MockAI service

This is a mock service for multiple AI services.

Documentation

Documentation

OpenAI API

Supported endpoints:

• /openai/v1/chat/completions (streaming supported)
• /openai/v1/images/generations
• /openai/v1/models
• /openai/v1/models/:id
• /anthropic/v1/messages (streaming supported)

Echo mode

If you set answer in the request body, the service will echo the answer back.

Extra parameters

• request_delay: Delay the response time.
• answer: Echo the answer back.

Example code

OpenAI

cd examples/openai
pnpm install
pnpm run build
pnpm run start

Anthropic

cd examples/anthropic
pnpm install
pnpm run build
pnpm run start

Deploy

Environment variables

• MAX_COMPLETION_TOKENS: The maximum number of tokens in the response.
• MAXIMUM_REQUEST_DELAY: The maximum request delay.
• RATELIMITING_ENABLED: Whether to enable rate limiting.
• ENV: The environment name.
• DOC_URL: The documentation URL.

npm install -g pnpm

cp wrangler_example.toml wrangler.toml

Customize the wrangler.toml file with your own values.

pnpm install
wrangler login
wrangler deploy -e production