docs(readme): Move 'messages << message' outside of loop to prevent duplicatentries

[taro1025]

Issue

When executing the provided code, the following error is encountered:

Error: {"message"=>"An assistant message with 'tool_calls' must be followed by tool messages responding to each 'tool_call_id'. The following tool_call_ids did not have response messages: call_EiPgaP98DOD7sgXMXgVNITDa", "type"=>"invalid_request_error", "param"=>"messages.[3].role", "code"=>nil}

This error occurs because, when handling multiple tool_calls in the message["tool_calls"].each loop, the same message is added to the messages array for every iteration of the loop. This results in duplicate entries for the assistant's message, causing the OpenAI API to fail to correctly process subsequent tool responses.

Reproduction Steps

Ask about the weather in two different locations (e.g., San Francisco and Japan) in the same request. This ensures that the assistant generates multiple tool_calls.

Execute the following Ruby code:

require 'openai'

client = OpenAI::Client.new(access_token: ENV["OPENAI_ACCESS_TOKEN"])

def get_current_weather(location:, unit: "fahrenheit")
  # Here you could use a weather api to fetch the weather.
  "The weather in #{location} is nice 🌞 #{unit}"
end

messages = [
  {
    "role": "user",
    "content": "What is the weather like in San Francisco and Japan?",
  },
]

response =
  client.chat(
    parameters: {
      model: "gpt-4o",
      messages: messages,  # Defined above because we'll use it again
      tools: [
        {
          type: "function",
          function: {
            name: "get_current_weather",
            description: "Get the current weather in a given location",
            parameters: {  # Format: https://json-schema.org/understanding-json-schema
                           type: :object,
                           properties: {
                             location: {
                               type: :string,
                               description: "The city and state, e.g. San Francisco, CA",
                             },
                             unit: {
                               type: "string",
                               enum: %w[celsius fahrenheit],
                             },
                           },
                           required: ["location"],
            },
          },
        }
      ],
      # Optional, defaults to "auto"
      # Can also put "none" or specific functions, see docs
      tool_choice: "required"
    },
    )

message = response.dig("choices", 0, "message")

if message["role"] == "assistant" && message["tool_calls"]
  message["tool_calls"].each do |tool_call|
    tool_call_id = tool_call.dig("id")
    function_name = tool_call.dig("function", "name")
    function_args = JSON.parse(
      tool_call.dig("function", "arguments"),
      { symbolize_names: true },
      )
    function_response =
      case function_name
      when "get_current_weather"
        get_current_weather(**function_args)  # => "The weather is nice 🌞"
      else
        # decide how to handle
      end

    # For a subsequent message with the role "tool", OpenAI requires the preceding message to have a tool_calls argument.
    messages << message

    messages << {
      tool_call_id: tool_call_id,
      role: "tool",
      name: function_name,
      content: function_response
    }  # Extend the conversation with the results of the functions
  end

  second_response = client.chat(
    parameters: {
      model: "gpt-4o",
      messages: messages
    }
  )

  puts second_response.dig("choices", 0, "message", "content")
  if second_response.dig("error")
    puts "Error: #{second_response.dig("error")}"
  end
end

All Submissions:

• Have you followed the guidelines in our Contributing document?
• Have you checked to ensure there aren't other open Pull Requests for the same update/change?
• Have you added an explanation of what your changes do and why you'd like us to include them?

[taro1025]

@alexrudall
When you have a moment, I’d appreciate it if you could review my PR.

Thank you!