io/sillytavern/sillytavern:latest
Usage：Fixed，0.5C512M
Container Port：8000 Enable Internet Access：开启
Environment Variables：
NODE_ENV=production
FORCE_COLOR=1
Configmaps：
File Name：/home/node/app/config/config.yamlFile content：
# -- DATA CONFIGURATION --
# Root directory for user data storage
dataRoot: ./data
# -- SERVER CONFIGURATION --
# Listen for incoming connections
listen: true
# Listen on a specific address, supports IPv4 and IPv6
listenAddress:
ipv4: 0.0.0.0
ipv6: '[::]'
# Enables IPv6 and/or IPv4 protocols. Need to have at least one enabled!
# - Use option "auto" to automatically detect support
# - Use true or false (no qoutes) to enable or disable each protocol
protocol:
ipv4: true
ipv6: false
# Prefers IPv6 for DNS. Enable this on ISPs that don't have issues with IPv6
dnsPreferIPv6: false
# The hostname that autorun opens.
# - Use "auto" to let the server decide
# - Use options like 'localhost', 'st.example.com'
autorunHostname: "auto"
# Server port
port: 8000
# Overrides the port for autorun in browser.
# - Use -1 to use the server port.
# - Specify a port to override the default.
autorunPortOverride: -1
# -- SSL options --
ssl:
enabled: false
certPath: "./certs/cert.pem"
keyPath: "./certs/privkey.pem"
# -- SECURITY CONFIGURATION --
# Toggle whitelist mode
whitelistMode: false
# Whitelist will also verify IP in X-Forwarded-For / X-Real-IP headers
enableForwardedWhitelist: true
# Whitelist of allowed IP addresses
whitelist:
- ::1
- 127.0.0.1
# Automatically whitelist Docker host and gateway IPs
whitelistDockerHosts: true
# Toggle basic authentication for endpoints
basicAuthMode: true
# Basic authentication credentials
basicAuthUser:
username: "admin"
password: "123456"
# Enables CORS proxy middleware
enableCorsProxy: false
# -- REQUEST PROXY CONFIGURATION --
requestProxy:
# If a proxy is enabled, all outgoing HTTP/HTTPS requests will be routed through it.
enabled: false
# Proxy URL. Possible protocols: http, https, socks, socks5, socks4, pac
url: "socks5://username:[email protected]:1080"
# Proxy bypass list. Requests to these hosts won't be routed through the proxy.
bypass:
- localhost
- 127.0.0.1
# Enable multi-user mode
enableUserAccounts: false
# Enable discreet login mode: hides user list on the login screen
enableDiscreetLogin: false
# Enable's authlia based auto login. Only enable this if you
# have setup and installed Authelia as a middle-ware on your
# reverse proxy
# https://www.authelia.com/
# This will use auto login to an account with the same username
# as that used for authlia. (Ensure the username in authlia
# is an exact match with that in sillytavern)
autheliaAuth: false
# If `basicAuthMode` and this are enabled then
# the username and passwords for basic auth are the same as those
# for the individual accounts
perUserBasicAuth: false
# User session timeout *in seconds* (defaults to 24 hours).
## Set to a positive number to expire session after a certain time of inactivity
## Set to 0 to expire session when the browser is closed
## Set to a negative number to disable session expiration
sessionTimeout: -1
# Disable CSRF protection - NOT RECOMMENDED
disableCsrfProtection: false
# Disable startup security checks - NOT RECOMMENDED
securityOverride: false
# -- LOGGING CONFIGURATION --
logging:
# Enable access logging to access.log file
# Records new connections with timestamp, IP address and user agent
enableAccessLog: true
# Minimum log level to display in the terminal (DEBUG = 0, INFO = 1, WARN = 2, ERROR = 3)
minLogLevel: 0
# -- RATE LIMITING CONFIGURATION --
rateLimiting:
# Use X-Real-IP header instead of socket IP for rate limiting
# Only enable this if you are using a properly configured reverse proxy (like Nginx/traefik/Caddy)
preferRealIpHeader: false
# -- ADVANCED CONFIGURATION --
# Open the browser automatically
autorun: true
# Avoids using 'localhost' for autorun in auto mode.
# use if you don't have 'localhost' in your hosts file
avoidLocalhost: false
## BACKUP CONFIGURATION
backups:
# Common settings for all backup types
common:
# Number of backups to keep for each chat and settings file
numberOfBackups: 50
chat:
# Enable automatic chat backups
enabled: true
# Maximum number of chat backups to keep per user (starting from the most recent). Set to -1 to keep all backups.
maxTotalBackups: -1
# Interval in milliseconds to throttle chat backups per user
throttleInterval: 10000
# THUMBNAILING CONFIGURATION
thumbnails:
# Enable thumbnail generation
enabled: true
# Image format of avatar thumbnails:
# * "jpg": best compression with adjustable quality, no transparency
# * "png": preserves transparency but increases filesize by about 100%
# Changing this only affects new thumbnails. To recreate the old ones, clear out /thumbnails folder in your user data.
format: "jpg"
# JPG thumbnail quality (0-100)
quality: 95
# Maximum thumbnail dimensions per type [width, height]
dimensions: { 'bg': [160, 90], 'avatar': [96, 144] }
# PERFORMANCE-RELATED CONFIGURATION
performance:
# Enables lazy loading of character cards. Improves performances with large card libraries.
# May have compatibility issues with some extensions.
lazyLoadCharacters: false
# The maximum amount of memory that parsed character cards can use. Set to 0 to disable memory caching.
memoryCacheCapacity: '100mb'
# Allow secret keys exposure via API
allowKeysExposure: false
# Skip new default content checks
skipContentCheck: false
# Allowed hosts for card downloads
whitelistImportDomains:
- localhost
- cdn.discordapp.com
- files.catbox.moe
- raw.githubusercontent.com
# API request overrides (for KoboldAI and Text Completion APIs)
## Note: host includes the port number if it's not the default (80 or 443)
## Format is an array of objects:
## - hosts:
## - example.com
## headers:
## Content-Type: application/json
## - 127.0.0.1:5001
## headers:
## User-Agent: "Googlebot/2.1 (+http://www.google.com/bot.html)"
requestOverrides: []
# EXTENSIONS CONFIGURATION
extensions:
# Enable UI extensions
enabled: true
# Automatically update extensions when a release version changes
autoUpdate: true
models:
# Enables automatic model download from HuggingFace
autoDownload: true
# Additional models for extensions. Expects model IDs from HuggingFace model hub in ONNX format
classification: Cohee/distilbert-base-uncased-go-emotions-onnx
captioning: Xenova/vit-gpt2-image-captioning
embedding: Cohee/jina-embeddings-v2-base-en
speechToText: Xenova/whisper-small
textToSpeech: Xenova/speecht5_tts
# Additional model tokenizers can be downloaded on demand.
# Disabling will fallback to another locally available tokenizer.
enableDownloadableTokenizers: true
# -- OPENAI CONFIGURATION --
# A placeholder message to use in strict prompt post-processing mode when the prompt doesn't start with a user message
promptPlaceholder: "[Start a new chat]"
openai:
# Will send a random user ID to OpenAI completion API
randomizeUserId: false
# If not empty, will add this as a system message to the start of every caption completion prompt
# Example: "Perform the instructions to the best of your ability.\n" (for LLaVA)
# Not used in image inlining mode
captionSystemPrompt: ""
# -- DEEPL TRANSLATION CONFIGURATION --
deepl:
# Available options: default, more, less, prefer_more, prefer_less
formality: default
# -- MISTRAL API CONFIGURATION --
mistral:
# Enables prefilling of the reply with the last assistant message in the prompt
# CAUTION: The prefix is echoed into the completion. You may want to use regex to trim it out.
enablePrefix: false
# -- OLLAMA API CONFIGURATION --
ollama:
# Controls how long the model will stay loaded into memory following the request
# * -1: Keep the model loaded indefinitely
# * 0: Unload the model immediately after the request
# * N (any positive number): Keep the model loaded for N seconds after the request.
keepAlive: -1
# Controls the "num_batch" (batch size) parameter of the generation request
# * -1: Use the default value of the model
# * N (positive number): Use the specified value. Must be a power of 2, e.g. 128, 256, 512, etc.
batchSize: -1
# -- ANTHROPIC CLAUDE API CONFIGURATION --
claude:
# Enables caching of the system prompt (if supported).
# https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching
# -- IMPORTANT! --
# Use only when the prompt before the chat history is static and doesn't change between requests
# (e.g {{random}} macro or lorebooks not as in-chat injections).
# Otherwise, you'll just waste money on cache misses.
enableSystemPromptCache: false
# Enables caching of the message history at depth (if supported).
# https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching
# -- IMPORTANT! --
# Use with caution. Behavior may be unpredictable and no guarantees can or will be made.
# Set to an integer to specify the desired depth. 0 (which does NOT include the prefill)
# should be ideal for most use cases.
# Any value other than a non-negative integer will be ignored and caching at depth will not be enabled.
cachingAtDepth: -1
# -- SERVER PLUGIN CONFIGURATION --
enableServerPlugins: false
# Attempt to automatically update server plugins on startup
enableServerPluginsAutoUpdate: true
Local Storage：
Capacity：2Mount Path：/home/node/app/data
部署样例 ：
确认无误，点击
Deploy Application
之后等待启动就可以了
自定义域可以ping通, 但是还是访问不了
我的问题, claw加上自定义域后我没有点更新
感谢佬友的解答