The committers listed above are authorized under a signed CLA.

• ✅ login: castlenthesky / name: Brian Henson (18ab8f6, 1a531dc, 5e4fe09, a2a5d92, c4e04e9, d72eaeb, e8ae53e, fb51058)
• ✅ login: lmolkova / name: Liudmila Molkova (5e4fe09, c4e04e9)

You might want to add the new metrics to docs/gen-ai/gen-ai-metrics.md.

See https://github.com/open-telemetry/semantic-conventions/blob/main/CONTRIBUTING.md#2-update-the-markdown-files on how to do that.

@kamphaus I updated the docs per your suggestion. Thanks for pointing that out.

@kamphaus Thanks for highlighting that template. I have pushed a correction. Please let me know if there are any other changes you'd like to see.

@lmolkova This most recent commit should get us across the finish line. Thanks for your patience.

@lmolkova I update the documentation, re-ran all checks outlined in the CONTRIBUTING.md file and submitted the new push. Thanks for your input.

@kamphaus Thanks for the final approval. I closed out all open conversations in case those were blocking the merge.
@lmolkova and @Cirilla-zmh - Thank you for your input and review.

Please let me know if there is anything else I need to do to have this successfully merged!

This PR talks about "chunks". What is the definition of "chunk"? Is that only about assistant content? Does it include reasoning if the model makes a distinction between reasoning and response text? Does it include any notification from the service, like a function call request (or a part of one)? Etc. My assumption is it's any packet of data from the llm, such that each update produced as part of a streaming implementation, regardless of what that update contains, counts as a "chunk".