[MLOB-1009] Auto-Instrument LLM Observability

[sabrenner]

What does this PR do?

Adds auto-instrumentation to the serverless layer for LLM Observability. Now, in order to enable LLM Observability for auto-instrumented integrations (OpenAI, LangChain, Bedrock, and Anthropic), set DD_LLMOBS_ENABLED=1, along with:

DD_LLMOBS_ML_APP=<YOUR_ML_APP> DD_API_KEY=<YOUR_DATADOG_API_KEY> DD_SITE=<YOUR_DATADOG_SITE> 

LLM Observability documentation is available for full instrumentation instructions.

Motivation

Enable easy onboarding and auto-instrumentation experience with LLM Observability in a serverless environment.

Testing Guidelines

Built the layer and tested against a lambda handler. Verified that

1. LLM traces were submitted per invocation of the function
2. APM traces were still being sent as well

Types of Changes

• Bug fix
• New feature
• Breaking change
• Misc (docs, refactoring, dependency upgrade, etc.)

Check all that apply

• This PR's description is comprehensive
• This PR contains breaking changes that are documented in the description
• This PR introduces new APIs or parameters that are documented and unlikely to change in the foreseeable future
• This PR impacts documentation, and it has been updated (or a ticket has been logged)
• This PR's changes are covered by the automated tests
• This PR collects user input/sensitive content into Datadog
• This PR passes the integration tests (ask a Datadog member to run the tests)

[purple4reina]

Move location of flush call

[purple4reina]

lgtm!