[MLOB-1562] feat(llmobs): add openai integration

[sabrenner]

What does this PR do?

Adds an additional OpenAI plugin, which is an LLM Observability OpenAI plugin. Also establishes the groundwork for the concept of a "base" LLM Obs plugin, which future LLMObs plugins will extend from.

Note: Most LOC are from moving the OpenAI plugin to it's own tracing file, and then resolving it and the LLMObs OpenAI plugin into a single composite plugin. I will highlight on "new" tracing plugin where I made some changes.

Note: I've put the llmobs plugin before the tracing plugin, since its asyncEnd needs to run before the tracing plugin's asyncEnd, because we process LLMObs spans when an APM span finishes, so if the tracing plugin's asyncEnd runs first, then we won't be able to add the proper annotations to our LLMObs span event.

LLM Observability Trace

Motivation

Adding auto-instrumentation for OpenAI for LLM Observability.

[github-actions]

Overall package size

Self size: 7.86 MB
Deduped: 64.88 MB
No deduping: 65.22 MB

Dependency sizes

| name | version | self size | total size | |------|---------|-----------|------------| | @datadog/native-appsec | 8.2.1 | 19.18 MB | 19.19 MB | | @datadog/native-iast-taint-tracking | 3.2.0 | 13.9 MB | 13.91 MB | | @datadog/pprof | 5.4.1 | 9.76 MB | 10.13 MB | | protobufjs | 7.2.5 | 2.77 MB | 5.16 MB | | @datadog/native-iast-rewriter | 2.5.0 | 2.51 MB | 2.65 MB | | @opentelemetry/core | 1.14.0 | 872.87 kB | 1.47 MB | | @datadog/native-metrics | 3.0.1 | 1.06 MB | 1.46 MB | | @opentelemetry/api | 1.8.0 | 1.21 MB | 1.21 MB | | import-in-the-middle | 1.11.2 | 112.74 kB | 826.22 kB | | msgpack-lite | 0.1.26 | 201.16 kB | 281.59 kB | | opentracing | 0.14.7 | 194.81 kB | 194.81 kB | | lru-cache | 7.18.3 | 133.92 kB | 133.92 kB | | pprof-format | 2.1.0 | 111.69 kB | 111.69 kB | | @datadog/sketches-js | 2.1.0 | 109.9 kB | 109.9 kB | | semver | 7.6.3 | 95.82 kB | 95.82 kB | | lodash.sortby | 4.7.0 | 75.76 kB | 75.76 kB | | ignore | 5.3.1 | 51.46 kB | 51.46 kB | | int64-buffer | 0.1.10 | 49.18 kB | 49.18 kB | | shell-quote | 1.8.1 | 44.96 kB | 44.96 kB | | istanbul-lib-coverage | 3.2.0 | 29.34 kB | 29.34 kB | | rfdc | 1.3.1 | 25.21 kB | 25.21 kB | | tlhunter-sorted-set | 0.1.0 | 24.94 kB | 24.94 kB | | limiter | 1.1.5 | 23.17 kB | 23.17 kB | | dc-polyfill | 0.1.4 | 23.1 kB | 23.1 kB | | retry | 0.13.1 | 18.85 kB | 18.85 kB | | jest-docblock | 29.7.0 | 8.99 kB | 12.76 kB | | crypto-randomuuid | 1.0.0 | 11.18 kB | 11.18 kB | | koalas | 1.0.2 | 6.47 kB | 6.47 kB | | path-to-regexp | 0.1.10 | 6.38 kB | 6.38 kB | | module-details-from-path | 1.0.3 | 4.47 kB | 4.47 kB |

_{🤖 This report was automatically generated by heaviest-objects-in-the-universe}

[pr-commenter]

Benchmarks

Benchmark execution time: 2024-10-30 17:06:47

Comparing candidate commit fa050e8 in PR branch sabrenner/openai-llmobs with baseline commit 1c0958e in branch master.

Found 0 performance improvements and 0 performance regressions! Performance is the same for 258 metrics, 8 unstable metrics.

[tlhunter]

Does OpenAI still use Open API to build it's API? 😆

[sabrenner]

yeah they do 😆

[Yun-Kim]

LGTM for team llm obs, no blocking comments!