feat: Added instrumentation for openai chat completion creation

[bizob2828]

Description

This PR adds instrumentation for chat completion create. It adds the relevant span and the associated LLM events: n chat completion messages, and 1 chat completion summary.

Note: Error handling has been deferred to #1845 as well as stream based chat completions(#1844).

Aside from instrumentation openai.Chat.Completions.prototype.create, I had to wrap openai.prototype.makeRequest to decorate the active segment with request headers and api key to be used when creating the LLM events. As you can see they are cleaned up before returning the result to the user. I also had to enhance shim to pass in the active segment as the last arg, this is because once a promise resolves the active segment is its parent. We need the active segment that was being recorded to decorate the LLM events.

How to Test

npm run versioned:internal openai

node test/unit/instrumentation/openai.test.js

If you want to use a sample app you can use this as the basis of it:

const newrelic = require('newrelic')
const OpenAI = require('openai')
const openai = new OpenAI({
  apiKey: process.env.OPENAI_API_KEY
})

async function main() {
  newrelic.startBackgroundTransaction('open ai tx', async () => {
    const chatCompletion = await openai.chat.completions.create({
      max_tokens: 20,
      temperature: 0.5,
      messages: [{ role: 'user', content: process.env.MSG || 'Say this is a test'}],
      model: 'gpt-4',
    });
    newrelic.shutdown({ collectPendingData: true }, () => {
      console.log('done')
      process.exit(0)
    })
  })
}

main()

Related Issues

Closes #1841

[codecov]

Codecov Report

Attention: 3 lines in your changes are missing coverage. Please review.

Comparison is base (20e7f1d) 96.85% compared to head (9218fef) 96.85%.

Files	Patch %	Lines
lib/instrumentation/openai.js	97.95%	3 Missing ⚠️

Additional details and impacted files

@@           Coverage Diff            @@
##             main    #1862    +/-   ##
========================================
  Coverage   96.85%   96.85%            
========================================
  Files         206      208     +2     
  Lines       39252    39422   +170     
========================================
+ Hits        38017    38184   +167     
- Misses       1235     1238     +3     

Flag	Coverage Δ
integration-tests-16.x	78.95% <66.66%> (+<0.01%)	⬆️
integration-tests-18.x	79.22% <66.66%> (+<0.01%)	⬆️
integration-tests-20.x	79.23% <66.66%> (+<0.01%)	⬆️
unit-tests-16.x	91.25% <56.86%> (-0.14%)	⬇️
unit-tests-18.x	91.23% <56.86%> (-0.14%)	⬇️
unit-tests-20.x	91.23% <56.86%> (-0.14%)	⬇️
versioned-tests-16.x	73.30% <92.81%> (+0.15%)	⬆️
versioned-tests-18.x	73.30% <92.81%> (+0.15%)	⬆️
versioned-tests-20.x	73.31% <92.81%> (+0.15%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[jsumners-nr]

Looks good to me.