-
Notifications
You must be signed in to change notification settings - Fork 310
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[MLOB-1524] feat(llmobs): Introduce LLM Observability SDK #4742
Conversation
add llmobs config
LLM Observability writers
LLM Observability tagger
…r/llmobs-sdk-release
Overall package sizeSelf size: 7.8 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 | 2.0.0 | 898.77 kB | 1.3 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 |
* span processor * tests * remove agent exporter log and do not stringify tags * remove llmobs from exporter tests * add in default unserializable value * review comments * warning log for metric * todo-ify * remove some duplicate logic * decouple llmobs span processing with a channel * use a static weakmap to store llmobs tags/annotations instead of span tags * do not register span in map if it does not have an llmobs span kind * span is passed on an object from sp publisher * re-clarify TODOs * only send span in publish * log multiple warnings and return conditional undefined * update error logic
BenchmarksBenchmark execution time: 2024-10-29 18:43:40 Comparing candidate commit 845c840 in PR branch Found 0 performance improvements and 0 performance regressions! Performance is the same for 260 metrics, 6 unstable metrics. |
* wip * type definitions * active + try/catch eval metric writer append * test ts * use tagger map and processor as a channel subscriber * change decorate and add in dev changes * try some api changes * add decorate to noop * fix breaking proxy tests * experimental decorators for TS docs * api changes, fix unit + e2e tests * try removing global log mocks * add some util tests * remove logger mocks * add module tests + do not enable when not specified * fix eval metric integration test * wip * memoize getFunctionArguments * move any subscriber and global writer to the module enablement level instead of sdk * should fix TS tests * add ts integration test and fix decorator * devex for ts versions * add noop typescript test * remove startSpan * remove unneeded change * dedup decorator code * Update index.d.ts Co-authored-by: Yun Kim <35776586+Yun-Kim@users.noreply.github.com> * map metrics names * change validKind to validateKind and throw * tagger for metrics follow-up * review feedback * add some tests for not auto-annotating in certain cases --------- Co-authored-by: Yun Kim <35776586+Yun-Kim@users.noreply.github.com>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
reviewed it to the best of my noob js and mlobs ability. Great job Sam 👏 🚢
Let's try to get some tests into the shared testing framework ASAP to assert the similarity with the Python interface!
this._setTag(span, key, data) | ||
} else { | ||
try { | ||
this._setTag(span, key, JSON.stringify(data)) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
lol we definitely gotta make a pitch to APM to better support this in the future
} | ||
|
||
// any public-facing LLMObs APIs using this tagger should not soft fail | ||
// auto-instrumentation should soft fail |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
👍
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## master #4742 +/- ##
==========================================
+ Coverage 68.58% 70.23% +1.65%
==========================================
Files 12 329 +317
Lines 818 14775 +13957
==========================================
+ Hits 561 10377 +9816
- Misses 257 4398 +4141 ☔ View full report in Codecov by Sentry. |
* [MLOB-1540] add llmobs configuration to global tracer config (#4696) add llmobs config * [MLOB-1555] LLM Observability writers (#4699) LLM Observability writers * [MLOB-1556] LLM Observability tagger (#4718) LLM Observability tagger * [MLOB-1560] LLMObs Span Processor (#4738) * span processor * tests * remove agent exporter log and do not stringify tags * remove llmobs from exporter tests * add in default unserializable value * review comments * warning log for metric * todo-ify * remove some duplicate logic * decouple llmobs span processing with a channel * use a static weakmap to store llmobs tags/annotations instead of span tags * do not register span in map if it does not have an llmobs span kind * span is passed on an object from sp publisher * re-clarify TODOs * only send span in publish * log multiple warnings and return conditional undefined * update error logic * [MLOB-1561] LLM Observability SDK API (#4773) * wip * type definitions * active + try/catch eval metric writer append * test ts * use tagger map and processor as a channel subscriber * change decorate and add in dev changes * try some api changes * add decorate to noop * fix breaking proxy tests * experimental decorators for TS docs * api changes, fix unit + e2e tests * try removing global log mocks * add some util tests * remove logger mocks * add module tests + do not enable when not specified * fix eval metric integration test * wip * memoize getFunctionArguments * move any subscriber and global writer to the module enablement level instead of sdk * should fix TS tests * add ts integration test and fix decorator * devex for ts versions * add noop typescript test * remove startSpan * remove unneeded change * dedup decorator code * Update index.d.ts Co-authored-by: Yun Kim <35776586+Yun-Kim@users.noreply.github.com> * map metrics names * change validKind to validateKind and throw * tagger for metrics follow-up * review feedback * add some tests for not auto-annotating in certain cases --------- Co-authored-by: Yun Kim <35776586+Yun-Kim@users.noreply.github.com> * hard fail instead of soft fail, except for `wrap` span name * add ml-observability codeowners * resolve ts test * update auto-annotation check * tagger can soft fail * using custom ASL instance and scope activation * fix test comments and remove * address review comments * remove llmobs.apiKey config, only rely on global * fix evaulations test * make llmobs storage accessible --------- Co-authored-by: Yun Kim <35776586+Yun-Kim@users.noreply.github.com>
* [MLOB-1540] add llmobs configuration to global tracer config (#4696) add llmobs config * [MLOB-1555] LLM Observability writers (#4699) LLM Observability writers * [MLOB-1556] LLM Observability tagger (#4718) LLM Observability tagger * [MLOB-1560] LLMObs Span Processor (#4738) * span processor * tests * remove agent exporter log and do not stringify tags * remove llmobs from exporter tests * add in default unserializable value * review comments * warning log for metric * todo-ify * remove some duplicate logic * decouple llmobs span processing with a channel * use a static weakmap to store llmobs tags/annotations instead of span tags * do not register span in map if it does not have an llmobs span kind * span is passed on an object from sp publisher * re-clarify TODOs * only send span in publish * log multiple warnings and return conditional undefined * update error logic * [MLOB-1561] LLM Observability SDK API (#4773) * wip * type definitions * active + try/catch eval metric writer append * test ts * use tagger map and processor as a channel subscriber * change decorate and add in dev changes * try some api changes * add decorate to noop * fix breaking proxy tests * experimental decorators for TS docs * api changes, fix unit + e2e tests * try removing global log mocks * add some util tests * remove logger mocks * add module tests + do not enable when not specified * fix eval metric integration test * wip * memoize getFunctionArguments * move any subscriber and global writer to the module enablement level instead of sdk * should fix TS tests * add ts integration test and fix decorator * devex for ts versions * add noop typescript test * remove startSpan * remove unneeded change * dedup decorator code * Update index.d.ts Co-authored-by: Yun Kim <35776586+Yun-Kim@users.noreply.github.com> * map metrics names * change validKind to validateKind and throw * tagger for metrics follow-up * review feedback * add some tests for not auto-annotating in certain cases --------- Co-authored-by: Yun Kim <35776586+Yun-Kim@users.noreply.github.com> * hard fail instead of soft fail, except for `wrap` span name * add ml-observability codeowners * resolve ts test * update auto-annotation check * tagger can soft fail * using custom ASL instance and scope activation * fix test comments and remove * address review comments * remove llmobs.apiKey config, only rely on global * fix evaulations test * make llmobs storage accessible --------- Co-authored-by: Yun Kim <35776586+Yun-Kim@users.noreply.github.com>
* [MLOB-1540] add llmobs configuration to global tracer config (#4696) add llmobs config * [MLOB-1555] LLM Observability writers (#4699) LLM Observability writers * [MLOB-1556] LLM Observability tagger (#4718) LLM Observability tagger * [MLOB-1560] LLMObs Span Processor (#4738) * span processor * tests * remove agent exporter log and do not stringify tags * remove llmobs from exporter tests * add in default unserializable value * review comments * warning log for metric * todo-ify * remove some duplicate logic * decouple llmobs span processing with a channel * use a static weakmap to store llmobs tags/annotations instead of span tags * do not register span in map if it does not have an llmobs span kind * span is passed on an object from sp publisher * re-clarify TODOs * only send span in publish * log multiple warnings and return conditional undefined * update error logic * [MLOB-1561] LLM Observability SDK API (#4773) * wip * type definitions * active + try/catch eval metric writer append * test ts * use tagger map and processor as a channel subscriber * change decorate and add in dev changes * try some api changes * add decorate to noop * fix breaking proxy tests * experimental decorators for TS docs * api changes, fix unit + e2e tests * try removing global log mocks * add some util tests * remove logger mocks * add module tests + do not enable when not specified * fix eval metric integration test * wip * memoize getFunctionArguments * move any subscriber and global writer to the module enablement level instead of sdk * should fix TS tests * add ts integration test and fix decorator * devex for ts versions * add noop typescript test * remove startSpan * remove unneeded change * dedup decorator code * Update index.d.ts Co-authored-by: Yun Kim <35776586+Yun-Kim@users.noreply.github.com> * map metrics names * change validKind to validateKind and throw * tagger for metrics follow-up * review feedback * add some tests for not auto-annotating in certain cases --------- Co-authored-by: Yun Kim <35776586+Yun-Kim@users.noreply.github.com> * hard fail instead of soft fail, except for `wrap` span name * add ml-observability codeowners * resolve ts test * update auto-annotation check * tagger can soft fail * using custom ASL instance and scope activation * fix test comments and remove * address review comments * remove llmobs.apiKey config, only rely on global * fix evaulations test * make llmobs storage accessible --------- Co-authored-by: Yun Kim <35776586+Yun-Kim@users.noreply.github.com>
* [MLOB-1540] add llmobs configuration to global tracer config (#4696) add llmobs config * [MLOB-1555] LLM Observability writers (#4699) LLM Observability writers * [MLOB-1556] LLM Observability tagger (#4718) LLM Observability tagger * [MLOB-1560] LLMObs Span Processor (#4738) * span processor * tests * remove agent exporter log and do not stringify tags * remove llmobs from exporter tests * add in default unserializable value * review comments * warning log for metric * todo-ify * remove some duplicate logic * decouple llmobs span processing with a channel * use a static weakmap to store llmobs tags/annotations instead of span tags * do not register span in map if it does not have an llmobs span kind * span is passed on an object from sp publisher * re-clarify TODOs * only send span in publish * log multiple warnings and return conditional undefined * update error logic * [MLOB-1561] LLM Observability SDK API (#4773) * wip * type definitions * active + try/catch eval metric writer append * test ts * use tagger map and processor as a channel subscriber * change decorate and add in dev changes * try some api changes * add decorate to noop * fix breaking proxy tests * experimental decorators for TS docs * api changes, fix unit + e2e tests * try removing global log mocks * add some util tests * remove logger mocks * add module tests + do not enable when not specified * fix eval metric integration test * wip * memoize getFunctionArguments * move any subscriber and global writer to the module enablement level instead of sdk * should fix TS tests * add ts integration test and fix decorator * devex for ts versions * add noop typescript test * remove startSpan * remove unneeded change * dedup decorator code * Update index.d.ts Co-authored-by: Yun Kim <35776586+Yun-Kim@users.noreply.github.com> * map metrics names * change validKind to validateKind and throw * tagger for metrics follow-up * review feedback * add some tests for not auto-annotating in certain cases --------- Co-authored-by: Yun Kim <35776586+Yun-Kim@users.noreply.github.com> * hard fail instead of soft fail, except for `wrap` span name * add ml-observability codeowners * resolve ts test * update auto-annotation check * tagger can soft fail * using custom ASL instance and scope activation * fix test comments and remove * address review comments * remove llmobs.apiKey config, only rely on global * fix evaulations test * make llmobs storage accessible --------- Co-authored-by: Yun Kim <35776586+Yun-Kim@users.noreply.github.com>
* [MLOB-1540] add llmobs configuration to global tracer config (#4696) add llmobs config * [MLOB-1555] LLM Observability writers (#4699) LLM Observability writers * [MLOB-1556] LLM Observability tagger (#4718) LLM Observability tagger * [MLOB-1560] LLMObs Span Processor (#4738) * span processor * tests * remove agent exporter log and do not stringify tags * remove llmobs from exporter tests * add in default unserializable value * review comments * warning log for metric * todo-ify * remove some duplicate logic * decouple llmobs span processing with a channel * use a static weakmap to store llmobs tags/annotations instead of span tags * do not register span in map if it does not have an llmobs span kind * span is passed on an object from sp publisher * re-clarify TODOs * only send span in publish * log multiple warnings and return conditional undefined * update error logic * [MLOB-1561] LLM Observability SDK API (#4773) * wip * type definitions * active + try/catch eval metric writer append * test ts * use tagger map and processor as a channel subscriber * change decorate and add in dev changes * try some api changes * add decorate to noop * fix breaking proxy tests * experimental decorators for TS docs * api changes, fix unit + e2e tests * try removing global log mocks * add some util tests * remove logger mocks * add module tests + do not enable when not specified * fix eval metric integration test * wip * memoize getFunctionArguments * move any subscriber and global writer to the module enablement level instead of sdk * should fix TS tests * add ts integration test and fix decorator * devex for ts versions * add noop typescript test * remove startSpan * remove unneeded change * dedup decorator code * Update index.d.ts Co-authored-by: Yun Kim <35776586+Yun-Kim@users.noreply.github.com> * map metrics names * change validKind to validateKind and throw * tagger for metrics follow-up * review feedback * add some tests for not auto-annotating in certain cases --------- Co-authored-by: Yun Kim <35776586+Yun-Kim@users.noreply.github.com> * hard fail instead of soft fail, except for `wrap` span name * add ml-observability codeowners * resolve ts test * update auto-annotation check * tagger can soft fail * using custom ASL instance and scope activation * fix test comments and remove * address review comments * remove llmobs.apiKey config, only rely on global * fix evaulations test * make llmobs storage accessible --------- Co-authored-by: Yun Kim <35776586+Yun-Kim@users.noreply.github.com>
What does this PR do?
Introduces an LLM Observability SDK into the tracer, with its own tracing API extending the core tracer, and span tagging and processing functionality to flush LLM Observability spans to LLM Observability.
A corp/public documentation link will be added here once the SDK has been released and docs published, for visibility.
The following PRs have been merged into the branch for this PR, and have been reviewed and approved:
(config) #4696 APM: @ida613 LLMObs: @Yun-Kim
(writer) #4699 APM: @rochdev LLMObs: @Yun-Kim
(tagger) #4718 APM: @rochdev LLMObs @Yun-Kim
(span processing) #4738 APM: @rochdev LLMObs: @lievan
(sdk api) #4773 APM: @rochdev LLMObs: @Yun-Kim @lievan @Kyle-Verhoog
Submitting OpenAI spans will be a direct follow-up PR.
Motivation
Introduce core LLM Observability SDK logic into the tracer.