Set up AI Proxy with OpenAI

You are browsing unreleased documentation.

This guide walks you through setting up the AI Proxy plugin with OpenAI.

For all providers, the Kong AI Proxy plugin attaches to route entities.

It can be installed into one route per operation, for example:

• OpenAI chat route
• Cohere chat route
• Cohere completions route

Each of these AI-enabled routes must point to a null service. This service doesn’t need to map to any real upstream URL, it can point somewhere empty (for example, http://localhost:32000), because the AI Proxy plugin overwrites the upstream URL. This requirement will be removed in a later Kong revision.

Prerequisites

• OpenAI account and subscription
• You need a service to contain the route for the LLM provider. Create a service first:

  curl -X POST http://localhost:8001/services \
    --data "name=ai-proxy" \
    --data "url=http://localhost:32000"
  

  Remember that the upstream URL can point anywhere empty, as it won’t be used by the plugin.

Provider configuration

Set up route and plugin

After creating an OpenAI account, and purchasing a subscription, you can then create an AI Proxy route and plugin configuration.

curl -X POST http://localhost:8001/services/ai-proxy/routes \
  --data "name=openai-chat" \
  --data "paths[]=~/openai-chat$"

curl -X POST http://localhost:8001/routes/openai-chat/plugins \
  --data "name=ai-proxy" \
  --data "config.route_type=llm/v1/chat" \
  --data "config.auth.header_name=Authorization" \
  --data "config.auth.header_value=Bearer <openai_key>" \
  --data "config.model.provider=openai" \
  --data "config.model.name=gpt-4" \
  --data "config.model.options.max_tokens=512" \
  --data "config.model.options.temperature=1.0"

name: openai-chat
paths:
  - "~/openai-chat$"
methods:
  - POST
plugins:
  - name: ai-proxy
    config:
      route_type: "llm/v1/chat"
      auth:
        header_name: "Authorization"
        header_value: "Bearer <openai_key>"  # add your own OpenAI API key
      model:
        provider: "openai"
        name: "gpt-4"
        options:
          max_tokens: 512
          temperature: 1.0

Test the configuration

Make an llm/v1/chat type request to test your new endpoint:

curl -X POST http://localhost:8000/openai-chat \
  -H 'Content-Type: application/json' \
  --data-raw '{ "messages": [ { "role": "system", "content": "You are a mathematician" }, { "role": "user", "content": "What is 1+1?"} ] }'