Set up AI Proxy with Cohere

古いプラグインバージョンのドキュメントを閲覧しています。

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

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

Cohere 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

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

Set up route and plugin

Kong Admin API

YAML

Create the route:

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

Enable and configure the AI Proxy plugin for Cohere, replacing the <cohere_key> with your own API key:

curl -X POST http://localhost:8001/routes/cohere-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 <cohere_key>" \
  --data "config.model.provider=cohere" \
  --data "config.model.name=command" \
  --data "config.model.options.max_tokens=512" \
  --data "config.model.options.temperature=1.0"

name: cohere-chat
paths:
  - "~/cohere-chat$"
methods:
  - POST
plugins:
  - name: ai-proxy
    config:
      route_type: "llm/v1/chat"
      auth:
        header_name: "Authorization"
        header_value: "Bearer <cohere_key>"  # add your own Cohere API key
      model:
        provider: "cohere"
        name: "command"
        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/cohere-chat \
  -H 'Content-Type: application/json' \
  --data-raw '{ "messages": [ { "role": "system", "content": "You are a mathematician" }, { "role": "user", "content": "What is 1+1?"} ] }'

前へ Set up AI Proxy with Bedrock

次へ Set up AI Proxy with Gemini