feat(wrappers): add decoration wrapper

[Dam-Buty]

To test this PR :

• check it out locally
• run the Literal Api on this branch : damien/eng-1724-integrations-change-how-we-handle-metadatatags
• unskip all sections marked with "Skip for the CI"
• run the tests with a .env containing an OPENAI_API_KEY.

Changes

• API : add possibility to attach a generation to an existing step (unused in the SDK but exposed to users)

await literalClient.api.createGeneration(generation, stepId)

• OpenAI :
  • fix option to add metadata/tags at the call level
  • add option to specify a Step ID at the call level
  • fix an issue when the same OpenAI client is instrumented more than once (mostly useful for the tests)

const openai_ = new OpenAI();

const openai = client.instrumentation.openai({
  // the initial client needs to be passed when instrumenting
  client: openai_
});

await openai.chat.completions.create(
  {
    model: 'gpt-3.5-turbo',
    messages: [
      { role: 'system', content: 'You are a helpful assistant.' },
      { role: 'user', content: 'What is the capital of Canada?' }
    ]
  },
  {
    literalaiTags: ['tag3', 'tag4'],
    literalaiMetadata: { otherKey: 'otherValue' },
    // You can also specify a Step ID at the call level
    // When this generation is logged, it will be created with the given Step ID
    literalaiStepId
  }
);

• Langchain
  • add an option to specify a Step ID in a call's metadata
  • add tags/metadata from LangChain to Literal AI generations

const literalaiStepId = uuidv4();

await model.invoke('Hello, how are you?', {
  callbacks: [cb],
  metadata: {
    key: 'value',
    // use literalaiStepId in the metadata to specify a Step ID
    literalaiStepId,
  },
  tags: ['tag1', 'tag2'],
});

• Vercel AI SDK : add option to add tags, metadata and a step ID at the call level

const { text } = await generateText({
  model: openai('gpt-3.5-turbo'),
  prompt: question,
  literalaiStepId,
  literalaiTags: ['tag1', 'tag2'],
  literalaiMetadata: { otherKey: 'otherValue' }
});

• Decorate wrapper : this wrapper allows you to store tags, metadata and a step ID inside the context
  • Threads, steps and generations logged inside the context will inherit the tags & metadata
  • The first generation/step created inside the context will inherit the step ID

await client.decorate({ metadata, tags, stepId }).wrap(async () => {
  // This generation will be logged with the provided stepId, metadata and tags
  const completion = await openai.chat.completions.create({
    model: 'gpt-4',
    messages: [{ role: 'user', content: 'Say hello !' }]
  });

  // Because step IDs are unique, this call will revert to the default behaviour of
  // assigning a random UUID to the generation when it is logged.
  const completion = await openai.chat.completions.create({
    model: 'gpt-4',
    messages: [{ role: 'user', content: 'Say hello !' }]
  });
})

[willydouhard]

this looks like a test file?

[clementsirieix]

Done
Moved to an example folder

[willydouhard]

this should be a peer dependency

[clementsirieix]

Done

[willydouhard]

this looks like a test file

[clementsirieix]

Done

[willydouhard]

one log should suffice

[clementsirieix]

Done

[willydouhard]

related to the cache PR but I think we should get rid of it

[clementsirieix]

Done